English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Objective: We develop a computer-aided diagnosis (CAD) system using deeplearning approaches for lesion detection and classification on whole-slideimages (WSIs) with breast cancer. The deep features being distinguishing inclassification from the convolutional neural networks (CNN) are demonstrated inthis study to provide comprehensive interpretability for the proposed CADsystem using pathological knowledge. Methods: In the experiment, a total of 186slides of WSIs were collected and classified into three categories:Non-Carcinoma, Ductal Carcinoma in Situ (DCIS), and Invasive Ductal Carcinoma(IDC). Instead of conducting pixel-wise classification into three classesdirectly, we designed a hierarchical framework with the multi-view scheme thatperforms lesion detection for region proposal at higher magnification first andthen conducts lesion classification at lower magnification for each detectedlesion. Results: The slide-level accuracy rate for three-categoryclassification reaches 90.8% (99/109) through 5-fold cross-validation andachieves 94.8% (73/77) on the testing set. The experimental results show thatthe morphological characteristics and co-occurrence properties learned by thedeep learning models for lesion classification are accordant with the clinicalrules in diagnosis. Conclusion: The pathological interpretability of the deepfeatures not only enhances the reliability of the proposed CAD system to gainacceptance from medical specialists, but also facilitates the development ofdeep learning frameworks for various tasks in pathology. Significance: Thispaper presents a CAD system for pathological image analysis, which fills theclinical requirements and can be accepted by medical specialists with providingits interpretability from the pathological perspective.

A Computer-Aided Diagnosis System for Breast Pathology: A Deep Learning Approach with Model Interpretability from Pathological Perspective