Clinical-grade endometrial cancer detection system via whole-slide images using deep learning

Abstract

The accurate pathological diagnosis of endometrial cancer (EC) improves the curative effect and reduces the mortality rate. Deep learning has demonstrated expert-level performance in pathological diagnosis of a variety of organ systems using whole-slide images (WSIs). It is urgent to build the deep learning system for endometrial cancer detection using WSIs. The deep learning model was trained and validated using a dataset of 601 WSIs from PUPH. The model performance was tested on three independent datasets containing a total of 1,190 WSIs. For the retrospective test, we evaluated the model performance on 581 WSIs from PUPH. In the prospective study, 317 consecutive WSIs from PUPH were collected from April 2022 to May 2022. To further evaluate the generalizability of the model, 292 WSIs were gathered from PLAHG as part of the external test set. The predictions were thoroughly analyzed by expert pathologists. The model achieved an area under the receiver operating characteristic curve (AUC), sensitivity, and specificity of 0.928, 0.924, and 0.801, respectively, on 1,190 WSIs in classifying EC and non-EC. On the retrospective dataset from PUPH/PLAGH, the model achieved an AUC, sensitivity, and specificity of 0.948/0.971, 0.928/0.947, and 0.80/0.938, respectively. On the prospective dataset, the AUC, sensitivity, and specificity were, in order, 0.933, 0.934, and 0.837. Falsely predicted results were analyzed to further improve the pathologists’ confidence in the model. The deep learning model achieved a high degree of accuracy in identifying EC using WSIs. By pre-screening the suspicious EC regions, it would serve as an assisted diagnostic tool to improve working efficiency for pathologists.

Detection of malignancy in whole slide images of endometrial cancer biopsies using artificial intelligence

“…A paper by Song et al [14] uses a dataset from the cancer genome atlas along with the CPTAC dataset to distinguish between subtypes of endonmetrial cancer. A paper by Zhang et al [15] aims to split slides into endometrial cancer or not, achieving sensitivity and specificity of 0.924 and 0.801.…”

A self-supervised classification model for endometrial diseases

“…However, the use of deep learning for the classification of endometrial diseases still faces certain challenges (Zhang et al 2022 , 2021 ; Li et al 2022 ; Urushibara et al 2022 ; Mao et al 2022 ; Tao et al 2022 ; Zhao et al 2022 ; Sun et al 2020 ), such as incomplete classification, limited sample diversity, and dependence on specific data such as MRI and HI, resulting in low model robustness and generalisation. To address these concerns, this study proposed the BSEM model, which utilised TVU images as raw data for disease classification, which enhanced the model performance by training a joint classifier on the original and self-supervised tasks.…”

“…Deep learning is reported as a promising tool for the classification of endometrial diseases (Zhang et al 2022 , 2021 ; Li et al 2022 ; Urushibara et al 2022 ; Mao et al 2022 ; Tao et al 2022 ; Zhao et al 2022 ; Sun et al 2020 ). However, the studies on this topic have several issues: (1) incomplete classification, such as distinguishing between endometrial and non-endometrial cancers; (2) lack of sample diversity, as samples are often obtained from the same hospital or imaging device; and (3) existing studies primarily rely on magnetic resonance imaging (MRI) and histopathological images (HI) for classification, but these methods have drawbacks (Szkodziak et al 2014 ; 2017 ) such as high cost, time-consuming procedures, dependence on expert interpretation, potential complications from invasive techniques, and limited access to MRI equipment in certain healthcare facilities.…”

Role of artificial intelligence in digital pathology for gynecological cancers

“…The attention heatmapping, feature visualization, and end-to-end saliency-mapping improved the interpretability of the model. Zhang et al [47] utilized DeepLab v3 and ResNet-50 for the diagnosis of EC and non-EC in multiple datasets, demonstrating good performance (AUC, sensitivity, and specificity all >0.8). Sun and collaborators [48] proposed the HIENet framework, based on VGG-16 and incorporates two crucial blocks that utilize the visual attention mechanism.…”