Owlet Smart Sock
February 1, 20221951 – 1952
March 1, 2022Article of the Month – February 2022
Evaluation of a Deep Neural Network for Automated Classification of Colorectal Polyps on Histopathologic Slides
Evaluation of a Deep Neural Network for Automated Classification of Colorectal Polyps on Histopathologic Slides
Jason W.Wei, BA; Arief A. Suriawinata, MD; Louis J. Vaickus, MD, PhD; Bing Ren, MD, PhD; Xiaoying Liu, MD; Mikhail Lisovsky,MD, PhD; Naofumi Tomita, MS; Behnaz Abdollahi, PhD; Adam S. Kim, MD; Dale C. Snover, MD; John A. Baron, MD; Elizabeth L. Barry, PhD; Saeed Hassanpour, PhD
Importance
Histologic classification of colorectal polyps plays a critical role in screening for colorectal cancer and care of affected patients. An accurate and automated algorithm for the classification of colorectal polyps on digitized histopathologic slides could benefit practitioners and patients.
Objectives
To evaluate the performance and generalizability of a deep neural network for colorectal polyp classification on histopathologic slide images using a multi-institutional data set.
Design, Setting and Participants
This prognostic study used histopathologic slides collected from January 1, 2016, to June 31, 2016, from Dartmouth-Hitchcock Medical Center, Lebanon, New Hampshire, with 326 slides used for training, 157 slides for an internal data set, and 25 for a validation set. For the external data set, 238 slides for 179 distinct patients were obtained from 24 institutions across 13 US states. Data analysis was performed from April 9 to November 23, 2019.
Main Outcomes and Measures.
Accuracy, sensitivity, and specificity of the model to classify 4 major colorectal polyp types: tubular adenoma, tubulovillous or villous adenoma, hyperplastic polyp, and sessile serrated adenoma. Performance was compared with that of local pathologists at the point of care identified from corresponding pathology laboratories.
Results
For the internal evaluation on the 157 slides with ground truth labels from 5 pathologists, the deep neural network had a mean accuracy of 93.5% (95% CI, 89.6%-97.4%) compared with local pathologists’ accuracy of 91.4% (95% CI, 87.0%-95.8%). On the external test set of 238 slides with ground truth labels from 5 pathologists, the deep neural network achieved an accuracy of 87.0% (95% CI, 82.7%-91.3%), which was comparable with local pathologists’ accuracy of 86.6% (95% CI, 82.3%-90.9%).
Conclusions
The findings suggest that this model may assist pathologists by improving the diagnostic efficiency, reproducibility, and accuracy of colorectal cancer screenings.
Relevance to Healthcare Field
Colorectal cancer is the second most common cancer-related death in the US. The risk of malignant tumors depends on factors, including the type of polyps present on colonoscopy. An accurate histologic classification of colorectal polyps is required to determine clinical decision and management. This study evaluated a deep neural network (a class of computational models) on a multi-institutional data set and proved to have comparable diagnostic performance with local pathologists’ increasing diagnostic accuracy of colorectal cancer screenings.
This model could be implemented to guide pathologists by identifying areas of interest on digitized slides improving diagnostic value.