Seong Ji Choi1, Mohammad Azam Khan2, Hyuk Soon Choi3, Jaegul Choo4, Jae Min Lee5, Soonwook Kwon6, Bora Keum5, Hoon Jai Chun5. 1. Department of Internal Medicine, Hanyang University College of Medicine, Seoul, Republic of Korea. 2. Graduate School of Artificial Intelligence, KAIST, Daejeon, Republic of Korea. 3. Division of Gastroenterology and Hepatology, Department of Internal Medicine, Korea University College of Medicine, Seoul, Republic of Korea. mdkorea@gmail.com. 4. Graduate School of Artificial Intelligence, KAIST, Daejeon, Republic of Korea. jchoo@kaist.ac.kr. 5. Division of Gastroenterology and Hepatology, Department of Internal Medicine, Korea University College of Medicine, Seoul, Republic of Korea. 6. Department of Anatomy, School of Medicine, Catholic University of Daegu, Daegu, Republic of Korea.
Abstract
BACKGROUND: Esophagogastroduodenoscopy (EGD) is generally a safe procedure, but adverse events often occur. This highlights the necessity of the quality control of EGD. Complete visualization and photo documentation of upper gastrointestinal (UGI) tracts are important measures in quality control of EGD. To evaluate these measures in large scale, we developed an AI-driven quality control system for EGD through convolutional neural networks (CNNs) using archived endoscopic images. METHODS: We retrospectively collected and labeled images from 250 EGD procedures, a total of 2599 images from eight locations of the UGI tract, using the European Society of Gastrointestinal Endoscopy (ESGE) photo documentation methods. The label confirmed by five experts was considered the gold standard. We developed a CNN model for multi-class classification of EGD images to one of the eight locations and binary classification of each EGD procedure based on its completeness. RESULTS: Our CNN model successfully classified the EGD images into one of the eight regions of UGI tracts with 97.58% accuracy, 97.42% sensitivity, 99.66% specificity, 97.50% positive predictive value (PPV), and 99.66% negative predictive value (NPV). Our model classified the completeness of EGD with 89.20% accuracy, 89.20% sensitivity, 100.00% specificity, 100.00% PPV, and 64.94% NPV. We analyzed the credibility of our model using a probability heatmap. CONCLUSIONS: We constructed a CNN model that could be used in the quality control of photo documentation in EGD. Our model needs further validation with a large dataset, and we expect our model to help both endoscopists and patients by improving the quality of EGD procedures.
BACKGROUND: Esophagogastroduodenoscopy (EGD) is generally a safe procedure, but adverse events often occur. This highlights the necessity of the quality control of EGD. Complete visualization and photo documentation of upper gastrointestinal (UGI) tracts are important measures in quality control of EGD. To evaluate these measures in large scale, we developed an AI-driven quality control system for EGD through convolutional neural networks (CNNs) using archived endoscopic images. METHODS: We retrospectively collected and labeled images from 250 EGD procedures, a total of 2599 images from eight locations of the UGI tract, using the European Society of Gastrointestinal Endoscopy (ESGE) photo documentation methods. The label confirmed by five experts was considered the gold standard. We developed a CNN model for multi-class classification of EGD images to one of the eight locations and binary classification of each EGD procedure based on its completeness. RESULTS: Our CNN model successfully classified the EGD images into one of the eight regions of UGI tracts with 97.58% accuracy, 97.42% sensitivity, 99.66% specificity, 97.50% positive predictive value (PPV), and 99.66% negative predictive value (NPV). Our model classified the completeness of EGD with 89.20% accuracy, 89.20% sensitivity, 100.00% specificity, 100.00% PPV, and 64.94% NPV. We analyzed the credibility of our model using a probability heatmap. CONCLUSIONS: We constructed a CNN model that could be used in the quality control of photo documentation in EGD. Our model needs further validation with a large dataset, and we expect our model to help both endoscopists and patients by improving the quality of EGD procedures.