Computers in Biology and Medicine

Dendrite cross attention for high-dose-rate brachytherapy distribution planning

Cervical cancer is a significant global health issue, and high-dose-rate brachytherapy (HDR-BT) is crucial for its treatment. However, manually creating HDR-BT plans is time-consuming and heavily relies on the planner's expertise, making standardization difficult. This study introduces two advanced deep learning models to address this need: Bi-branch Cross-Attention UNet (BiCA-UNet) and Dendrite Cross-Attention UNet (DCA-UNet). BiCA-UNet enhances the correlation between the CT scan and segmentation maps of the clinical target volume (CTV), applicator, bladder, and rectum. It uses two branches: one processes the stacked input of CT scans and segmentations, and the other focuses on the CTV segmentation. A cross-attention mechanism integrates these branches, improving the model's understanding of the CTV region for accurate dose predictions. Building on BiCA-UNet, DCA-UNet further introduces a primary branch of stacked inputs and three secondary branches for CTV, bladder, and rectum segmentations forming a dendritic structure. Cross attention with bladder and rectum segmentation helps the model understand the regions of organs at risk (OAR), refining dose prediction. Evaluation of these models using multiple metrics indicates that both BiCA-UNet and DCA-UNet significantly improve HDR-BT dose prediction accuracy for various applicator types. The cross-attention mechanisms enhance the feature representation of critical anatomical regions, leading to precise and reliable treatment plans. This research highlights the potential of BiCA-UNet and DCA-UNet in advancing HDR-BT planning, contributing to the standardization of treatment plans, and offering promising directions for future research to improve patient outcomes in the source data.

Cervical cancer diagnosis based on modified uniform local ternary patterns and feed forward multilayer network optimized by genetic algorithm

Cervical cancer is one of the most common types of cancer for women. Early and accurate diagnosis can save the patient's life. Pap smear testing is nowadays commonly used to diagnose cervical cancer. The type, structure and size of the cervical cells in pap smears images are major factors which are used by specialist doctors to diagnosis abnormality. Various image processing-based approaches have been proposed to acquire pap smear images and diagnose cervical cancer in pap smears images. Accuracy is usually the primary objective in evaluating the performance of these systems. In this paper, a two-stage method for pap smear image classification is presented. The aim of the first stage is to extract texture information of the cytoplasm and nucleolus jointly. For this purpose, the pap smear image is first segmented using the appropriate threshold. Then, a texture descriptor is proposed titled modified uniform local ternary patterns (MULTP), to describe the local textural features. Secondly, an optimized multi-layer feed-forward neural network is used to classify the pap smear images. The proposed deep neural network is optimized using genetic algorithm in terms of number of hidden layers and hidden nodes. In this respect, an innovative chromosome representation and cross-over process is proposed to handle these parameters. The performance of the proposed method is evaluated on the Herlev database and compared with many other efficient methods in this scope under the same validation conditions. The results show that the detection accuracy of the proposed method is higher than the compared methods. Insensitivity to image rotation is one of the major advantages of the proposed method. Results show that the proposed method has the capability to be used in online problems because of low run time. The proposed texture descriptor, MULTP is a general operator which can be used in many computer vision problems to describe texture properties of image. Also, the proposed optimization algorithm can be used in deep-networks to improve performance.

Bone marrow sparing oriented multi-model image registration in cervical cancer radiotherapy

Cervical cancer poses a serious threat to the health of women and radiotherapy is one of the primary treatment methods for this condition. However, this treatment is associated with a high risk of causing acute hematologic toxicity. Delineating the bone marrow (BM) for sparing based on computer tomography (CT) images before radiotherapy can effectively avoid this risk. Unfortunately, compared to magnetic resonance (MR) images, CT images lack the ability to express the activity of BM. Therefore, medical practitioners currently manually delineate the BM on CT images by corresponding to MR images. However, the manual delineation of BM is time-consuming and cannot guarantee accuracy due to the inconsistency of the CT-MR multimodal images. This study proposes a multimodal image-oriented automatic registration method for pelvic BM sparing. The proposed method includes three-dimensional (3D) bone point clouds reconstruction and an iterative closest point registration based on a local spherical system for marking BM on CT images. By introducing a joint coordinate system that combines the global Cartesian coordinate system with the local point clouds' spherical coordinate system, the increasement of point descriptive dimension avoids the local optimal registration and improves the registration accuracy. Experiments on the dataset of patients demonstrate that our proposed method can enhance the multimodal image registration accuracy and efficiency for medical practitioners in BM-sparing of cervical cancer radiotherapy. The method proposed in this contribution might also provide a solution to multimodal registration, especially in multimodal sequential images in other clinical applications, such as the diagnosis of cervical cancer and the preservation of normal organs during radiotherapy.

Repurposing of PI3K inhibitors for high-grade serous ovarian cancer: A novel competing endogenous network analysis-based approach

The average survival time for High-Grade Serous Ovarian Cancer (HGSOC) is around 3.4 years post-diagnosis. The treatment options are limited, especially for relapsed patients, resistant to standard treatment. Therefore, novel drug candidates are needed. We propose a novel approach for predicting potential drug candidates by focusing on agents capable of reversing the effects of perturbed RNA network. The competing endogenous RNA (ceRNAs) network was constructed on differential expression (DE) of long non-coding RNAs (lncRNAs), protein-coding RNAs (mRNAs) and microRNAs (miRNAs) from the primary HGSOC tumour tissues. It allowed for identification of key perturbed axes of RNA regulation. The publicly available resources for drug repurposing were used to select candidates for in-vitro validation. The phosphoinositide 3-kinase (PI3K) pathway, known to be involved in developing drug resistance in ovarian cancer, was identified as highly dependent from the coding and non-coding RNA interactions. PI3K pathway inhibitors, PI-103 and ZSTK474, were identified as drug candidates and their efficacy against HGSOC was confirmed in vitro. E2F1 and SNAI2 are essential transcription factors (TFs) known for regulating critical cancer pathways such as cell cycle repair or epithelial-mesenchymal transition (EMT). In our study, these TFs were identified as hub regulators within the ceRNA network. Investigation of fine-tune regulation of RNA by non-coding RNAs and TFs uncovered a significant role of ceRNA network in cancer development, highlighting its integration with master regulatory pathways that drive tumor progression and sustainability. The drug repurposing workflow based on ceRNA-limited differentially expressed mRNAs allowed for effective prioritization of compounds with potential to be applied as treatment.

Global trends in endometrial cancer and metabolic syndrome research: A bibliometric and visualization analysis

Currently, many studies have shown that there is a link between metabolic syndrome (MetS) and endometrial cancer (EC). However, there has been no systematic bibliometric analysis of related publications, which limits the comprehensive understanding of research trends and priorities. Our study makes up for this problem. Through bibliometric analysis, this study aimed to reveal key research focus areas, developmental trends, and major contributors of EC and MetS. The literature for this study was obtained from the Web of Science Core Collection (WoSCC) through August 31, 2024. We searched for EC and MetS using subject and free terms. Microsoft Office Excel 2016, CiteSpace, and VOSviewer software packages were used for bibliometric analysis, considering specific characteristics such as year of publication, country, institution, authorship, journal, references, and keywords. A total of 367 publications were included. Annual publications exhibited exponential growth (R2 = 0.8282), indicatingsustained interest in the field. The United States (111 publications), China (80), and Italy (38) were the most productive countries. The University of California System led institutional contributions. Keyword co-occurrence and burst analysis revealed that obesity (occurrence: 113; link strength: 630), insulin resistance (112; 587), and polycystic ovary syndrome (83; 386) were the most frequent and interconnected research foci. Emerging trends, identified through keyword time-zone mapping (average citation year: 2015-2019), highlighted weight control and bariatric surgery as novel interventions. Journals with the highest impact included ∗Fertility and Sterility∗ (IF: 6.6) and ∗International Journal of Epidemiology (IF: 6.4). This study conducted a preliminary bibliometric and visual analysis of the EC and MetS research literature, revealing trends, global cooperation models, fundamental knowledge, and emerging frontiers of EC and MetS. For over 30 years, research has mainly focused on the correlation between MetS and EC, disease factors, prognosis, prevention, and other aspects that have guiding significance for public health.

Prediction of a radiomics-based nomogram for complete remission in atypical endometrial hyperplasia and early endometrial cancer patients seeking fertility preservation

Fertility-sparing treatments are becoming increasingly important for patients worldwide with atypical endometrial hyperplasia (AEH) and early endometrial cancer (EC). The primary aim of these treatments is to achieve complete regression (CR). Accurately predicting CR and applying effective treatment strategies throughout the process are crucial for successful fertility preservation in these patients. In our cohort, we included 155 patients and selected six radiomic features strongly correlated with CR from over 1500 MRI-based features. Tn area under the curve (AUC) value of MR score achieved up to 0.871. We then incorporated MR scores and clinical factors into a nomogram, demonstrating a strong predictive performance. With the introduction of MR score, the AUC value reached as high as 0.871, indicating a significant improvement in net benefit. In summary, we introduced an innovative MR score and developed a nomogram that significantly improves predictive accuracy for the likelihood of CR in patients seeking fertility preservation. Moving forward, we plan to establish a multicenter patient cohort to further refine this model and support its broader implementation in clinical practice following thorough evaluation.

Computer-aided diagnosis of low grade endometrial stromal sarcoma (LGESS)

Low grade endometrial stromal sarcoma (LGESS) accounts for about 0.2% of all uterine cancer cases. Approximately 75% of LGESS patients are initially misdiagnosed with leiomyoma, which is a type of benign tumor, also known as fibroids. In this research, uterine tissue biopsy images of potential LGESS patients are preprocessed using segmentation and stain normalization algorithms. We then apply a variety of classic machine learning and advanced deep learning models to classify tissue images as either benign or cancerous. For the classic techniques considered, the highest classification accuracy we attain is about 0.85, while our best deep learning model achieves an accuracy of approximately 0.87. These results clearly indicate that properly trained learning algorithms can aid in the diagnosis of LGESS.

Multi-strategy assisted chaotic coot-inspired optimization algorithm for medical feature selection: A cervical cancer behavior risk study

Real-world optimization problems require some advanced metaheuristic algorithms, which functionally sustain a variety of solutions and technically explore the tracking space to find the global optimal solution or optimizer. One such algorithm is the newly developed COOT algorithm that is used to solve complex optimization problems. However, like other swarm intelligence algorithms, the COOT algorithm also faces the issues of low diversity, slow iteration speed, and stagnation in local optimization. In order to ameliorate these deficiencies, an improved population-initialized COOT algorithm named COBHCOOT is developed by integrating chaos map, opposition-based learning strategy and hunting strategy, which are used to accelerate the global convergence speed and boost the exploration efficiency and solution quality of the algorithm. To validate the dominance of the proposed COBHCOOT, it is compared with the original COOT algorithm and the well-known natural heuristic optimization algorithm on the recognized CEC2017 and CEC2019 benchmark suites, respectively. For the 29 CEC2017 problems, COBHCOOT performed the best in 15 (51.72%, 30-Dim), 14 (48.28%, 50-Dim) and 11 (37.93%, 100-Dim) respectively, and for the 10 CEC2019 benchmark functions, COBHCOOT performed the best in 7 of them. Furthermore, the practicability and potential of COBHCOOT are also highlighted by solving two engineering optimization problems and four truss structure optimization problems. Eventually, to examine the validity and performance of COBHCOOT for medical feature selection, eight medical datasets are used as benchmarks to compare with other superior methods in terms of average accuracy and number of features. Particularly, COBHCOOT is applied to the feature selection of cervical cancer behavior risk dataset. The findings testified that COBHCOOT achieves better accuracy with a minimal number of features compared with the comparison methods.

Monte Carlo Tree Search for optimal cancer intervention strategies among BRCA mutation carriers

Breast and ovarian cancers are the second and fifth leading causes of cancer-related death among women in the United States. Compared to non-carriers, BRCA mutation carriers are subject to a higher risk of developing breast and ovarian cancers. Prophylactic surgeries including prophylactic mastectomy and prophylactic bilateral salpingo-oophorectomy can significantly reduce the incidence risks of breast and ovarian cancers for BRCA mutation carriers. However, both prophylactic surgeries are permanent one-time interventions. Determining the optimal age for BRCA carriers to undergo such surgeries is critical. The optimal solution depends on sequential decision-making over long periods during a patient's life involving the cancer incidence risk and quality of life (QOL). Thus, there is an urgent need to develop an optimal cancer intervention strategy with the goal to reduce cancer risk and maintain a high-level QOL. This paper presents a novel sequential decision-making framework for BRCA mutation carriers by jointly considering the two objectives. We first propose to model the dynamic progression of cancer risk using a continuous-time Markov Decision Process. Second, we propose to solve for the optimal intervention strategies through Monte Carlo Tree Search (MCTS) by optimally balancing the exploitation of current knowledge and exploration of uncertainty factors about the cancer state. Experimental results show that the proposed MCTS planning method can effectively provide optimal sequential intervention strategies for BRCA mutation carriers, reducing the risk of cancer incidence while maintaining a high-level QOL.

Computer-aided drug discovery of a dual-target inhibitor for ovarian cancer: therapeutic intervention targeting CDK1/TTK signaling pathway and structural insights in the NCI-60

Ovarian cancer remains the third most prevalent and deadliest gynecologic malignancy worldwide, with most patients eventually developing resistance to platinum-based chemotherapy. This highlights a critical unmet need for innovative multitargeted therapies to address current treatment challenges. In this study, we identified 35 differentially expressed genes (DEGs) through integrated analysis of four GEO ovarian cancer datasets, with validation using TCGA data. Gene Ontology (GO) and KEGG enrichment analyses highlighted key tumor-associated pathways, and protein-protein interaction (PPI) network modeling prioritized CDK1 and TTK as high-value therapeutic targets. We evaluated the association between molecular genomic features and drug responses across the NCI-60 ovarian cancer cell line panel (IGROV1, OVCAR-3, OVCAR-4, OVCAR-5, OVCAR-8, NCI/ADR-RES, and SK-OV-3), using a series of salicylanilide-derived compounds and four FDA-approved drugs (cabozantinib, paclitaxel, rapamycin, and niclosamide) from the NCI Developmental Therapeutics Program (DTP). Among these, NSC765690 (MCC22) emerged as the most promising candidate. It demonstrated potent antiproliferative activity, high target selectivity, and strong binding affinity to both CDK1 and TTK. Multi-omics integration, combined with AI-driven network modeling, further elucidated NSC765690's mechanism of action and its relevance to ovarian cancer pathogenesis. Additionally, ADMET and pharmacokinetic profiling confirmed its favorable drug-like properties and low predicted toxicity. Collectively, these findings establish NSC765690 as a potent dual-target inhibitor and exemplify a rational, data-driven drug discovery pipeline for overcoming chemotherapy resistance in ovarian cancer.

Overexpression of miR-23b–3p+miR-218-5p+miR-124-3p differentially modifies the transcriptome of C-33A and CaSki cells and the regulation of cellular processes involved in the progression of cervical cancer

Dysregulation of tumor suppressor miRNAs (tsmiRs) is associated with tumor progression in cancer. miR-23b-3p, miR-218-5p and miR-124-3p are tsmiRs in cervical cancer (CC) and regulate the translation of genes involved in metastasis-related biological processes. To analyze transcriptome changes in cervical cancer cell lines (C-33A HPV-negative and CaSki HPV-positive) overexpressing miR-23b-3p + miR-218-5p + miR-124-3p, to identify specific target transcripts common to all three miRNAs, as well as signaling pathways and cellular processes related to tumor progression. The transcriptome of C-33A and CaSki cells transfected with miR-23b-3p + miR-218-5p + miR-124-3p was analyzed by RNA-seq. Differentially expressed genes (DEGs) were subjected to Gene Ontology analysis on the DAVID platform. The function of under-regulated genes was analyzed on the GEPIA 2.0, Kaplan-Meier plotter and STRING platforms. On the TargetScanHuman platform it was determined which transcripts have MREs for miR-23b-3p, miR-218-5p and/or miR-124-3p in their 3'UTR region. Simultaneous overexpression of miR-218-5p, miR-124-3p and miR-23b-3p induced changes in global gene expression in C-33A and CaSki cells. In C-33A cells, DEGs included 45 over- and 172 under-regulated transcripts; in CaSki, 125 transcripts were over- and 84 under-regulated. The under-regulated transcripts enrich proliferation, migration, apoptosis and angiogenesis; 20 of these genes are associated with overall survival (OS) in women with CC, and 18 of the 20 mRNAs have MREs for one, two or all three miRNAs. miR-23b-3p + miR-218-5p + miR-124-3p, differentially modify global gene expression in C-33A and CaSki cells. The results indicate that these miRNAs act synergistically and modulate CC progression through individual and shared targets by two or all three miRNAs.

OCDet: A comprehensive ovarian cell detection model with channel attention on immunohistochemical and morphological pathology images

Ovarian cancer is among the most lethal gynecologic malignancy that threatens women's lives. Pathological diagnosis is a key tool for early detection and diagnosis of ovarian cancer, guiding treatment strategies. The evaluation of various ovarian cancer-related cells, based on morphological and immunohistochemical pathology images, is deemed an important step. Currently, the lack of a comprehensive deep learning framework for detecting various ovarian cells poses a performance bottleneck in ovarian cancer pathological diagnosis. This paper presents OCDet, an object detection model with channel attention, which achieves comprehensive detection of CD3, CD8, and CD20 positive lymphocytes in immunohistochemical pathology slides, and neutrophils and polyploid giant cancer cells in H&E slides of ovarian cancer. OCDet, utilizing CSPDarkNet as its backbone, incorporates an Efficient Channel Attention module for Resolution-Specified Embedding Refinement and Multi-Resolution Embedding Fusion, enabling the efficient extraction of pathological features. The experiment demonstrated that OCDet performed well in target detection of three types of positive lymphocytes in immunohistochemical images, as well as neutrophils and polyploid giant cancer cells in H&E images. The mAP@0.5 reached 98.82 %, 92.91 %, and 90.49 % respectively, all surpassing other compared models. The ablation experiment further highlighted the superiority of the introduced Efficient Channel Attention (ECA) mechanism. The proposed OCDet enables accurate detection of multiple types of cells in immunohistochemical and morphological pathology images of ovarian cancer, serving as an efficient application tool for pathological diagnosis thereof. The proposed framework has the potential to be further applied to other cancer types.

DSFF-GAN: A novel stain transfer network for generating immunohistochemical image of endometrial cancer

Immunohistochemistry (IHC) is a commonly used histological examination technique. Compared to Hematoxylin and Eosin (H&E) staining, it enables the examination of protein expression and localization in tissues, which is valuable for cancer treatment and prognosis assessment, such as the detection and diagnosis of endometrial cancer. However, IHC involves multiple staining steps, is time-consuming and expensive. One potential solution is to utilize deep learning networks to generate corresponding virtual IHC images from H&E images. However, the similarity of the IHC image generated by the existing methods needs to be further improved. In this work, we propose a novel dual-scale feature fusion (DSFF) generative adversarial network named DSFF-GAN, which comprises a cycle structure-color similarity loss, and DSFF block to constrain the model's training process and enhance its stain transfer capability. In addition, our method incorporates labeling information of positive cell regions as prior knowledge into the network to further improve the evaluation metrics. We train and test our model using endometrial cancer and publicly available breast cancer IHC datasets, and compare it with state-of-the-art methods. Compared to previous methods, our model demonstrates significant improvements in most evaluation metrics on both datasets. The research results show that our method further improves the quality of image generation and has potential value for the future clinical application of virtual IHC images.

Genome-wide perturbations of A-to-I RNA editing dysregulated circular RNAs promoting the development of cervical cancer

Cervical cancer, the second most common female malignant tumor, seriously threatens women's health and lives. Despite the availability of the HPV vaccine, effective treatment options for cervical cancer are still lacking. New research perspectives now clarify that RNA editing dysregulation and changes in circRNA expression are jointly involved in disease pathogenesis, so molecular changes associated with circRNA and RNA editing may provide clues for the development of new therapeutic strategies for cervical cancer. In this study, we designed a series of pipelines to identify and analyze dysregulated RNA editing events in circRNAs. Our findings indicate a decrease in A-to-I RNA editing levels in cervical cancer compared to normal tissues, and editing may influence the back-splicing process of circRNAs through structural modifications of Alu elements. Moreover, our research reveals that RNA editing could modulate circRNA biogenesis by influencing RNA binding protein (RBP) binding on a transcriptome-wide scale, as well as influence the expression and coding potential of circRNAs. Importantly, we identified three RNA editing sites that could serve as potential biomarkers. In summary, our study presents a comprehensive landscape of RNA editing perturbations in circRNAs, providing new insights into the complex relationship between RNA editing and circRNA dysregulation in cervical cancer.

Exploration of pyroptosis-associated prognostic gene signature and lncRNA regulatory network in ovarian cancer

Ovarian cancer (OC), is a tumor that poses a serious threat to women's health due to its high mortality rate and bleak prognosis. Pyroptosis, a type of programmed cell death, is important for determining the prognosis of a patient's prognosis for cancer and may represent a novel target for treatment. However, research into how prognosis is impacted by pyroptosis-related genes (PRGs) is poorly understood. In this study, a prognostic model was created using bioinformatic analysis of PRGs in OC. In OC, we discovered 18 pyroptosis regulators that were either up- or down-regulated. By analyzing prognoses, we developed a 9-genes based prognostic model. Each OC patient received a risk score that could be used to categorize them into two subgroups: those with high risk and/or low chance of survival and those with low risk and/or high chance of survival. Functional enrichment and immunoinfiltration analysis indicated that low expression of immune pathways in high-risk group may account for the decrease of survival possibility. In Multivariable cox regression studies, age, clinical stage and the prognostic model were discovered to be independent factors impacting the prognosis for OC. To forecast OC patient survival, a predictive nomogram was developed. Furthermore, we found a correlation between predictive PRGs and clinical stage, indicating that AIM2, CASP3, ZBP1 and CASP8 may play a role in the growth of tumor in OC. After detailed and complete bioinformatics analysis, the lncRNA RP11-186B7.4/hsa-miR-449a/CASP8/AIM2/ZBP1 regulatory axis was identified in OC. Our study may provide a novel approach for prognostic biomarkers and therapeutic targets of OC.

Cytokine gene variants and socio-demographic characteristics as predictors of cervical cancer: A machine learning approach

Cervical cancer is still one of the most prevalent cancers in women and a significant cause of mortality. Cytokine gene variants and socio-demographic characteristics have been reported as biomarkers for determining the cervical cancer risk in the Indian population. This study was designed to apply a machine learning-based model using these risk factors for better prognosis and prediction of cervical cancer. This study includes the dataset of cytokine gene variants, clinical and socio-demographic characteristics of normal healthy control subjects, and cervical cancer cases. Different risk factors, including demographic details and cytokine gene variants, were analysed using different machine learning approaches. Various statistical parameters were used for evaluating the proposed method. After multi-step data processing and random splitting of the dataset, machine learning methods were applied and evaluated with 5-fold cross-validation and also tested on the unseen data records of a collected dataset for proper evaluation and analysis. The proposed approaches were verified after analysing various performance metrics. The logistic regression technique achieved the highest average accuracy of 82.25% and the highest average F1-score of 82.58% among all the methods. Ridge classifiers and the Gaussian Naïve Bayes classifier achieved the highest sensitivity-85%. The ridge classifier surpasses most of the machine learning classifiers with 84.78% accuracy and 97.83% sensitivity. The risk factors analysed in this study can be taken as biomarkers in developing a cervical cancer diagnosis system. The outcomes demonstrate that the machine learning assisted analysis of cytokine gene variants and socio-demographic characteristics can be utilised effectively for predicting the risk of developing cervical cancer.

Application of artificial intelligence in the diagnosis and prognostic prediction of ovarian cancer

In recent years, the wide application of artificial intelligence (AI) has dramatically improved the work efficiency of clinicians and reduced their workload. This review provides a glance at the latest advances in AI-assisted diagnosis and prognostic prediction of ovarian cancer (OC). We performed an advanced search in PubMed and IEEE/IET Electronic Library, and included 39 articles in this review. A comprehensive and objective criterion was built to assess the reliability and quality of all studies from four aspects: the size of datasets for model development, research design, the division of training sets and test sets, and the type of quantitative performance indicators. This review analyzed the construction of AI models, including data pre-processing methods, feature selection techniques, AI classifiers, or algorithms. Additionally, we compared the performance of these models built on different datasets, which may support researchers for further iteration and development of AI. Finally, we discussed the challenges and future directions for AI application in medicine.

Is the aspect ratio of cells important in deep learning? A robust comparison of deep learning methods for multi-scale cytopathology cell image classification: From convolutional neural networks to visual transformers

Cervical cancer is a very common and fatal type of cancer in women. Cytopathology images are often used to screen for this cancer. Given that there is a possibility that many errors can occur during manual screening, a computer-aided diagnosis system based on deep learning has been developed. Deep learning methods require a fixed dimension of input images, but the dimensions of clinical medical images are inconsistent. The aspect ratios of the images suffer while resizing them directly. Clinically, the aspect ratios of cells inside cytopathological images provide important information for doctors to diagnose cancer. Therefore, it is difficult to resize directly. However, many existing studies have resized the images directly and have obtained highly robust classification results. To determine a reasonable interpretation, we have conducted a series of comparative experiments. First, the raw data of the SIPaKMeD dataset are pre-processed to obtain standard and scaled datasets. Then, the datasets are resized to 224 × 224 pixels. Finally, 22 deep learning models are used to classify the standard and scaled datasets. The results of the study indicate that deep learning models are robust to changes in the aspect ratio of cells in cervical cytopathological images. This conclusion is also validated via the Herlev dataset.

DeepCervix: A deep learning-based framework for the classification of cervical cells using hybrid deep feature fusion techniques

Cervical cancer, one of the most common fatal cancers among women, can be prevented by regular screening to detect any precancerous lesions at early stages and treat them. Pap smear test is a widely performed screening technique for early detection of cervical cancer, whereas this manual screening method suffers from high false-positive results because of human errors. To improve the manual screening practice, machine learning (ML) and deep learning (DL) based computer-aided diagnostic (CAD) systems have been investigated widely to classify cervical Pap cells. Most of the existing studies require pre-segmented images to obtain good classification results. In contrast, accurate cervical cell segmentation is challenging because of cell clustering. Some studies rely on handcrafted features, which cannot guarantee the classification stage's optimality. Moreover, DL provides poor performance for a multiclass classification task when there is an uneven distribution of data, which is prevalent in the cervical cell dataset. This investigation has addressed those limitations by proposing DeepCervix, a hybrid deep feature fusion (HDFF) technique based on DL, to classify the cervical cells accurately. Our proposed method uses various DL models to capture more potential information to enhance classification performance. Our proposed HDFF method is tested on the publicly available SIPaKMeD dataset and compared the performance with base DL models and the late fusion (LF) method. For the SIPaKMeD dataset, we have obtained the state-of-the-art classification accuracy of 99.85%, 99.38%, and 99.14% for 2-class, 3-class, and 5-class classification. This method is also tested on the Herlev dataset and achieves an accuracy of 98.32% for 2-class and 90.32% for 7-class classification. The source code of the DeepCervix model is available at: https://github.com/Mamunur-20/DeepCervix.

Diagnosis of cervical precancerous lesions based on multimodal feature changes

To realize the automatic diagnosis of cervical intraepithelial neoplasia (CIN) cases by preacetic acid test and postacetic acid test colposcopy images, this paper proposes a method of cervical precancerous lesion diagnosis based on multimodal feature changes. First, the preacetic acid test and postacetic acid test colposcopy images were registered based on cross-correlation and projection transformation, and then the cervical region was extracted by the k-means clustering algorithm. Finally, a deep learning network was used to extract features and classify the preacetic acid test and postacetic acid test cervical images after registration. Finally, the proposed method achieves a classification accuracy of 86.3%, a sensitivity of 84.1%, and a specificity of 89.8% in 60 test cases. Experimental results show that this method can make better use of the multimodal features of colposcopy images and has lower requirements for medical staff in the process of data acquisition. It has certain clinical significance in cervical cancer precancerous lesion screening systems.

LFANet: Lightweight feature attention network for abnormal cell segmentation in cervical cytology images

With the widely applied computer-aided diagnosis techniques in cervical cancer screening, cell segmentation has become a necessary step to determine the progression of cervical cancer. Traditional manual methods alleviate the dilemma caused by the shortage of medical resources to a certain extent. Unfortunately, with their low segmentation accuracy for abnormal cells, the complex process cannot realize an automatic diagnosis. In addition, various methods on deep learning can automatically extract image features with high accuracy and small error, making artificial intelligence increasingly popular in computer-aided diagnosis. However, they are not suitable for clinical practice because those complicated models would result in more redundant parameters from networks. To address the above problems, a lightweight feature attention network (LFANet), extracting differentially abundant feature information of objects with various resolutions, is proposed in this study. The model can accurately segment both the nucleus and cytoplasm regions in cervical images. Specifically, a lightweight feature extraction module is designed as an encoder to extract abundant features of input images, combining with depth-wise separable convolution, residual connection and attention mechanism. Besides, the feature layer attention module is added to precisely recover pixel location, which employs the global high-level information as a guide for the low-level features, capturing dependencies of channel features. Finally, our LFANet model is evaluated on all four independent datasets. The experimental results demonstrate that compared with other advanced methods, our proposed network achieves state-of-the-art performance with a low computational complexity.

KS-TMIL: A K-Stage Transformer approach with multiple instance learning model for ovarian cancer subtype classification

Existing multiple instance learning (MIL) methods treat whole slide image (WSI) as collections of independent patches, neglecting these crucial spatial and morphological connections. This paper proposes K-Stage Transformer with multiple instance learning framework (KS-TMIL) that leverages the power of transformers. Unlike traditional MIL methods, KS-TMIL excels at modeling relationships between patches within a WSI. This capability is achieved through a multi-stage transformer that incorporates inception based position encoding generator (IBPEG) block. This enables KS-TMIL to effectively leverage the weakly supervised labels and achieve accurate classifications. KS-TMIL offers a family of models with varying numbers of transformer layers, catering to different classification tasks. The evaluation is conducted using publicly available Kaggle dataset "UBC ovarian cancer subtype classification and outlier detection", demonstrating the effectiveness of the proposed model with an AUC and balanced accuracy of 99% and 93.3% respectively.

Identifying miRNA as biomarker for breast cancer subtyping using association rule

Unraveling the role of tissue colonized microbiome in ovarian cancer progression

Ovarian cancer (OC) is found to be the third most common gynecologic malignancy over the world, having the highest mortality rate among such tumors. Emerging studies underscore the presence of microorganisms within tumor tissues, with certain pathogens intricately linked to disease onset and progression. Disruption of the microbiome frequently precipitates disturbances in host metabolic and immune pathways, thereby fostering the development of cancer. In this study, we initiated the investigation by conducting microbial reannotation on the RNA sequencing data derived from ovarian cancer tissues. Subsequently, a comprehensive array of analyses on tissue microbes was executed. These analyses encompassed the assessment of intergroup variations in microbial diversity, differential microbiological analysis, exploration of the association between host gene expression and microbial abundance, as well as an enrichment analysis of functional pathways linked to host genes associated with microbes. The analysis results revealed that Proteobacteria, Actinobacteria, Firmicutes, and Bacteroidetes were the main components at phylum level in ovarian tissue. Notably, the microbial composition of ovarian cancer tissue significantly diverged from that of normal ovarian tissue e, exhibiting markedly lower alpha diversity and distinct beta diversity. Besides, pathogenic microorganisms Achromobacter xylosoxidans and Enterobacter hormaechei were enriched in cancer tissue. Host genes associated with these pathogens were enriched in key pathways including "JAK-STAT signaling pathway", "Transcriptional misregulation in cancer", and "Th1 and Th2 cell differentiation", suggesting their role in ovarian cancer progression through microbial dysbiosis and immune response interaction. Abundance of pathogenic microorganisms in ovarian cancer tissue could modulate the expression of host genes, consequently impacting cancer-related signaling pathways and fostering cancer progression.

Gene selection and cancer classification using interaction-based feature clustering and improved-binary Bat algorithm

Intra-sample reversed pairs based on differentially ranked genes reveal biosignature for ovarian cancer

Ovarian cancer, a major gynecological malignancy, often remains undetected until advanced stages, necessitating more effective early screening methods. Existing biomarker based on differential genes often suffers from variations in clinical practice. To overcome the limitations of absolute gene expression values including batch effects and biological heterogeneity, we introduced a pairwise biosignature leveraging intra-sample differentially ranked genes (DRGs) and machine learning for ovarian cancer detection across diverse cohorts. We analyzed ten cohorts comprising 872 samples with 796 ovarian cancer and 76 normal. Our method, DRGpair, involves three stages: intra-sample ranking differential analysis, reversed gene pair analysis, and iterative LASSO regression. We identified four DRG pairs, demonstrating superior diagnostic performance compared to current state-of-the-art biomarkers and differentially expressed genes in seven independent cohorts. This rank-based approach not only reduced computational complexity but also enhanced the specificity and effectiveness of biomarkers, revealing DRGs as promising candidates for ovarian cancer detection and offering a scalable model adaptable to varying cohort characteristics.

Developing a novel image marker to predict the clinical outcome of neoadjuvant chemotherapy (NACT) for ovarian cancer patients

Neoadjuvant chemotherapy (NACT) is one kind of treatment for advanced stage ovarian cancer patients. However, due to the nature of tumor heterogeneity, the clinical outcomes to NACT vary significantly among different subgroups. Partial responses to NACT may lead to suboptimal debulking surgery, which will result in adverse prognosis. To address this clinical challenge, the purpose of this study is to develop a novel image marker to achieve high accuracy prognosis prediction of NACT at an early stage. For this purpose, we first computed a total of 1373 radiomics features to quantify the tumor characteristics, which can be grouped into three categories: geometric, intensity, and texture features. Second, all these features were optimized by principal component analysis algorithm to generate a compact and informative feature cluster. This cluster was used as input for developing and optimizing support vector machine (SVM) based classifiers, which indicated the likelihood of receiving suboptimal cytoreduction after the NACT treatment. Two different kernels for SVM algorithm were explored and compared. A total of 42 ovarian cancer cases were retrospectively collected to validate the scheme. A nested leave-one-out cross-validation framework was adopted for model performance assessment. The results demonstrated that the model with a Gaussian radial basis function kernel SVM yielded an AUC (area under the ROC [receiver characteristic operation] curve) of 0.806 ± 0.078. Meanwhile, this model achieved overall accuracy (ACC) of 83.3%, positive predictive value (PPV) of 81.8%, and negative predictive value (NPV) of 83.9%. This study provides meaningful information for the development of radiomics based image markers in NACT treatment outcome prediction.

ECPC-IDS: A benchmark endometrial cancer PET/CT image dataset for evaluation of semantic segmentation and detection of hypermetabolic regions

Endometrial cancer is one of the most common tumors in the female reproductive system and is the third most common gynecological malignancy that causes death after ovarian and cervical cancer. Early diagnosis can significantly improve the 5-year survival rate of patients. With the development of artificial intelligence, computer-assisted diagnosis plays an increasingly important role in improving the accuracy and objectivity of diagnosis and reducing the workload of doctors. However, the absence of publicly available image datasets restricts the application of computer-assisted diagnostic techniques. In this paper, a publicly available Endometrial Cancer PET/CT Image Dataset for Evaluation of Semantic Segmentation and Detection of Hypermetabolic Regions (ECPC-IDS) are published. Specifically, the segmentation section includes PET and CT images, with 7159 images in multiple formats totally. In order to prove the effectiveness of segmentation on ECPC-IDS, six deep learning semantic segmentation methods are selected to test the image segmentation task. The object detection section also includes PET and CT images, with 3579 images and XML files with annotation information totally. Eight deep learning methods are selected for experiments on the detection task. This study is conduct using deep learning-based semantic segmentation and object detection methods to demonstrate the distinguishability on ECPC-IDS. From a separate perspective, the minimum and maximum values of Dice on PET images are 0.546 and 0.743, respectively. The minimum and maximum values of Dice on CT images are 0.012 and 0.510, respectively. The target detection section's maximum mAP values on PET and CT images are 0.993 and 0.986, respectively. As far as we know, this is the first publicly available dataset of endometrial cancer with a large number of multi-modality images. ECPC-IDS can assist researchers in exploring new algorithms to enhance computer-assisted diagnosis, benefiting both clinical doctors and patients. ECPC-IDS is also freely published for non-commercial at: https://figshare.com/articles/dataset/ECPC-IDS/23808258.

CytoGAN: Unpaired staining transfer by structure preservation for cytopathology image analysis

With the development of digital pathology, deep learning is increasingly being applied to endometrial cell morphology analysis for cancer screening. And cytology images with different staining may degrade the performance of these analysis algorithms. To address the impact of staining patterns, many strategies have been proposed and hematoxylin and eosin (H&E) images have been transferred to other staining styles. However, none of the existing methods are able to generate realistic cytological images with preserved cellular layout, and many important clinical structural information is lost. To address the above issues, we propose a different staining transformation model, CytoGAN, which can quickly and realistically generate images with different staining styles. It includes a novel structure preservation module that preserves the cell structure well, even if the resolution or cell size between the source and target domains do not match. Meanwhile, a stain adaptive module is designed to help the model generate realistic and high-quality endometrial cytology images. We compared our model with ten state-of-the-art stain transformation models and evaluated by two pathologists. Furthermore, in the downstream endometrial cancer classification task, our algorithm improves the robustness of the classification model on multimodal datasets, with more than 20 % improvement in accuracy. We found that generating specified specific stains from existing H&E images improves the diagnosis of endometrial cancer. Our code will be available on github.

Computational identification of DNA damage-relevant lncRNAs for predicting therapeutic efficacy and clinical outcomes in cancer

Weakly supervised segmentation of uterus by scribble labeling on endometrial cancer MR images

Uterine segmentation of endometrial cancer MR images can be a valuable diagnostic tool for gynecologists. However, uterine segmentation based on deep learning relies on artificial pixel-level annotation, which is time-consuming, laborious and subjective. To reduce the dependence on pixel-level annotation, a method of weakly supervised uterine segmentation on endometrial cancer MRI slices is proposed, which only requires scribble label and is enhanced by pseudo-label technology, exponential geodesic distance loss and input disturbance strategy. Specifically, the limitations caused by the shortage of supervision are addressed by dynamically mixing the two outputs of the dual branch network to generate pseudo-labels, expanding supervision information and promoting mutual supervision training. On the other hand, considering the large difference of grayscale intensity between the uterus and surrounding tissues, the exponential geodesic distance loss is introduced to enhance the ability of the network to capture the edge of the uterus. Input disturbance strategies are incorporated to adapt to the flexible and variable characteristics of the uterus and further improve the segmentation performance of the network. The proposed method is evaluated on MRI images from 135 cases of endometrial cancer. Compared with other four weakly supervised segmentation methods, the performance of the proposed method is the best, whose mean DI, HD

Biomarkers discovery for endometrial cancer: A graph convolutional sample network method

Endometrial carcinoma is the sixth most common cancer in women worldwide. Importantly, endometrial cancer is among the few types of cancers with patient mortality that is still increasing, which indicates that the improvement in its diagnosis and treatment is still urgent. Moreover, biomarker discovery is essential for precise classification and prognostic prediction of endometrial cancer. A novel graph convolutional sample network method was used to identify and validate biomarkers for the classification of endometrial cancer. The sample networks were first constructed for each sample, and the gene pairs with high frequencies were identified to construct a subtype-specific network. Putative biomarkers were then screened using the highest degrees in the subtype-specific network. Finally, simplified sample networks are constructed using the biomarkers for the graph convolutional network (GCN) training and prediction. Putative biomarkers (23) were identified using the novel bioinformatics model. These biomarkers were then rationalised with functional analyses and were found to be correlated to disease survival with network entropy characterisation. These biomarkers will be helpful in future investigations of the molecular mechanisms and therapeutic targets of endometrial cancers. A novel bioinformatics model combining sample network construction with GCN modelling is proposed and validated for biomarker discovery in endometrial cancer. The model can be generalized and applied to biomarker discovery in other complex diseases.

Glycosyltransferase-related prognostic and diagnostic biomarkers of uterine corpus endometrial carcinoma

Uterine corpus endometrial carcinoma (UCEC) has a strong ability of invasion and metastasis, high recurrence rate, and poor survival. Glycosyltransferases are one of the most important enzymes that coordinate the glycosylation process, and abnormal modification of proteins by glycosyltransferases is closely related to the occurrence and development of cancer. However, there were fewer reports on glycosyltransferase related biomarkers in UCEC. In this paper, based on the UCEC transcriptome data published on The Cancer Genome Atlas (TCGA), we predicted the relationship between the expression of glycosyltransferase-related genes (GTs) and the diagnosis and prognosis of UCEC using bioinformatics methods. And validation of model genes by clinical samples. We used 4 methods: generalized linear model (GLM), random forest (RF), support vector machine (SVM) and extreme gradient boosting (XGB) to screen biomarkers with diagnostic significance, and the binary logistic regression was used to establish a diagnostic model for the 2-GTs (AUC = 0.979). And the diagnostic model was validated using a GEO external database (AUC = 0.978). Moreover, a prognostic model for the 6-GTs was developed using univariate, Lasso, and multivariate Cox regression analyses, and the model was made more stable by internal validation using the bootstrap. In addition, risk score is closely related to immune microenvironment (TME), immune infiltration, mutation, immunotherapy and chemotherapy. Overall, this study provides novel biomarkers for the diagnosis and prognosis of UCEC, and the models established by these biomarkers can also provide a good reference for individualized and precision medicine in UCEC.

A novel five-gene metabolism-related risk signature for predicting prognosis and immune infiltration in endometrial cancer: A TCGA data mining

Metabolism dysfunction can affect the biological behavior of tumor cells and result in carcinogenesis and the development of various cancers. However, few thoughtful studies focus on the predictive value and efficacy of immunotherapy of metabolism-related gene signatures in endometrial cancer (EC). This research aims to construct a predictive metabolism-related gene signature in EC with prognostic and therapeutic implications. We downloaded the RNA profile and clinical data of 503 EC patients and screened out different expressions of metabolism-related genes with prognosis influence of EC from The Cancer Genome Atlas (TCGA) database. We first established a metabolism-related genes model using univariate and multivariate Cox regression and Lasso regression analysis. To internally validate the predictive model, 503 samples (entire set) were randomly assigned into the test set and the train set. Then, we applied the receiver operating characteristic (ROC) curve to confirm our previous predictive model and depicted a nomogram integrating the risk score and the clinicopathological feature. We employed a gene set enrichment analysis (GSEA) to explore the biological processes and pathways of the model. Afterward, we used ESTIMATE to evaluate the TME. Also, we adopted CIBERSORT and ssGSEA to estimate the fraction of immune infiltrating cells and immune function. At last, we investigated the relationship between the predictive model and immune checkpoint genes. We first constructed a predictive model based on five metabolism-related genes (INPP5K, PLPP2, MBOAT2, DDC, and ITPKA). This model showed the ability to predict EC patients' prognosis accurately and performed well in the train set, test set, and entire set. Then we confirmed the predictive signature was a novel independent prognostic factor in EC patients. In addition, we drew and validated a nomogram to precisely predict the survival rate of EC patients at 1-, 3-, and 5-years (ROC The metabolism-related genes signature (INPP5K, PLPP2, MBOAT2, DDC, and ITPKA) is a valuable index for predicting the survival outcomes and efficacy of immunotherapy for EC in clinical settings.

Identification of cuproptosis-related subtypes, establishment of a prognostic model and tumor immune landscape in endometrial carcinoma

Cuproptosis, the mechanism of copper-dependent cell death, is distinct from all other known forms of regulated cell death and dependents on mitochondrial respiration. Cuproptosis promises to be a novel treatment, especially for tumors resistant to conventional therapies. We investigated the changes in cuproptosis-related genes (CRGs) in endometrial cancer (EC) cohorts from the merged Gene Expression Omnibus and the Cancer Genome Atlas databases, which could be divided into three distinct CRGclusters. Patients in CRGcluster C would have higher survival probability (P = 0.007), and higher levels of tumor microenvironment (TME) cell infiltration than other CRGclusters. CRG score was calculated via the results of univariate, multivariate cox analysis and least absolute shrinkage and selection operator regression analysis. Patients were divided into two risk subgroups according to the median risk score. Low-risk patients exhibited a more favorable prognosis, higher immunogenicity, and greater immunotherapy efficacy. Besides, CRG scores were strongly correlated to copy number variation, immunophenoscore, tumor mutation load, cancer stem cell index, microsatellite instability, and chemosensitivity. The c-index of our model is 0.702, which is higher than other four published model. The results proved that our model can distinguish EC patients with high-risk and low-risk and accurately predict the prognosis of EC patients. It will provide new ideas for clinical prognosis and precise treatments.

Detection of deep myometrial invasion in endometrial cancer MR imaging based on multi-feature fusion and probabilistic support vector machine ensemble

The depth of myometrial invasion affects the treatment and prognosis of patients with endometrial cancer (EC), conventionally evaluated using MR imaging (MRI). However, only a few computer-aided diagnosis methods have been reported for identifying deep myometrial invasion (DMI) using MRI. Moreover, these existing methods exhibit relatively unsatisfactory sensitivity and specificity. This study proposes a novel computerized method to facilitate the accurate detection of DMI on MRI. This method requires only the corpus uteri region provided by humans or computers instead of the tumor region. We also propose a geometric feature called LS to describe the irregularity of the tissue structure inside the corpus uteri triggered by EC, which has not been leveraged for the DMI prediction model in other studies. Texture features are extracted and then automatically selected by recursive feature elimination. Utilizing a feature fusion strategy of strong and weak features devised in this study, multiple probabilistic support vector machines incorporate LS and texture features, which are then merged to form the ensemble model EPSVM. The model performance is evaluated via leave-one-out cross-validation. We make the following comparisons, EPSVM versus the commonly used classifiers such as random forest, logistic regression, and naive Bayes; EPSVM versus the models using LS or texture features alone. The results show that EPSVM attains an accuracy, sensitivity, specificity, and F1 score of 93.7%, 94.7%, 93.3%, and 87.8%, all of which are higher than those of the commonly used classifiers and the models using LS or texture features alone. Compared with the methods in existing studies, EPSVM exhibits high performance in terms of both sensitivity and specificity. Moreover, LS can achieve an accuracy, sensitivity, and specificity of 89.9%, 89.5%, and 90.0%. Thus, the devised geometric feature LS is significant for DMI detection. The fusion of LS and texture features in the proposed EPSVM can provide more reliable prediction. The computer-aided classification based on the proposed method can assist radiologists in accurately identifying DMI on MRI.

High-throughput nucleotide sequencing reveals new circulatory miRNA genes in cervical cancer patients

Cervical cancer is one of the most common cancers in the world, and it is the second gynecological cancer in women after breast cancer. Recent evidence has shown miRNAs are dysregulated in cervical cancer, which can be used as a valuable tool for diagnosis, prognosis, or treatment. In this study, we aimed to find a new miRNA signature for cervical cancer and its potential target genes. 5.0 mL of whole blood were taken from 20 samples, 10 cervical cancer, and 10 healthy women, then we separated the serum and extracted RNA. The RNA samples of each group were pooled together. The differentially expressed miRNAs were found using high-throughput nucleotide sequencing. The target genes of the selected miRNAs were predicted by two tools (miRTarBase and TargetScan). The mRNA data of the target genes were downloaded from TCGA and processed with R version 4.4.1 for survival analysis. The study found two low-expressed miRNAs (miR-384 and miR-6880-5p) and three upregulated miRNAs (miR-325, miR-504-5p, and miR-3074-5p); those miRNAs are targeting 11 critical genes in cancer pathways. Survival analysis identified the target genes CDK6 and FGF19 as potential prognostic genes. The qRT-PCR results showed that the expression of the miRNAs miR-6880-5p and ch21_12598 was downregulated in the patient group. The current study found five known miRNAs and one novel miRNA in cervical cancer that target essential genes in cancer pathways. These potential biomarkers can be further investigated for their potential role in cervical cancer diagnosis, prognosis, and treatment.

Classification of cervical lesions based on multimodal features fusion

Cervical cancer is a severe threat to women's health worldwide with a long cancerous cycle and a clear etiology, making early screening vital for the prevention and treatment. Based on the dataset provided by the Obstetrics and Gynecology Hospital of Fudan University, a four-category classification model for cervical lesions including Normal, low-grade squamous intraepithelial lesion (LSIL), high-grade squamous intraepithelial lesion (HSIL) and cancer (Ca) is developed. Considering the dataset characteristics, to fully utilize the research data and ensure the dataset size, the model inputs include original and acetic colposcopy images, lesion segmentation masks, human papillomavirus (HPV), thinprep cytologic test (TCT) and age, but exclude iodine images that have a significant overlap with lesions under acetic images. Firstly, the change information between original and acetic images is introduced by calculating the acetowhite opacity to mine the correlation between the acetowhite thickness and lesion grades. Secondly, the lesion segmentation masks are utilized to introduce prior knowledge of lesion location and shape into the classification model. Lastly, a cross-modal feature fusion module based on the self-attention mechanism is utilized to fuse image information with clinical text information, revealing the features correlation. Based on the dataset used in this study, the proposed model is comprehensively compared with five excellent models over the past three years, demonstrating that the proposed model has superior classification performance and a better balance between performance and complexity. The modules ablation experiments further prove that each proposed improved module can independently improve the model performance.

Self-supervised learning-based cervical cytology for the triage of HPV-positive women in resource-limited settings and low-data regime

Screening Papanicolaou test samples has proven to be highly effective in reducing cervical cancer-related mortality. However, the lack of trained cytopathologists hinders its widespread implementation in low-resource settings. Deep learning-assisted telecytology diagnosis emerges as an appealing alternative, but it requires the collection of large annotated training datasets, which is costly and time-consuming. In this paper, we demonstrate that the abundance of unlabeled images that can be extracted from Pap smear test whole slide images presents a fertile ground for self-supervised learning methods, yielding performance improvements compared to off-the-shelf pre-trained models for various downstream tasks. In particular, we propose Cervical Cell Copy-Pasting (C

Whole transcriptome analysis reveals non-coding RNA's competing endogenous gene pairs as novel form of motifs in serous ovarian cancer

The non-coding RNA (ncRNA) regulation appears to be associated to the diagnosis and targeted therapy of complex diseases. Motifs of non-coding RNAs and genes in the competing endogenous RNA (ceRNA) network would probably contribute to the accurate prediction of serous ovarian carcinoma (SOC). We conducted a microarray study profiling the whole transcriptomes of eight human SOCs and eight controls and constructed a ceRNA network including mRNAs, long ncRNAs, and circular RNAs (circRNAs). Novel form of motifs (mRNA-ncRNA-mRNA) were identified from the ceRNA network and defined as non-coding RNA's competing endogenous gene pairs (ceGPs), using a proposed method denoised individualized pair analysis of gene expression (deiPAGE). 18 cricRNA's ceGPs (cceGPs) were identified from multiple cohorts and were fused as an indicator (SOC index) for SOC discrimination, which carried a high predictive capacity in independent cohorts. SOC index was negatively correlated with the CD8+/CD4+ ratio in tumour-infiltration, reflecting the migration and growth of tumour cells in ovarian cancer progression. Moreover, most of the RNAs in SOC index were experimentally validated involved in ovarian cancer development. Our results elucidate the discriminative capability of SOC index and suggest that the novel competing endogenous motifs play important roles in expression regulation and could be potential target for investigating ovarian cancer mechanism or its therapy.

Molecular evolution of driver mutations in cancer with microsatellite instability and their impact on tumor progression: Implications for precision medicine in patients with UCEC

Cancer development is driven by genetic alterations, particularly cancer driver mutations (CDMs), which are associated with aggressive phenotypes and shorter survival. In contrast, higher mutation loads caused by microsatellite instability (MSI) or mismatch repair deficiency (MMRd) can induce anti-cancer immunity, leading to tumor shrinkage and improved responses to immune checkpoint inhibitor (ICI) therapies. However, understanding how CDMs and MSI/MMRd influence cancer evolution remains limited. We opted uterine corpus endometrial carcinoma (UCEC) as a model in this study due to its MSI-high/MMRd characteristics. Somatic mutation screening revealed that UCEC has a significantly higher mutation rate in cancer driver genes compared to ovarian cancer (OVCA) and cervical squamous cell carcinoma (CSCC), despite these cancers arising from histologically connected organs in the reproductive tract. Interestingly, these CDMs did not necessarily drive tumor progression. Using a cutoff of 7.0 (mutations/Mb) for tumor mutation burden (TMB), we classified UCEC patients into two groups with distinct clinical features, genetic profiles, and drug sensitivities. Among the known CDMs, TP53 mutations and their functional networks emerged as key drivers in UCEC progression, while mutations in CTNNB1, PTEN, and ARID1A may enhance anti-tumor immunity, correlating with longer overall survivals. Drug screening using GDSC and CTRPv2 databases suggested that GSK-3 inhibitor IX may be effective for treating aggressive UCEC patients with a non-MSI phenotype. Curcumin showed efficacy for UCEC patients with MSI, especially with ICI therapy. Our study highlights the importance of immune regulation and tolerance over CDMs in cancer development, particularly in those with an MSI-high/MMRd phenotype. We propose that TMB could serve as a valuable screening method alongside molecular and histopathological classifications to guide treatment strategies for UCEC patients.

HVS-Unsup: Unsupervised cervical cell instance segmentation method based on human visual simulation

Instance segmentation plays an important role in the automatic diagnosis of cervical cancer. Although deep learning-based instance segmentation methods can achieve outstanding performance, they need large amounts of labeled data. This results in a huge consumption of manpower and material resources. To solve this problem, we propose an unsupervised cervical cell instance segmentation method based on human visual simulation, named HVS-Unsup. Our method simulates the process of human cell recognition and incorporates prior knowledge of cervical cells. Specifically, firstly, we utilize prior knowledge to generate three types of pseudo labels for cervical cells. In this way, the unsupervised instance segmentation is transformed to a supervised task. Secondly, we design a Nucleus Enhanced Module (NEM) and a Mask-Assisted Segmentation module (MAS) to address problems of cell overlapping, adhesion, and even scenarios involving visually indistinguishable cases. NEM can accurately locate the nuclei by the nuclei attention feature maps generated by point-level pseudo labels, and MAS can reduce the interference from impurities by updating the weight of the shallow network through the dice loss. Next, we propose a Category-Wise droploss (CW-droploss) to reduce cell omissions in lower-contrast images. Finally, we employ an iterative self-training strategy to rectify mislabeled instances. Experimental results on our dataset MS-cellSeg, the public datasets Cx22 and ISBI2015 demonstrate that HVS-Unsup outperforms existing mainstream unsupervised cervical cell segmentation methods.

Machine learning-based classification of deubiquitinase USP26 and its cell proliferation inhibition through stabilizing KLF6 in cervical cancer

We aim to accurately distinguish ubiquitin-specific proteases (USPs) from other members within the deubiquitinating enzyme families based on protein sequences. Additionally, we seek to elucidate the specific regulatory mechanisms through which USP26 modulates Krüppel-like factor 6 (KLF6) and assess the subsequent effects of this regulation on both the proliferation and migration of cervical cancer cells. All the deubiquitinase (DUB) sequences were classified into USPs and non-USPs. Feature vectors, including 188D, n-gram, and 400D dimensions, were extracted from these sequences and subjected to binary classification via the Weka software. Next, thirty human USPs were also analyzed to identify conserved motifs and ascertained evolutionary relationships. Experimentally, more than 90 unique DUB-encoding plasmids were transfected into HeLa cell lines to assess alterations in KLF6 protein levels and to isolate a specific DUB involved in KLF6 regulation. Subsequent experiments utilized both wild-type (WT) USP26 overexpression and shRNA-mediated USP26 knockdown to examine changes in KLF6 protein levels. The half-life experiment was performed to assess the influence of USP26 on KLF6 protein stability. Immunoprecipitation was applied to confirm the USP26-KLF6 interaction, and ubiquitination assays to explore the role of USP26 in KLF6 deubiquitination. Additional cellular assays were conducted to evaluate the effects of USP26 on HeLa cell proliferation and migration. 1. Among the extracted feature vectors of 188D, 400D, and n-gram, all 12 classifiers demonstrated excellent performance. The RandomForest classifier demonstrated superior performance in this assessment. Phylogenetic analysis of 30 human USPs revealed the presence of nine unique motifs, comprising zinc finger and ubiquitin-specific protease domains. 2. Through a systematic screening of the deubiquitinase library, USP26 was identified as the sole DUB associated with KLF6. 3. USP26 positively regulated the protein level of KLF6, as evidenced by the decrease in KLF6 protein expression upon shUSP26 knockdown in both 293T and Hela cell lines. Additionally, half-life experiments demonstrated that USP26 prolonged the stability of KLF6. 4. Immunoprecipitation experiments revealed a strong interaction between USP26 and KLF6. Notably, the functional interaction domain was mapped to amino acids 285-913 of USP26, as opposed to the 1-295 region. 5. WT USP26 was found to attenuate the ubiquitination levels of KLF6. However, the mutant USP26 abrogated its deubiquitination activity. 6. Functional biological assays demonstrated that overexpression of USP26 inhibited both proliferation and migration of HeLa cells. Conversely, knockdown of USP26 was shown to promote these oncogenic properties. 1. At the protein sequence level, members of the USP family can be effectively differentiated from non-USP proteins. Furthermore, specific functional motifs have been identified within the sequences of human USPs. 2. The deubiquitinating enzyme USP26 has been shown to target KLF6 for deubiquitination, thereby modulating its stability. Importantly, USP26 plays a pivotal role in the modulation of proliferation and migration in cervical cancer cells.

Deep integrated fusion of local and global features for cervical cell classification

Cervical cytology image classification is of great significance to the cervical cancer diagnosis and prognosis. Recently, convolutional neural network (CNN) and visual transformer have been adopted as two branches to learn the features for image classification by simply adding local and global features. However, such the simple addition may not be effective to integrate these features. In this study, we explore the synergy of local and global features for cytology images for classification tasks. Specifically, we design a Deep Integrated Feature Fusion (DIFF) block to synergize local and global features of cytology images from a CNN branch and a transformer branch. Our proposed method is evaluated on three cervical cell image datasets (SIPaKMeD, CRIC, Herlev) and another large blood cell dataset BCCD for several multi-class and binary classification tasks. Experimental results demonstrate the effectiveness of the proposed method in cervical cell classification, which could assist medical specialists to better diagnose cervical cancer.

Conduction and validation of a novel prognostic signature in cervical cancer based on the necroptosis characteristic genes via integrating of multiomics data

The significance of necroptosis in recurrent or metastatic cervical cancer remains unclear. In this study, we utilized various bioinformatics methods to analyze the cancer genome atlas (TCGA) data, gene chip and the single-cell RNA-sequencing (scRNA seq) data. And a necroptosis-related genes signature for prognostic assessment of patients with cervical cancer was constructed successfully. Survival analysis, receiver operating characteristic (ROC) curve, the support vector machine recursive feature elimination (SVM-RFE) algorithm and random forest analysis were performed to validate this signature. Patients in TCGA-CESC cohort were grouped into "high-necroptosis score (H-NCPS)" vs "low-necroptosis score (L-NCPS)" subgroups based on the median of necroptosis score of each patient. Analyses of the tumor microenvironment manifested "H-NCPS" patients associated with lower degree of immune infiltration. Through the utilization of survival analysis, cell communication, and Gene Set Enrichment Analysis (GSEA), PGK1 was determined to be the pivotal gene within the 9-gene signature associated with necroptosis. The high expression of PGK1 in cervical cancer cells was confirmed through the utilization of quantitative real-time polymerase chain reaction (RT-qPCR) and the human protein atlas (HPA). In the interim, PGK1 prompted the transition of M1 macrophages to M2 macrophages and influenced the occurrence and development of necroptosis. In conclusion, the 9-gene signature developed from necroptosis-related genes has shown significant predictive capabilities for the prognosis of cervical cancer, offered valuable guidance for individualized and targeted treatment approaches for patients.

Exploring the utility of FTS as a bonafide binding partner for EGFR: A potential drug target for cervical cancer

Establishment of human papilloma virus (HPV) infection and its progression to cervical cancer (CC) requires the participation of epidermal growth factor (EGF) receptor (EGFR) and fused toes homolog (FTS). This review is an attempt to understand the structure-function relationship between FTS and EGFR as a tool for the development of newer CC drugs. Motif analysis was performed using national center for biotechnology information (NCBI), kyoto encyclopedia of genes and genomes (KEGG), simple modular architecture research tool (SMART) and multiple expectation maximizations for motif elicitation (MEME) database. The secondary and tertiary structure prediction of FTS was performed using DISOPRED3 and threading assembly, respectively. A positive correlation was found between the transcript levels of FTS and EGFR. Amino acids responsible for interaction between EGFR and FTS were determined. The nine micro-RNAs (miRNAs) that regulates the expression of FTS were predicted using Network Analyst 3.0 database. hsa-miR-629-5p and hsa-miR-615-3p are identified as significant positive and negative regulators of FTS gene expression. This review opens up new avenues for the development of CC drugs which interfere with the interaction between FTS and EGFR.

Integrated immunological analysis of single-cell and bulky tissue transcriptomes reveals the role of interactions between M0 macrophages and naïve CD4+ T cells in the immunosuppressive microenvironment of cervical cancer

In recent decades, the incidence and mortality of cervical cancer have declined in developed countries due to the implementation of screening and vaccination programs. However, cervical cancer remains one of the major culprits of cancer-related deaths in young women. Current studies have found that immune cell-related intercellular communication in the tumor microenvironment has a large impact on the construction of the immunosuppressive microenvironment. In this study, we performed a comprehensive immune analysis on bulk RNA-seq and scRNA-seq data obtained from cervical cancer and revealed that two highly plastic cell populations, M0 macrophages and naïve CD4

CAM-VT: A Weakly supervised cervical cancer nest image identification approach using conjugated attention mechanism and visual transformer

Cervical cancer is the fourth most common cancer among women, and cytopathological images are often used to screen for this cancer. However, manual examination is very troublesome and the misdiagnosis rate is high. In addition, cervical cancer nest cells are denser and more complex, with high overlap and opacity, increasing the difficulty of identification. The appearance of the computer aided automatic diagnosis system solves this problem. In this paper, a weakly supervised cervical cancer nest image identification approach using Conjugated Attention Mechanism and Visual Transformer (CAM-VT), which can analyze pap slides quickly and accurately. CAM-VT proposes conjugated attention mechanism and visual transformer modules for local and global feature extraction respectively, and then designs an ensemble learning module to further improve the identification capability. In order to determine a reasonable interpretation, comparative experiments are conducted on our datasets. The average accuracy of the validation set of three repeated experiments using CAM-VT framework is 88.92%, which is higher than the optimal result of 22 well-known deep learning models. Moreover, we conduct ablation experiments and extended experiments on Hematoxylin and Eosin stained gastric histopathological image datasets to verify the ability and generalization ability of the framework. Finally, the top 5 and top 10 positive probability values of cervical nests are 97.36% and 96.84%, which have important clinical and practical significance. The experimental results show that the proposed CAM-VT framework has excellent performance in potential cervical cancer nest image identification tasks for practical clinical work.

A random forest-based metabolic risk model to assess the prognosis and metabolism-related drug targets in ovarian cancer

As one of the most common gynecologic malignant tumors, ovarian cancer is usually diagnosed at an advanced and incurable stage because of its early asymptomatic onset. Increasing research into tumor biology has demonstrated that abnormal cellular metabolism precedes tumorigenesis, therefore it has become an area of active research in academia. Cellular metabolism is of great significance in cancer diagnostic and prognostic studies. In this study, we integrated The Cancer Genome Atlas dataset with multiple Gene Expression Omnibus ovarian cancer datasets, identified 17 metabolic pathways with prognostic values using the random forest algorithm, constructed a metabolic risk scoring model based on metabolic pathway enrichment scores, and classified patients with ovarian cancer into two subtypes. Then, we systematically investigated the differences between different subtypes in terms of prognosis, differential gene expression, immune signature enrichment, Hallmark signature enrichment, and somatic mutations. As well, we successfully predicted differences in sensitivity to immunotherapy and chemotherapy drugs in patients with different metabolic risk subtypes. Moreover, we identified 5 drug targets associated with high metabolic risk and low metabolic risk ovarian cancer phenotypes through the weighted correlation network analysis and investigated their roles in the genesis of ovarian cancer. Finally, we developed an XGBoost classifier for predicting metabolic risk types in patients with ovarian cancer, producing a good predictive effect. In light of the above study, the research findings will provide valuable information for prognostic prediction and personalized medical treatment of patients with ovarian cancer.

Metabolic signatures of immune checkpoint inhibitor response in gynecologic cancers: Insights from flux balance analysis

Modifiers of immune checkpoint inhibitor (ICI) responses in cancer patients are complex and remain poorly characterized, especially in gynecologic cancers. In this study, we explored fluxomic biomarkers that differentiate responders from non-responders to ICIs in a series of 49 patients with gynecologic cancers, including ovarian, cervical, and endometrial cancers. By applying metabolic enzyme expression as constraints, we utilized an objective-customizable flux balance analysis within a genome-scale metabolic model to predict the metabolic flux differences between responders versus non-responders of ICI treatment. We identified three reactions with consistent differential activity across all ten different optimization objectives: Succinate Dehydrogenase (SUCD1m) in the citric acid cycle, NADH: Guanosine-5-Phosphate Oxidoreductase (r0276) involved in purine catabolism, and Ornithine Transaminase Reversible, Mitochondrial (ORNTArm) in the urea cycle. Additionally, reactions within the folate cycle subsystem, particularly involving MTHFD2, demonstrated significance in distinguishing treatment responses, aligning with previous findings linking MTHFD2 to immune evasion and tumor progression. To further analyze the association between metabolic features and survival outcomes, we implemented machine learning models that integrate multi-omics data. Our model included clinical-pathologic, molecular-genomic features (gene expression, TGF-β score, immune cell abundance from transcriptomic deconvolution), and significant reaction fluxes. Our findings suggest that SUCD1m, MTHFDm and ORNTArm are important metabolic biomarkers that could serve as predictive indicators for ICI response and, if validated in a larger cohort, may guide the development of targeted therapies to enhance treatment efficacy for gynecologic cancer patients. This study highlights the use of genome-scale metabolic modeling to identify clinically relevant biomarkers and improve therapeutic strategies.

FDA-approved Levophed as an alternative multitargeted therapeutic against cervical cancer transferase, cell cycle, and regulatory proteins

Despite the availability of Pap tests and HPV vaccines, Cervical Cancer continues to be a significant factor contributing to women's deaths. It poses severe consequences to women's health. The disease's severity lies in its potential to progress silently in its early stages, mainly detected in its advanced stage, and clinical treatment is challenging due to drug resistance. This study aims to identify multitargeted lead molecules based on the interactome of Cervical Cancer-related crucial genes, which can help develop drug-resistant therapies. We have considered 9 crucial Cervical Cancer genes, namely BUBR1, CCNB1, FEN1, MAD2, MCM10, MCM6, ITGB8, POLE, and TPX2, to perform gene network analysis and Gene Ontology enrichment studies to identify the potential hub genes and their role. Further, we performed multitarget screening using multisampling algorithms HTVS, SP, and XP to screen the protein products of the 9 genes for their binding affinity for the FDA-approved drugs library. The binding affinities of the compounds were evaluated using MM\GBSA that identified multitargeted potential inhibitor as a Levophed for Cervical Cancer, and the docking results showed a range of MM/GBSA scores, varying from -8.35 to -5.38 kcal/mol for docking, and -43.41 to -19.37 kcal/mol for MM/GBSA scoring. The protein residues that interact the most with Levophed are ALA, THR, ILE, ASN, GLY, ASP, LEU, LYS, VAL, GLN, PRO, CYS, GLU, and TYR. The pharmacokinetic properties and WaterMap computations also support the idea that the compound can potentially become a drug candidate. Furthermore, all 9 complexes were simulated for 100ns, resulting in cumulative deviation and fluctuation of <2 Å, with many intermolecular interactions and binding free energy computations supporting the studies. The study shows that Levophed could treat Cervical Cancer without encountering drug resistance- however, experimental studies are needed to confirm the accuracy.

DCE-MRI pharmacokinetic parameter maps for cervical carcinoma prediction

Pharmacokinetic parameters estimated from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) time course data enable the physio-biological interpretation of tissue angiogenesis. This study aims to develop machine learning approaches for cervical carcinoma prediction based on pharmacokinetic parameters. The performance of individual parameters was assessed in terms of their efficacy in differentiating cancerous tissue from normal cervix tissue. The effect of combining parameters was evaluated using the following two approaches: the first approach was based on support vector machines (SVMs) to combine the parameters from one pharmacokinetic model or across several models; the second approach was based on a novel method called APITL (artificial pharmacokinetic images for transfer learning), which was designed to fully utilize the comprehensive pharmacokinetic information acquired from DCE-MRI data. A "winner-takes-all" strategy was employed to consolidate the slice-wise prediction into subject-wise prediction. Experiments were carried out with a dataset comprising 36 patients with cervical cancer and 17 healthy subjects. The results demonstrated that parameter V

Machine learning-based radiomics for predicting outcomes in cervical cancer patients undergoing concurrent chemoradiotherapy

To investigate the value of machine learning-based radiomics for predicting disease-free survival (DFS) and overall survival (OS) undergoing concurrent chemoradiotherapy (CCRT) for patients with locally advanced cervical cancer (LACC). In this multicentre study, 700 patients with IB2-IVA cervical cancer who underwent CCRT with ongoing follow-up were retrospectively analyzed. Three-dimensional radiomics features of primary lesions and its surrounding 5 mm region in T2WI sequences were collected. Six machine learning methods were used to construct the optimal radiomics model for accurate prediction of DFS and OS after CCRT in LACC patients. Eventually, TCGA and GEO databases were used to explore the mechanisms of radiomics in predicting the progression and survival of cervical cancer. This study adhered CLEAR for reporting and its quality was assessed using RQS and METRICS. In the prediction of DFS, the RSF model combined tumor and peritumor radiomics demonstrated the best predictive efficacy, with the AUC for predicting 1-year, 3-year, and 5-year DFS in the training, validation, and test sets of 0.986, 0.989, 0.990, and 0.884, 0.838, 0.823, and 0.829, 0.809, 0.841, respectively. In the prediction of OS, the GBM model best performer, with AUC of 0.999, 0.995, 0.978, and 0.981, 0.975, 0.837, and 0.904, 0.860, 0.905. Differential genes in TCGA and GEO suggest that the prediction of radiomics model may be associated with KDELR2 and HK2. Machine learning-based radiomics models help to predict DFS and OS after CCRT in LACC patients, and the combination of tumor and peritumor information has higher predictive efficacy, which can provide a reliable basis for therapeutic decision-making in cervical cancer patients.

Discovery of the potential biomarkers for early diagnosis of endometrial cancer via integrating metabolomics and transcriptomics

Endometrial cancer (EC) is one of the most common malignant tumors in women, and the increasing incidence and mortality pose a serious threat to the public health. Early diagnosis of EC could prolong the survival period and optimize the survivorship, greatly alleviating patients' suffering and social medical pressure. In this study, we collected urine and serum samples from the recruited patients, analyzed the samples using LC-MS approach, and identified the differential metabolites through metabolomic analysis. Then, the differentially expressed genes were identified through the systematic transcriptomic analysis of EC-related dataset from Gene Expression Omnibus (GEO), followed by network profiling of metabolic-reaction-enzyme-gene. In this experiment, a total of 83 differential metabolites and 19 hub genes were discovered, of which 10 different metabolites and 3 hub genes were further evaluated as more potential biomarkers based on network analysis. According to the KEGG enrichment analysis, the potential biomarkers and gene-encoded proteins were found to be involved in the arginine and proline metabolism, histidine metabolism, and pyrimidine metabolism, which was of significance for the early diagnosis of EC. In particular, the combination of metabolites (histamine, 1-methylhistamine, and methylimidazole acetaldehyde) as well as the combination of RRM2, TYMS and TK1 exerted more accurate discrimination abilities between EC and healthy groups, providing more criteria for the early diagnosis of EC.

Construction of an immune infiltration landscape based on immune-related genes in cervical cancer

Clinical trials demonstrated that immunotherapy improved the prognosis of patients with cervical cancer (CC), which is strongly associated with immune infiltration landscape. We aimed to comprehensively analyze the immune infiltration landscape and provide directions for immunotherapy of CC. The study was based on the Cancer Genome Atlas (TCGA) database and utilized immune-related genes (IRGs) to identify heterogeneous immune subtypes. The ESTIMATE and CIBERSORT algorithms were performed to unravel the landscape of the tumor immune microenvironment. The IRGs score was constructed by principal component analysis. Then, we analyzed the differences in immune-related characteristics and prognosis between high and low IRGs score groups. An independent immunotherapy cohort (IMvigor210) was used to verify the reliability and stability of the IRGs score. Herein, a total of 272 TCGA-CC samples were divided into high (n = 199) and low (n = 73) IRGs score groups. The infiltration of CD8 T cells, memory resting CD4 T cells, and memory activated CD4 T cells, as well as better prognostic outcomes, mainly exhibited in the low IRGs score group and gene cluster A. GSEA analysis showed that JAK/STAT and VEGF signaling pathways were activated in the low IRGs score group. In contrast, the high IRGs score group with least lymphocyte infiltration may contribute to the poor prognosis. The prognosis of the IMvigor210 cohort was still significantly different between high and low IRGs score groups (P < 0.001). This study demonstrated that the IRGs score could be an independent prognostic biomarker and provide direction for tailoring immunotherapy strategies in the future clinical treatment.

Prognostic signature construction and immunotherapy response analysis for Uterine Corpus Endometrial Carcinoma based on cuproptosis-related lncRNAs

As a general female malignant tumor, Uterine Corpus Endometrial Carcinoma (UCEC) has high mortality and relapses. Cuproptosis was found to play an essential role in tumor by more and more researches. However, it is still unclear of the prognostic value and function of cuproptosis related Long non-coding RNA (lncRNA) in UCEC. Sequencing data with the corresponding clinical data and cuproptosis-related genes (CRGs) data were obtained from the Cancer Gene Atlas (TCGA) database and cuproptosis related studies. Pearson test was applied to select cuproptosis-related lncRNAs (CRLs). Prognosis associated CRLs was identified by univariate Cox analysis and the predictors were determined by least absolute shrinkage and selection operator (Lasso)-Cox and multivariate Cox analyses to construct the cuproptosis-related lncRNA prognostic signature (CRLPS). The performance of the CRLPs was evaluated by consistency index (C-index) and Kaplan-Meier analysis. A nomogram model was constructed for survival prediction and the accuracy of the model was evaluated by calibration curve. Finally, immune related analyses were applied to predict immune responses and identify drugs with potential efficacy for the overall survival (OS). A total of 734 CRLs were found and 29 of them were identified as prognosis related lncRNAs. 12 CRLs were finally determined to build the CRLPS which revealed good ability on prognosis predicting. Subsequently, risk score of the CRLPS and grade were assessed as independent prognosis factors for UCEC, based on which the prognostic model provided the highest prediction accuracy of 99.7%. The calibration curve suggested that the prediction results consisted well with the observation. Enrichment analysis showed the CRLPS was mainly associated with tumor development and immune response. Patients in low tumor mutation burden (TMB) group had poorer OS. Significant difference was found in tumor immune dysfunction and exclusion (TIDE) score between different risk score groups. Finally, based on the CRLPs, drug sensitivity analysis identified nine anticancer drugs with potential efficacy on prognosis. Cuproptosis-related lncRNA prognostic signature was constructed for UCEC for the first time. Its high reliability and accuracy on predicting prognosis and immunotherapy response provided new perspective to explore the tumor mechanism and improve clinical prognosis. Nine discovered sensitive drugs provided important clues for personalized treatment of UCEC.