{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/computer-aided-diagnosis-in-histopathological","title":"Computer-aided diagnosis in histopathological images of the endometrium using a convolutional neural network and attention mechanisms","arxiv_id":"1904.10626","date":"2019-04-24","proceeding":null,"authors":["Hao Sun","Xianxu Zeng","Tao Xu","Gang Peng","Yutao Ma"],"abstract":"Uterine cancer, also known as endometrial cancer, can seriously affect the\nfemale reproductive organs, and histopathological image analysis is the gold\nstandard for diagnosing endometrial cancer. However, due to the limited\ncapability of modeling the complicated relationships between histopathological\nimages and their interpretations, these computer-aided diagnosis (CADx)\napproaches based on traditional machine learning algorithms often failed to\nachieve satisfying results. In this study, we developed a CADx approach using a\nconvolutional neural network (CNN) and attention mechanisms, called HIENet.\nBecause HIENet used the attention mechanisms and feature map visualization\ntechniques, it can provide pathologists better interpretability of diagnoses by\nhighlighting the histopathological correlations of local (pixel-level) image\nfeatures to morphological characteristics of endometrial tissue. In the\nten-fold cross-validation process, the CADx approach, HIENet, achieved a 76.91\n$\\pm$ 1.17% (mean $\\pm$ s. d.) classification accuracy for four classes of\nendometrial tissue, namely normal endometrium, endometrial polyp, endometrial\nhyperplasia, and endometrial adenocarcinoma. Also, HIENet achieved an\narea-under-the-curve (AUC) of 0.9579 $\\pm$ 0.0103 with an 81.04 $\\pm$ 3.87%\nsensitivity and 94.78 $\\pm$ 0.87% specificity in a binary classification task\nthat detected endometrioid adenocarcinoma (Malignant). Besides, in the external\nvalidation process, HIENet achieved an 84.50% accuracy in the four-class\nclassification task, and it achieved an AUC of 0.9829 with a 77.97% (95% CI,\n65.27%-87.71%) sensitivity and 100% (95% CI, 97.42%-100.00%) specificity. In\nsummary, the proposed CADx approach, HIENet, outperformed three human experts\nand four end-to-end CNN-based classifiers on this small-scale dataset composed\nof 3,500 hematoxylin and eosin (H&E) images regarding overall classification\nperformance.","url_abs":"http://arxiv.org/abs/1904.10626v1","url_pdf":"http://arxiv.org/pdf/1904.10626v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"computer-aided-diagnosis-in-histopathological","repo_url":"https://github.com/ssea-lab/DL4ETI","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"binary-classification","task_name":"Binary Classification"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"sensitivity","task_name":"Sensitivity"},{"task_slug":"specificity","task_name":"Specificity"}],"methods":[{"method_slug":"interpretability","method_name":"Interpretability"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}