Chen Li

Artificial Intelligence Performance in Image-Based Cancer Identification: Umbrella Review of Systematic Reviews

Background Artificial intelligence (AI) has the potential to transform cancer diagnosis, ultimately leading to better patient outcomes. Objective We performed an umbrella review to summarize and critically evaluate the evidence for the AI-based imaging diagnosis of cancers. Methods PubMed, Embase, Web of Science, Cochrane, and IEEE databases were searched for relevant systematic reviews from inception to June 19, 2024. Two independent investigators abstracted data and assessed the quality of evidence, using the Joanna Briggs Institute (JBI) Critical Appraisal Checklist for Systematic Reviews and Research Syntheses. We further assessed the quality of evidence in each meta-analysis by applying the Grading of Recommendations, Assessment, Development, and Evaluation (GRADE) criteria. Diagnostic performance data were synthesized narratively. Results In a comprehensive analysis of 158 included studies evaluating the performance of AI algorithms in noninvasive imaging diagnosis across 8 major human system cancers, the accuracy of the classifiers for central nervous system cancers varied widely (ranging from 48% to 100%). Similarities were observed in the diagnostic performance for cancers of the head and neck, respiratory system, digestive system, urinary system, female-related systems, skin, and other sites. Most meta-analyses demonstrated positive summary performance. For instance, 9 reviews meta-analyzed sensitivity and specificity for esophageal cancer, showing ranges of 90%-95% and 80%-93.8%, respectively. In the case of breast cancer detection, 8 reviews calculated the pooled sensitivity and specificity within the ranges of 75.4%-92% and 83%-90.6%, respectively. Four meta-analyses reported the ranges of sensitivity and specificity in ovarian cancer, and both were 75%-94%. Notably, in lung cancer, the pooled specificity was relatively low, primarily distributed between 65% and 80%. Furthermore, 80.4% (127/158) of the included studies were of high quality according to the JBI Critical Appraisal Checklist, with the remaining studies classified as medium quality. The GRADE assessment indicated that the overall quality of the evidence was moderate to low. Conclusions Although AI shows great potential for achieving accelerated, accurate, and more objective diagnoses of multiple cancers, there are still hurdles to overcome before its implementation in clinical settings. The present findings highlight that a concerted effort from the research community, clinicians, and policymakers is required to overcome existing hurdles and translate this potential into improved patient outcomes and health care delivery. Trial Registration PROSPERO CRD42022364278; https://www.crd.york.ac.uk/PROSPERO/view/CRD42022364278

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.

MYB Activates the Hedgehog Signaling Pathway to Repress Natural Killer Cytotoxicity in Cervical Cancer

ABSTRACT Natural killer (NK) cells present in the tumor microenvironment serve as a critical line of defense against various malignancies, including cervical cancer. While MYB is known to drive malignancy progression, its influence on NK cell activity remains poorly understood. This study aimed to elucidate the role of MYB in regulating NK cell cytotoxicity and its underlying mechanism in cervical cancer cells. MYB expression in cervical cancer tissues and cells was analyzed using bioinformatics and qRT‐PCR. Cell viability was assessed via CCK‐8 assay, while NK cell‐mediated killing of cervical cancer cells was evaluated through cytotoxicity assays. The expression levels of cytotoxic factors (IFN‐ γ and TNF‐ α ) were measured by ELISA, whereas perforin and granzyme B were detected via immunofluorescence. Apoptosis was analyzed using flow cytometry. To investigate the impact of MYB on the hedgehog signaling pathway, the expression levels of related factors (PTCH1, Gli1, and Gli2) were assessed using qRT‐PCR and Western blot. Bioinformatics and qRT‐PCR analyses revealed MYB overexpression in cervical cancer. Signaling pathway prediction indicated MYB enrichment in cytotoxic signaling pathways. Functional experiments demonstrated that MYB overexpression activated the hedgehog signaling pathway, thereby suppressing NK cell cytotoxicity in cervical cancer. Rescue experiments using the hedgehog signaling inhibitor GANT58 attenuated the suppressive effect of MYB overexpression on NK cytotoxicity. In summary, MYB inhibited NK cell cytotoxicity by activating the hedgehog signaling pathway in cervical cancer, suggesting its potential as a novel diagnostic marker and immunotherapeutic target.

Toripalimab combined with bevacizumab plus chemotherapy as first-line treatment for refractory recurrent or metastatic cervical cancer: a single-arm, open-label, phase II study (JS001-ISS-CO214)

To evaluate the efficacy and safety of adding toripalimab to bevacizumab and platinum-based chemotherapy as first-line treatment for refractory recurrent or metastatic (R/M) cervical cancer (CC). Patients were administered toripalimab (240 mg) + bevacizumab (7.5 mg/kg) combined with platinum-based chemotherapy once every three weeks for six cycles, followed by the maintenance therapy involving toripalimab + bevacizumab once every 3 weeks for 12 months or when disease progression or intolerable toxicity occurred. The primary endpoint was the objective response rate (ORR) per Response Evaluation Criteria in Solid Tumors version 1.1. The secondary endpoints were safety profiles, disease control rate (DCR), progression-free survival (PFS), and overall survival (OS). Twenty-four patients were enrolled in this study and in the final analysis. The median follow-up duration was 18.6 (range, 3.3-28.5) months. The ORR was 83.3% (95% confidence interval [CI]=62.6-95.3) and the DCR was 95.8% (95% CI=78.9-99.9); 9 (37.5%) patients achieved complete response, 11 (45.8%) achieved partial response, and 3 (12.5%) had stable disease. The median PFS was 22.6 (95% CI=10.4-34.7) months and the median OS was not reached. The most common grade 3 treatment-related adverse events (AEs) were neutropenia (41.7%) and leukopenia (16.7%). The most common immune-related AEs (irAEs) were thyroid dysfunction (37.5%) and increased adrenocorticotropic hormone (37.5%) and serum cortisol levels (33.3%). No grade ≥3 irAEs were observed. Toripalimab combined with bevacizumab and platinum-based chemotherapy show promising clinical efficacy and favorable safety profile, providing an alternative first-line treatment option for patients with R/M CC. ClinicalTrials.gov Identifier: NCT04973904.

PTGIS May Be a Predictive Marker for Ovarian Cancer by Regulating Fatty Acid Metabolism

Background. Ovarian cancer tends to metastasize to the omentum, which is an organ mainly composed of adipose tissue. Many studies have found that fatty acid metabolism is related to the occurrence and metastasis of cancers. Therefore, it is possible that fatty acid metabolism‐related genes (FAMRG) affect the prognosis of ovarian cancer patients. Methods. First, profiles of ovarian cancer and normal ovarian tissue transcriptomes were acquired from The Cancer Genome Atlas (TCGA) and the Genotype‐Tissue Expression (GTEx) databases. A LASSO regression predictive model was developed via the “glmnet” R package. The nomogram was created via the “regplot.” Gene Set Variation Analysis (GSVA), Kyoto Encyclopedia of Genes and Genomes (KEGG), and Gene Ontology (GO) analyses were conducted to determine the FAMRGs’ roles. The percentage of immunocyte infiltration was calculated via CIBERSORT. Using “pRRophetic,” the sensitivity of eight regularly used medications and immunotherapy was anticipated. Results. 125 genes were determined as different expression genes (DEGs). Based on RXRA, ECI2, PTGIS, and ACACB, a prognostic model is created and the risk score is calculated. Analyses of univariate and multivariate regressions revealed that the risk score was a distinct prognostic factor (univariate: HR: 2.855, 95% CI: 1.756‐4.739, P < 0.001; multivariate: HR: 2.943, 95% CI: 1.800‐4.812, P < 0.001). The nomogram demonstrated that it properly predicted the 1‐year survival rate. The expression of memory B molecular units, follicular helper T molecular units, regulatory T molecular units, and M1 macrophages differed remarkably between the groups at high and low risk (P < 0.05). Adipocytokine signaling pathways, cancer pathways, and degradation of valine, leucine, and isoleucine vary between high‐ and low‐risk populations. The findings of the GO enrichment revealed that the extracellular matrix and cellular structure were the two most enriched pathways. PTGIS, which is an important gene in fatty acid metabolism, was identified as the hub gene. This result was verified in ovarian cancer and ovarian tissues. The connection between the gene and survival was statistically remarkable (P = 0.015). The pRRophetic algorithm revealed that the low‐risk group was more adaptable to cisplatin, doxorubicin, 5‐fluorouracil, and etoposide (P < 0.001). Conclusion. PTGIS may be an indicator of prognosis and a possible therapeutic target for the therapy of ovarian cancer patients. The fatty acid metabolism of immune cells may be controlled, which has an indirect effect on cancer cell growth.

Circ_TMCO3 Inhibits the Progression of Cervical Cancer by Activating FRMD6 Expression by Restraining miR-1291

Cervical cancer (CC) is one of the most common cancers that threaten the life of women. More and more circular RNAs (circRNAs) have been found to be maladjusted in tumor tissues. However, the mechanism of circ_TMCO3 in CC needs to be studied. In this study, quantitative real-time polymerase chain reaction (qRT-PCR), western blot, and immunohistochemistry (IHC) were used to detect the expressions of circ_TMCO3, miR-1291, and FERM domain-containing protein 6 (FRMD6). Cell viability, proliferation, apoptosis, migration, invasion, and protein level were detected via 3-(4, 5-dimethyl-2-thiazolyl)-2, 5-diphenyl-2-H-tetrazolium bromide (MTT), 5-Ethynyl-2

Macrophages Phenotype Regulated by IL-6 Are Associated with the Prognosis of Platinum-Resistant Serous Ovarian Cancer: Integrated Analysis of Clinical Trial and Omics

Background. The treatment of platinum-resistant recurrent ovarian cancer (PROC) is a clinical challenge and a hot topic. Tumor microenvironment (TME) as a key factor promoting ovarian cancer progression. Macrophage is a component of TME, and it has been reported that macrophage phenotype is related to the development of PROC. However, the mechanism underlying macrophage polarization and whether macrophage phenotype can be used as a prognostic indicator of PROC remains unclear. Methods. We used ESTIMATE to calculate the number of immune and stromal components in high-grade serous ovarian cancer (HGSOC) cases from The Cancer Genome Atlas database. The differential expression genes (DEGs) were analyzed via protein–protein interaction network, Kyoto Encyclopedia of Genes and Genomes (KEGG) and gene ontology (GO) analysis to reveal major pathways of DEGs. CD80 was selected for survival analysis. IL-6 was selected for gene set enrichment analysis (GSEA). A subsequent cohort study was performed to confirm the correlation of IL-6 expression with macrophage phenotype in peripheral blood and to explore the clinical utility of macrophage phenotype for the prognosis of PROC patients. Results. A total of 993 intersecting genes were identified as candidates for further survival analysis. Further analysis revealed that CD80 expression was positively correlated with the survival of HGSOC patients. The results of GO and KEGG analysis suggested that macrophage polarization could be regulated via chemokine pathway and cytokine–cytokine receptor interaction. GSEA showed that the genes were mainly enriched in IL-6-STAT-3. Correlation analysis for the proportion of tumor infiltration macrophages revealed that M2 was correlated with IL-6. The results of a cohort study demonstrated that the regulation of macrophage phenotype by IL-6 is bidirectional. The high M1% was a protective factor for progression-free survival. Conclusion. Thus, the macrophage phenotype is a prognostic indicator in PROC patients, possibly via a hyperactive IL-6-related pathway, providing an additional clue for the therapeutic intervention of PROC.

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.

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.

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.

Toripalimab Combined With Chemotherapy and Bevacizumab as First-Line Treatment in Patients With Advanced Cervical Cancer

This is a single-arm, multicenter, phase II study to investigate efficacy and safety of Toripalimab combined with chemotherapy (paclitaxel and cisplatin) and Bevacizumab as first-line treatment in patients with recurrent, refractory and metastatic cervical cancer