Deep learning-based endoscopic anatomy classification: an accelerated approach for data preparation and model validation

• Published in: Surgical Endoscopy Vol. 36; no. 6; pp. 3811 - 3821
• Main Authors: Chang, Yuan-Yen, Li, Pai-Chi, Chang, Ruey-Feng, Yao, Chih-Da, Chen, Yang-Yuan, Chang, Wen-Yen, Yen, Hsu-Heng
• Format: Journal Article
• Language: English
• Published: New York Springer Science and Business Media LLC 01.06.2022; Springer US; Springer Nature B.V
• Subjects: Abdominal Surgery; Accuracy; Artificial Intelligence; Classification; Computer engineering; Datasets; Deep Learning; Endoscopy; Endoscopy, Gastrointestinal; Endoscopy, Gastrointestinal - methods; Esophagus; Gastroenterology; Gynecology; Hepatology; Hospitals; Humans; Medicine; Medicine & Public Health; Neural Networks, Computer; Proctology; Quality control; Retrospective Studies; Surgery; Ulcers; Deep learning; Artificial intelligence; Endoscopy anatomy
• ISSN: 0930-2794; 1432-2218; 1432-2218
• DOI: 10.1007/s00464-021-08698-2

Background Photodocumentation during endoscopy procedures is one of the indicators for endoscopy performance quality; however, this indicator is difficult to measure and audit in the endoscopy unit. Emerging artificial intelligence technology may solve this problem, which requires a large amount of material for model development. We developed a deep learning-based endoscopic anatomy classification system through convolutional neural networks with an accelerated data preparation approach. Patients and methods We retrospectively collected 8,041 images from esophagogastroduodenoscopy (EGD) procedures and labeled them using two experts for nine anatomical locations of the upper gastrointestinal tract. A base model for EGD image multiclass classification was first developed, and an additional 6,091 images were enrolled and classified by the base model. A total of 5,963 images were manually confirmed and added to develop the subsequent enhanced model. Additional internal and external endoscopy image datasets were used to test the model performance. Results The base model achieved total accuracy of 96.29%. For the enhanced model, the total accuracy was 96.64%. The overall accuracy improved with the enhanced model compared with the base model for the internal test dataset without narrowband images (93.05% vs. 91.25%, p  < 0.01) or with narrowband images (92.74% vs. 90.46%, p  < 0.01). The total accuracy was 92.56% of the enhanced model on the external test dataset. Conclusions We constructed a deep learning-based model with an accelerated approach that can be used for quality control in endoscopy units. The model was also validated with both internal and external datasets with high accuracy.