Detection of Colorectal Adenocarcinoma and Grading Dysplasia on Histopathologic Slides Using Deep Learning.

Researchers

Journal

Modalities

Models

Abstract

Colorectal cancer is one of the most common types of cancer among men and women. The grading of dysplasia and the detection of adenocarcinoma are important clinical tasks in the diagnosis of colorectal cancer and shape the patients’ follow-up plans. This study evaluates the feasibility of deep learning models for the classification of colorectal lesions into four classes: benign, low-grade dysplasia, high-grade dysplasia, and adenocarcinoma. To this end, a deep neural network was developed on a training set of 655 whole-slide images of digitized colorectal resection slides from a tertiary medical institution and evaluate it on an internal test set of 234 slides, as well as on an external test set of 606 adenocarcinoma slides from The Cancer Genome Atlas database. The model achieves an overall accuracy, sensitivity, and specificity of 95.5%, 91.0%, and 97.1% on the internal test set and an accuracy and sensitivity of 98.5% for adenocarcinoma detection task on the external test set. Results suggest that such deep learning models can potentially assist pathologists in grading colorectal dysplasia, detecting adenocarcinoma, prescreening, and prioritizing the reviewing of suspicious cases to improve the turnaround time for patients with a high risk of colorectal cancer. Furthermore, the high sensitivity on the external test set suggests the model’s generalizability in detecting colorectal adenocarcinoma on whole slide images across different institutions.Copyright © 2022. Published by Elsevier Inc.