【Successful Development of Pathological AI】Now Possible to Classify Poorly Differentiated Colorectal Adenocarcinoma - Published in Diagnostics/Special issue: Artificial Intelligence in Gastrointestinal Disease: Diagnosis and Management -


Medmain Inc., a provider of “PidPort” digital pathology support solutions, has successfully developed a pathological AI that enables to classify Poorly Differentiated Colorectal Adenocarcinoma using deep learning.
We would also like to announce that a paper on this development has been submitted to Diagnostics issued by MDPI and published as a special feature of Artificial Intelligence in Gastrointestinal Disease: Diagnosis and Management on November 9, 2021.

DOI:https://www.mdpi.com/2075-4418/11/11/2074

Colorectal poorly differentiated adenocarcinoma (ADC) is known to have a poor prognosis as compared with well to moderately differentiated ADC. The frequency of poorly differentiated ADC is relatively low (usually less than 5% among colorectal carcinomas). Histopathological diagnosis based on endoscopic biopsy specimens is currently the most cost effective method to perform as part of colonoscopic screening in average risk patients, and it is an area that could benefit from AI-based tools to aid pathologists in their clinical workflows. In this study, we trained deep learning models to classify poorly differentiated colorectal ADC from Whole Slide Images (WSIs) using a simple transfer learning method. We evaluated the models on a combination of test sets obtained from five distinct sources, achieving receiver operating characteristic curve (ROC) area under the curves (AUCs) up to 0.95 on 1799 test cases.