This paper is only available as a PDF. To read, Please Download here.
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.
Acronyms and abbreviations:
AI (Artificial intelligence), AUC (Area under the receiver operator curve), BE (Barrett’s esophagus), CAD (computer aided diagnosis), CNN (Convolutional neural network), EAC (Esophageal adenocarcinoma), EMR (endoscopic mucosal resection), Fps (frames per second), GPU (Graphics processing unit), HD (High definition), HGD (high grade dysplasia), IMC (Intramucosal adenocarcinoma), LGD (low grade dysplasia), NBI (Narrow band imaging), NDBE (non dysplastic Barrett’s esophagus), OE (optical enhancement), WL (white light)Article info
Publication history
Accepted:
November 18,
2022
Received in revised form:
November 8,
2022
Received:
September 25,
2022
Publication stage
In Press Journal Pre-ProofFootnotes
Acknowledgements
LBL is supported by the National Institute for Health Research University College London Hospitals Biomedical Research Centre and the CRUK Experimental Cancer Medicine Centre at UCL. RH and LBL are supported by the Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS) at UCL; [203145Z/16/Z].
Identification
Copyright
© 2022 by the American Society for Gastrointestinal Endoscopy
User license
Creative Commons Attribution (CC BY 4.0) | How you can reuse 
Elsevier's open access license policy
Creative Commons Attribution (CC BY 4.0)
Permitted
- Read, print & download
- Redistribute or republish the final article
- Text & data mine
- Translate the article
- Reuse portions or extracts from the article in other works
- Sell or re-use for commercial purposes
Elsevier's open access license policy
