Cookies on this website
We use cookies to ensure that we give you the best experience on our website. If you click 'Continue' we'll assume that you are happy to receive all cookies and you won't see this message again. Click 'Find out more' for information on how to change your cookie settings.

BACKGROUND AIMS: Barrett's epithelium measurement using widely accepted Prague C&M classification is highly operator dependent. We propose a novel methodology for measuring this risk score automatically. The method also enables quantification of the area of Barrett's epithelium (BEA) and islands which was not possible before. Furthermore, it allows 3D reconstruction of the esophageal surface enabling interactive 3D visualization. We aim to assess the accuracy of the proposed AI system both on phantom and endoscopic patient data. METHODS: Utilizing advanced deep learning, a depth estimator network is used to predict endoscope camera distance from the gastric folds. By segmenting BEA and gastro-esophageal junction and projecting them to the estimated mm distances, we measure C&M scores including the BEA. The derived endoscopy AI system is tested on a purpose-built 3D printed esophagus phantom with varying BEA and on 194 high-definition videos from 131 patients with C&M values scored by expert endoscopists. RESULTS: Endoscopic phantom video data demonstrated a 97.2 % accuracy with a marginal ± 0.9 mm average deviation for C&M and island measurements, while for BEA we achieved 98.4 % accuracy with only ± 0.4 cm2 average deviation compared to ground-truth. On patient data, the C&M measurements provided by our system concord with expert scores with marginal overall relative error (mean difference) of 8 % (3.6 mm) and 7 % (2.8 mm) for C and M scores, respectively. CONCLUSIONS: The proposed methodology automatically extracts Prague C&M scores with high accuracy. Quantification and 3D-reconstruction of the entire Barrett's area provides new opportunities for risk stratification and assessment of therapy response.

Original publication

DOI

10.1053/j.gastro.2021.05.059

Type

Journal article

Journal

Gastroenterology

Publication Date

08/06/2021

Keywords

Deep learning, Esophageal cancer gastric folds), Imaging, Risk assessment, Three-Dimensional