UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

A clinically interpretable convolutional neural network for the real time prediction of early squamous cell cancer of the esophagus; comparing diagnostic performance with a panel of expert European and Asian endoscopists

Everson, MA; Herrera, LCGP; Wang, H-P; Lee, C-T; Chung, C-S; Hsieh, P-H; Chen, C-C; ... Haidry, RJ; + view all (2021) A clinically interpretable convolutional neural network for the real time prediction of early squamous cell cancer of the esophagus; comparing diagnostic performance with a panel of expert European and Asian endoscopists. Gastrointestinal Endoscopy 10.1016/j.gie.2021.01.043. (In press).

[thumbnail of IPCL paper - revised final manuscript clean.pdf] Text
IPCL paper - revised final manuscript clean.pdf - Accepted version
Access restricted to UCL open access staff until 6 February 2022.

Download (266kB)

Abstract

BACKGROUND AND AIMS: Intrapapillary capillary loops (IPCLs) are microvascular structures that correlate with invasion depth of early squamous cell neoplasia (ESCN) and allow accurate prediction of histology. Artificial intelligence may improve human recognition of IPCL patterns and prediction of histology to allow prompt access to endoscopic therapy of ESCN where appropriate METHODS: One hundred fifteen patients were recruited at 2 academic Taiwanese hospitals. ME-NBI videos of squamous mucosa were labeled as dysplastic or normal according to their histology and IPCL patterns classified by consensus of 3 experienced clinicians. A convolutional neural network (CNN) was trained to classify IPCLs, using 67742 high quality ME-NBI by 5-fold cross validation. Performance measures were calculated to give an average F1 score, accuracy, sensitivity, and specificity. A panel of 5 Asian and 4 European experts predicted the histology of a random selection of 158 images using the JES IPCL classification; accuracy, sensitivity, specificity, positive and negative predictive values were calculated. RESULTS: Expert European Union (EU) and Asian endoscopists attained F1 scores (a measure of binary classification accuracy) of 97.0% and 98%, respectively. Sensitivity and accuracy of the EU and Asian clinicians were 97%, 98% and 96.9%, 97.1% respectively. The CNN average F1 score was 94%, sensitivity 93.7% and accuracy 91.7%. Our CNN operates at video rate and generates class activation maps that can be used to visually validate CNN predictions. CONCLUSIONS: We report a clinically interpretable CNN developed to predict histology based on IPCL patterns, in real-time, using the largest reported dataset of images for this purpose. Our CNN achieved diagnostic performance comparable to an expert panel of endoscopists.

Type: Article
Title: A clinically interpretable convolutional neural network for the real time prediction of early squamous cell cancer of the esophagus; comparing diagnostic performance with a panel of expert European and Asian endoscopists
Location: United States
DOI: 10.1016/j.gie.2021.01.043
Publisher version: http://dx.doi.org/10.1016/j.gie.2021.01.043
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
UCL classification: UCL
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Medical Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Medical Sciences > Div of Surgery and Interventional Sci
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Medical Sciences > Div of Surgery and Interventional Sci > Department of Targeted Intervention
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Med Phys and Biomedical Eng
URI: https://discovery.ucl.ac.uk/id/eprint/10125333
Downloads since deposit
1Download
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item