Hussein, Mohamed;
Lines, David;
Puyal, Juana González-Bueno;
Kader, Rawen;
Bowman, Nicola;
Sehgal, Vinay;
Toth, Daniel;
... Haidry, Rehan; + view all
(2023)
Computer aided characterization of early cancer in Barrett's esophagus on i-scan magnification imaging - Multicenter international study.
Gastrointestinal Endoscopy
, 97
(4)
pp. 646-654.
10.1016/j.gie.2022.11.020.
Preview |
Text
1-s2.0-S0016510722021952-main.pdf Download (1MB) | Preview |
Abstract
BACKGROUND AND AIMS: We aimed to develop a computer aided characterization system that can support the diagnosis of dysplasia in Barrett's esophagus (BE) on magnification endoscopy. METHODS: Videos were collected in high-definition magnification white light and virtual chromoendoscopy with i-scan (Pentax Hoya, Japan) imaging in patients with dysplastic/ non-dysplastic BE (NDBE) from 4 centres. We trained a neural network with a Resnet101 architecture to classify frames as dysplastic or non-dysplastic. The network was tested on three different scenarios: high-quality still images, all available video frames and a selected sequence within each video. RESULTS: 57 different patients each with videos of magnification areas of BE (34 dysplasia, 23 NDBE) were included. Performance was evaluated using a leave-one-patient-out cross-validation methodology. 60,174 (39,347 dysplasia, 20,827 NDBE) magnification video frames were used to train the network. The testing set included 49,726 iscan-3/optical enhancement magnification frames. On 350 high-quality still images the network achieved a sensitivity of 94%, specificity of 86% and Area under the ROC (AUROC) of 96%. On all 49,726 available video frames the network achieved a sensitivity of 92%, specificity of 82% and AUROC of 95%. On a selected sequence of frames per case (total of 11,471 frames) we used an exponentially weighted moving average of classifications on consecutive frames to characterize dysplasia. The network achieved a sensitivity of 92%, specificity of 84% and AUROC of 96% The mean assessment speed per frame was 0.0135 seconds (SD, + 0.006) CONCLUSION: Our network can characterize BE dysplasia with high accuracy and speed on high-quality magnification images and sequence of video frames moving it towards real time automated diagnosis.
Archive Staff Only
 |
View Item |
