1
|
Everson MA, Garcia-Peraza-Herrera L, Wang HP, Lee CT, Chung CS, Hsieh PH, Chen CC, Tseng CH, Hsu MH, Vercauteren T, Ourselin S, Kashin S, Bisschops R, Pech O, Lovat L, Wang WL, Haidry RJ. 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. Gastrointest Endosc 2021; 94:273-281. [PMID: 33549586 DOI: 10.1016/j.gie.2021.01.043] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/20/2020] [Accepted: 01/29/2021] [Indexed: 12/11/2022]
Abstract
BACKGROUND AND AIMS Intrapapillary capillary loops (IPCLs) are microvascular structures that correlate with the invasion depth of early squamous cell neoplasia 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 for early squamous cell neoplasia where appropriate. METHODS One hundred fifteen patients were recruited at 2 academic Taiwanese hospitals. Magnification endoscopy narrow-band imaging videos of squamous mucosa were labeled as dysplastic or normal according to their histology, and IPCL patterns were classified by consensus of 3 experienced clinicians. A convolutional neural network (CNN) was trained to classify IPCLs, using 67,742 high-quality magnification endoscopy narrow-band images 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 Japanese Endoscopic Society 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 with an expert panel of endoscopists.
Collapse
Affiliation(s)
| | | | - Hsiu-Po Wang
- National Taiwan University Hospital, Taipei, Taiwan
| | | | | | | | | | | | - Ming-Hung Hsu
- Department of Internal Medicine, E-Da Hospital/ I-Shou University, Kaohsiung, Taiwan
| | - Tom Vercauteren
- Department of Interventional Image Computing, Kings College London, London, United Kingdom
| | - Sebastien Ourselin
- School of Biomedical Engineering & Imaging Sciences, Kings College London, London, United Kingdom
| | - Sergey Kashin
- Department of Gastroenterology, Yaroslavl Oncology Hospital, Yaroslavl, Russian Federation
| | - Raf Bisschops
- Department of Gastroenterology, UZ Leuven, Leuven, Belgium
| | - Oliver Pech
- Department of Gastroenterology, Krankenhaus Barmherzige Bruder, Regensburg, Germany
| | - Laurence Lovat
- Department of Gastroenterology, University College London Hospitals, London, United Kingdom
| | - Wen-Lun Wang
- Department of Internal Medicine, E-Da Hospital/ I-Shou University, Kaohsiung, Taiwan; School of Medicine, College of Medicine, I-Shou University, Kaohsiung, Taiwan
| | - Rehan J Haidry
- University College London Hospitals, London, United Kingdom
| |
Collapse
|