Computer-aided Detection of Squamous Carcinoma of the Cervix in Whole Slide Images

Abstract

Goal: Squamous cell carcinoma of cervix is one of the most prevalent cancer worldwide in females. Traditionally, the most indispensable diagnosis of cervix squamous carcinoma is histopathological assessment which is achieved under microscope by pathologist. However, human evaluation of pathology slide is highly depending on the experience of pathologist, thus big inter-and intra-observer variability exists. Digital pathology, in combination with deep learning provides an opportunity to improve the objectivity and efficiency of histopathologic slide analysis. Methods: In this study, we obtained 800 haematoxylin and eosin stained slides from 300 patients suffered from cervix squamous carcinoma. Based on information from morphological heterogeneity in the tumor and its adjacent area, we established deep learning models using popular convolution neural network architectures (inception-v3, InceptionResnet-v2 and Resnet50). Then random forest was introduced to feature extractions and slide-based classification. Results: The overall performance of our proposed models on slide-based tumor discrimination were outstanding with an AUC scores ¿ 0.94. While, location identifications of lesions in whole slide images were mediocre (FROC scores ¿ 0.52) duo to the extreme complexity of tumor tissues. Conclusion: For the first time, our analysis workflow highlighted a quantitative visual-based slide analysis of cervix squamous carcinoma. Significance: This study demonstrates a pathway to assist pathologist and accelerate the diagnosis of patients by utilizing new computational approaches.

HEROHE Challenge: Predicting HER2 Status in Breast Cancer from Hematoxylin–Eosin Whole-Slide Imaging

“…The team Macaroon employed a two-stage method to solve the problem ( (accessed on 24 July 2022)). In stage A, a ResNet34 model, pre-trained on the CAMELYON16 [ 19 ] challenge datasets, was used for training a patch-based (256 by 256 pixels) classification model to differentiate normal tissue patches from tumor patches (see [ 41 ] for training details). A probability map, PM_A, was constructed using the results from each WSI.…”

Whole-slide-imaging Cancer Metastases Detection and Localization with Limited Tumorous Data

“…In the past decades, various deep-learning-based methods have been proposed to assist pathologists to detect and segment the cancer regions on histopathology slide images (Mori et al, 2013;Morar et al, 2012;Bandi et al, 2018;Li and Ping, 2018;Tian et al, 2019). However, all of these high-accuracy cancer detection methods follow the data-driven based supervised learning paradigm, where a large number of well-annotated whole slide images (WSI) containing tumors is demanding for model generalization and robustness.…”