BioMedical Engineering OnLine

Screening ovarian cancer by using risk factors: machine learning assists

Abstract Background and aim Ovarian cancer (OC) is a prevalent and aggressive malignancy that poses a significant public health challenge. The lack of preventive strategies for OC increases morbidity, mortality, and other negative consequences. Screening OC through risk prediction could be leveraged as a powerful strategy for preventive purposes that have not received much attention. So, this study aimed to leverage machine learning approaches as predictive assistance solutions to screen high-risk groups of OC and achieve practical preventive purposes. Materials and methods As this study is data-driven and retrospective in nature, we leveraged 1516 suspicious OC women data from one concentrated database belonging to six clinical settings in Sari City from 2015 to 2019. Six machine learning (ML) algorithms, including XG-Boost, Random Forest (RF), J-48, support vector machine (SVM), K-nearest neighbor (KNN), and artificial neural network (ANN) were leveraged to construct prediction models for OC. To choose the best model for predicting OC, we compared various prediction models built using the area under the receiver characteristic operator curve (AU-ROC). Results Current experimental results revealed that the XG-Boost with AU-ROC = 0.93 (0.95 CI = [0.91–0.95]) was recognized as the best-performing model for predicting OC. Conclusions ML approaches possess significant predictive efficiency and interoperability to achieve powerful preventive strategies leveraging OC screening high-risk groups.

Development and validation of an ultrasound-based deep learning radiomics nomogram for predicting the malignant risk of ovarian tumours

Abstract Background The timely identification and management of ovarian cancer are critical determinants of patient prognosis. In this study, we developed and validated a deep learning radiomics nomogram (DLR_Nomogram) based on ultrasound (US) imaging to accurately predict the malignant risk of ovarian tumours and compared the diagnostic performance of the DLR_Nomogram to that of the ovarian-adnexal reporting and data system (O-RADS). Methods This study encompasses two research tasks. Patients were randomly divided into training and testing sets in an 8:2 ratio for both tasks. In task 1, we assessed the malignancy risk of 849 patients with ovarian tumours. In task 2, we evaluated the malignancy risk of 391 patients with O-RADS 4 and O-RADS 5 ovarian neoplasms. Three models were developed and validated to predict the risk of malignancy in ovarian tumours. The predicted outcomes of the models for each sample were merged to form a new feature set that was utilised as an input for the logistic regression (LR) model for constructing a combined model, visualised as the DLR_Nomogram. Then, the diagnostic performance of these models was evaluated by the receiver operating characteristic curve (ROC). Results The DLR_Nomogram demonstrated superior predictive performance in predicting the malignant risk of ovarian tumours, as evidenced by area under the ROC curve (AUC) values of 0.985 and 0.928 for the training and testing sets of task 1, respectively. The AUC value of its testing set was lower than that of the O-RADS; however, the difference was not statistically significant. The DLR_Nomogram exhibited the highest AUC values of 0.955 and 0.869 in the training and testing sets of task 2, respectively. The DLR_Nomogram showed satisfactory fitting performance for both tasks in Hosmer–Lemeshow testing. Decision curve analysis demonstrated that the DLR_Nomogram yielded greater net clinical benefits for predicting malignant ovarian tumours within a specific range of threshold values. Conclusions The US-based DLR_Nomogram has shown the capability to accurately predict the malignant risk of ovarian tumours, exhibiting a predictive efficacy comparable to that of O-RADS.

CT radiomics-based explainable machine learning model for accurate differentiation of malignant and benign endometrial tumors: a two-center study

This study aimed to develop and validate a CT radiomics-based explainable machine learning model for precise diagnosing of malignancy and benignity specifically in endometrial cancer (EC) patients. A total of 83 EC patients from two centers, including 46 with malignant and 37 with benign conditions, were included, with data split into a training set (n = 59) and a testing set (n = 24). The regions of interest (ROIs) were manually segmented from pre-surgical CT scans, and 1132 radiomic features were extracted from the pre-surgical CT scans using Pyradiomics. Six explainable machine learning (ML) modeling algorithms were implemented, respectively, for determining the optimal radiomics pipeline. The diagnostic performance of the radiomic model was evaluated by using sensitivity, specificity, accuracy, precision, F1 score, area under the receiver operating characteristic curve (AUROC), and area under the precision-recall curve (AUPRC). To enhance clinical understanding and usability, we separately implemented SHAP analysis and feature mapping visualization and evaluated the calibration curve and decision curve. By comparing six modeling strategies, the Random Forest model emerged as the optimal choice for diagnosing EC, with a training AUROC of 1.00 and a testing AUROC of 0.96. SHAP identified the most important radiomic features, revealing that all selected features were significantly associated with EC (p < 0.05). Radiomics feature maps also provide a feasible assessment tool for clinical applications. Decision curve analysis (DCA) indicated a higher net benefit for our model compared to the "All" and "None" strategies, suggesting its clinical utility in identifying high-risk cases and reducing unnecessary interventions. CT radiomics-based explainable ML model achieved high diagnostic performance, which could be used as an intelligent auxiliary tool for the diagnosis of endometrial cancer.

A computer-aided determining method for the myometrial infiltration depth of early endometrial cancer on MRI images

AbstractTo classify early endometrial cancer (EC) on sagittal T2-weighted images (T2WI) by determining the depth of myometrial infiltration (MI) using a computer-aided diagnosis (CAD) method based on a multi-stage deep learning (DL) model. This study retrospectively investigated 154 patients with pathologically proven early EC at the institution between January 1, 2018, and December 31, 2020. Of these patients, 75 were in the International Federation of Gynecology and Obstetrics (FIGO) stage IA and 79 were in FIGO stage IB. An SSD-based detection model and an Attention U-net-based segmentation model were trained to select, crop, and segment magnetic resonance imaging (MRl) images. Then, an ellipse fitting algorithm was used to generate a uterine cavity line (UCL) to obtain MI depth for classification. In the independent test datasets, the uterus and tumor detection model achieves an average precision rate of 98.70% and 87.93%, respectively. Selecting the optimal MRI slices method yields an accuracy of 97.83%. The uterus and tumor segmentation model with mean IOU of 0.738 and 0.655, mean PA of 0.867 and 0.749, and mean DSC of 0.845 and 0.779, respectively. Finally, the CAD method based on the calculated MI depth reaches an accuracy of 86.9%, a sensitivity of 81.8%, and a specificity of 91.7% for early EC classification. In this study, the CAD method implements an end-to-end early EC classification and is found to be on par with radiologists in terms of performance. It is more intuitive and interpretable than previous DL-based CAD methods.

Effects of intensity-modulated radiotherapy (IMRT) and volumetric modulated arc therapy (VMAT) on survival benefits and poor prognostic factors in patients with cervical cancer

This study aimed to explore the influencing factors of survival benefit and poor prognosis of cervical cancer patients under different radiotherapy modalities. A total of 186 patients with cervical cancer treated in our hospital from January 2022 to December 2023 were selected for the retrospective analysis. 126 patients received static intensity-modulated radiation therapy (IMRT) combined with cisplatin. Another 60 cases received volumetric modulated arc therapy (VMAT) combined with cisplatin. The occurrence of adverse reactions, overall survival rate, and recurrence rate were compared between the two groups. COX regression model was used to analyze the influencing factors of the poor prognosis. There was no difference between the disease control rate (DCR) and objective remission rate (ORR), and the overall survival and recurrence rates in the two groups. The incidence of myelosuppression was much higher in the IMRT group than the VMAT group. Compared with the survival group, the percentage of lymph node metastasis (LNM) and positive margins were significantly increased in the patients in the death group. COX multifactorial analysis confirmed that LNM and positive cutting margins were independent risk factors affecting poor prognosis after radiotherapy in cervical cancer patients (P < 0.05). Both IMRT and VMAT could achieve certain effects in the treatment of cervical cancer and had similar effects in short-term survival recurrence. However, VMAT had a lower incidence of myelosuppression. LNM and positive margins were factors influencing the poor prognosis of patients.

Super-resolution reconstruction for early cervical cancer magnetic resonance imaging based on deep learning

This study aims to develop a super-resolution (SR) algorithm tailored specifically for enhancing the image quality and resolution of early cervical cancer (CC) magnetic resonance imaging (MRI) images. The proposed method is subjected to both qualitative and quantitative analyses, thoroughly investigating its performance across various upscaling factors and assessing its impact on medical image segmentation tasks. The innovative SR algorithm employed for reconstructing early CC MRI images integrates complex architectures and deep convolutional kernels. Training is conducted on matched pairs of input images through a multi-input model. The research findings highlight the significant advantages of the proposed SR method on two distinct datasets at different upscaling factors. Specifically, at a 2× upscaling factor, the sagittal test set outperforms the state-of-the-art methods in the PSNR index evaluation, second only to the hybrid attention transformer, while the axial test set outperforms the state-of-the-art methods in both PSNR and SSIM index evaluation. At a 4× upscaling factor, both the sagittal test set and the axial test set achieve the best results in the evaluation of PNSR and SSIM indicators. This method not only effectively enhances image quality, but also exhibits superior performance in medical segmentation tasks, thereby providing a more reliable foundation for clinical diagnosis and image analysis.

A transcription factor that promotes proliferation, migration, invasion, and epithelial–mesenchymal transition of ovarian cancer cells and its possible mechanisms

Abstract Background Ovarian cancer is one of the most common gynecological malignancies with the high morbidity and mortality. This study was aimed to explore the role of non-structure maintenance of chromosomes condensin I complex subunit H (NCAPH) in the progression of ovarian cancer (OC) and the transcription regulatory effects of GATA binding protein 3 (GATA3) on this gene. Methods Firstly, NCAPH and GATA3 expression in OC tissues and several human OC cell lines was, respectively, evaluated by TNMplot database and Western blot analysis. Then, NCAPH was silenced to assess the proliferation, migration, and invasion of OC cells in turn using CCK-8, wound healing, and transwell assays. Western blotting was used to determine the expression of epithelial--mesenchymal transition (EMT)-related proteins and PI3K/PDK1/AKT signaling proteins. The potential binding sites of GATA3 on NCAPH promoter were predicated using JASPAR database, which were verified by luciferase reporter assay and chromosomal immunoprecipitation. Subsequently, GATA3 was overexpressed to examine the biological functions of OC cells with NCAPH silencing. Results NCAPH and GATA3 expression was significantly upregulated in OC tissues and cell lines. NCAPH loss-of-function notably inhibited the proliferation, migration, invasion, and EMT of OC cells. Moreover, the expression of p-PI3K, PDK1, and p-AKT was downregulated after NCAPH knockdown. Furthermore, GATA3 was confirmed to bind to NCAPH promoter. GATA3 overexpression alleviated the inhibitory effects of NCAPH silencing on the proliferation, migration, invasion, EMT, and expression of proteins in PI3K/PDK1/AKT pathway of OC cells. Conclusion To sum up, NCAPH expression transcriptional activation by GATA3 accelerates the progression of OC via upregulating PI3K/PDK1/AKT pathway.

Deep learning based on ultrasound images to predict platinum resistance in patients with epithelial ovarian cancer

The study aimed at developing and validating a deep learning (DL) model based on the ultrasound imaging for predicting the platinum resistance of patients with epithelial ovarian cancer (EOC). 392 patients were enrolled in this retrospective study who had been diagnosed with EOC between 2014 and 2020 and underwent pelvic ultrasound before initial treatment. A DL model was developed to predict patients' platinum resistance, and the model underwent evaluation through receiver-operating characteristic (ROC) curves, decision curve analysis (DCA), and calibration curve. The ROC curves showed that the area under the curve (AUC) of the DL model for predicting patients' platinum resistance in the internal and external test sets were 0.86 (95% CI 0.83-0.90) and 0.86 (95% CI 0.84-0.89), respectively. The model demonstrated high clinical value through clinical decision curve analysis and exhibited good calibration efficiency in the training cohort. Kaplan-Meier analyses showed that the model's optimal cutoff value successfully distinguished between patients at high and low risk of recurrence, with hazard ratios of 3.1 (95% CI 2.3-4.1, P < 0.0001) and 2.9 (95% CI 2.3-3.9; P < 0.0001) in the high-risk group of the internal and external test sets, serving as a prognostic indicator. The DL model based on ultrasound imaging can predict platinum resistance in patients with EOC and may support clinicians in making the most appropriate treatment decisions.

An immune-related pseudogene signature to improve prognosis prediction of endometrial carcinoma patients

AbstractBackgroundPseudogenes show multiple functions in various cancer types, and immunotherapy is a promising cancer treatment. Therefore, this study aims to identify immune-related pseudogene signature in endometrial cancer (EC).MethodsGene transcriptome data of EC tissues and corresponding clinical information were downloaded from The Cancer Genome Atlas (TCGA) through UCSC Xena browser. Spearman correlation analysis was performed to identify immune-related pseudogenes (IRPs) between the immune genes and pseudogenes. Univariate Cox regression, LASSO, and multivariate were performed to develop a risk score signature to investigate the different overall survival (OS) between high- and low-risk groups. The prognostic significance of the signature was assessed by the Kaplan–Meier curve, time-dependent receiver operating characteristic (ROC) curve. The abundance of 22 immune cell subtypes of EC patients was evaluated using CIBERSORT.ResultsNine IRPs were used to build a prognostic signature. Survival analysis revealed that patients in the low-risk group presented longer OS than those in the high-risk group as well as in multiple subgroups. The signature risk score was independent of other clinical covariates and was associated with several clinicopathological variables. The prognostic signature reflected infiltration by multiple types of immune cells and revealed the immunotherapy response of patients with anti-programmed death-1 (PD-1) and anti-programmed cell death 1 ligand 1 (PD-L1) therapy. Function enrichment analysis revealed that the nine IRPs were mainly involved in multiple cancer-related pathways.ConclusionWe identified an immune-related pseudogene signature that was strongly correlated with the prognosis and immune response to EC. The signature might have important implications for improving the clinical survival of EC patients and provide new strategies for cancer treatment.