Frontiers in Oncology (Aug 2022)
Application of deep learning in the real-time diagnosis of gastric lesion based on magnifying optical enhancement videos
- Mingjun Ma,
- Mingjun Ma,
- Mingjun Ma,
- Zhen Li,
- Zhen Li,
- Zhen Li,
- Tao Yu,
- Tao Yu,
- Tao Yu,
- Guanqun Liu,
- Guanqun Liu,
- Guanqun Liu,
- Rui Ji,
- Rui Ji,
- Rui Ji,
- Guangchao Li,
- Guangchao Li,
- Guangchao Li,
- Zhuang Guo,
- Limei Wang,
- Limei Wang,
- Limei Wang,
- Qingqing Qi,
- Qingqing Qi,
- Qingqing Qi,
- Xiaoxiao Yang,
- Xiaoxiao Yang,
- Xiaoxiao Yang,
- Junyan Qu,
- Junyan Qu,
- Junyan Qu,
- Xiao Wang,
- Xiuli Zuo,
- Xiuli Zuo,
- Xiuli Zuo,
- Hongliang Ren,
- Hongliang Ren,
- Yanqing Li,
- Yanqing Li,
- Yanqing Li
Affiliations
- Mingjun Ma
- Department of Gastroenterology, Qilu Hospital of Shandong University, Jinan, China
- Mingjun Ma
- Laboratory of Translational Gastroenterology, Qilu Hospital of Shandong University, Jinan, China
- Mingjun Ma
- Robot Engineering Laboratory for Precise Diagnosis and Therapy of Gastrointestinal Tumor, Qilu Hospital of Shandong University, Jinan, China
- Zhen Li
- Department of Gastroenterology, Qilu Hospital of Shandong University, Jinan, China
- Zhen Li
- Laboratory of Translational Gastroenterology, Qilu Hospital of Shandong University, Jinan, China
- Zhen Li
- Robot Engineering Laboratory for Precise Diagnosis and Therapy of Gastrointestinal Tumor, Qilu Hospital of Shandong University, Jinan, China
- Tao Yu
- Department of Gastroenterology, Qilu Hospital of Shandong University, Jinan, China
- Tao Yu
- Laboratory of Translational Gastroenterology, Qilu Hospital of Shandong University, Jinan, China
- Tao Yu
- Robot Engineering Laboratory for Precise Diagnosis and Therapy of Gastrointestinal Tumor, Qilu Hospital of Shandong University, Jinan, China
- Guanqun Liu
- Department of Gastroenterology, Qilu Hospital of Shandong University, Jinan, China
- Guanqun Liu
- Laboratory of Translational Gastroenterology, Qilu Hospital of Shandong University, Jinan, China
- Guanqun Liu
- Robot Engineering Laboratory for Precise Diagnosis and Therapy of Gastrointestinal Tumor, Qilu Hospital of Shandong University, Jinan, China
- Rui Ji
- Department of Gastroenterology, Qilu Hospital of Shandong University, Jinan, China
- Rui Ji
- Laboratory of Translational Gastroenterology, Qilu Hospital of Shandong University, Jinan, China
- Rui Ji
- Robot Engineering Laboratory for Precise Diagnosis and Therapy of Gastrointestinal Tumor, Qilu Hospital of Shandong University, Jinan, China
- Guangchao Li
- Department of Gastroenterology, Qilu Hospital of Shandong University, Jinan, China
- Guangchao Li
- Laboratory of Translational Gastroenterology, Qilu Hospital of Shandong University, Jinan, China
- Guangchao Li
- Robot Engineering Laboratory for Precise Diagnosis and Therapy of Gastrointestinal Tumor, Qilu Hospital of Shandong University, Jinan, China
- Zhuang Guo
- Department of Gastroenterology, Shengli Oilfield Central Hospital, Dongying, China
- Limei Wang
- Department of Gastroenterology, Qilu Hospital of Shandong University, Jinan, China
- Limei Wang
- Laboratory of Translational Gastroenterology, Qilu Hospital of Shandong University, Jinan, China
- Limei Wang
- Robot Engineering Laboratory for Precise Diagnosis and Therapy of Gastrointestinal Tumor, Qilu Hospital of Shandong University, Jinan, China
- Qingqing Qi
- Department of Gastroenterology, Qilu Hospital of Shandong University, Jinan, China
- Qingqing Qi
- Laboratory of Translational Gastroenterology, Qilu Hospital of Shandong University, Jinan, China
- Qingqing Qi
- Robot Engineering Laboratory for Precise Diagnosis and Therapy of Gastrointestinal Tumor, Qilu Hospital of Shandong University, Jinan, China
- Xiaoxiao Yang
- Department of Gastroenterology, Qilu Hospital of Shandong University, Jinan, China
- Xiaoxiao Yang
- Laboratory of Translational Gastroenterology, Qilu Hospital of Shandong University, Jinan, China
- Xiaoxiao Yang
- Robot Engineering Laboratory for Precise Diagnosis and Therapy of Gastrointestinal Tumor, Qilu Hospital of Shandong University, Jinan, China
- Junyan Qu
- Department of Gastroenterology, Qilu Hospital of Shandong University, Jinan, China
- Junyan Qu
- Laboratory of Translational Gastroenterology, Qilu Hospital of Shandong University, Jinan, China
- Junyan Qu
- Robot Engineering Laboratory for Precise Diagnosis and Therapy of Gastrointestinal Tumor, Qilu Hospital of Shandong University, Jinan, China
- Xiao Wang
- Department of Pathology, Qilu Hospital, Cheeloo College of Medicine, Shandong University, Jinan, China
- Xiuli Zuo
- Department of Gastroenterology, Qilu Hospital of Shandong University, Jinan, China
- Xiuli Zuo
- Laboratory of Translational Gastroenterology, Qilu Hospital of Shandong University, Jinan, China
- Xiuli Zuo
- Robot Engineering Laboratory for Precise Diagnosis and Therapy of Gastrointestinal Tumor, Qilu Hospital of Shandong University, Jinan, China
- Hongliang Ren
- Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China
- Hongliang Ren
- Department of Biomedical Engineering, National University of Singapore, Singapore, Singapore
- Yanqing Li
- Department of Gastroenterology, Qilu Hospital of Shandong University, Jinan, China
- Yanqing Li
- Laboratory of Translational Gastroenterology, Qilu Hospital of Shandong University, Jinan, China
- Yanqing Li
- Robot Engineering Laboratory for Precise Diagnosis and Therapy of Gastrointestinal Tumor, Qilu Hospital of Shandong University, Jinan, China
- DOI
- https://doi.org/10.3389/fonc.2022.945904
- Journal volume & issue
-
Vol. 12
Abstract
Background and aimMagnifying image-enhanced endoscopy was demonstrated to have higher diagnostic accuracy than white-light endoscopy. However, differentiating early gastric cancers (EGCs) from benign lesions is difficult for beginners. We aimed to determine whether the computer-aided model for the diagnosis of gastric lesions can be applied to videos rather than still images.MethodsA total of 719 magnifying optical enhancement images of EGCs, 1,490 optical enhancement images of the benign gastric lesions, and 1,514 images of background mucosa were retrospectively collected to train and develop a computer-aided diagnostic model. Subsequently, 101 video segments and 671 independent images were used for validation, and error frames were labeled to retrain the model. Finally, a total of 117 unaltered full-length videos were utilized to test the model and compared with those diagnostic results made by independent endoscopists.ResultsExcept for atrophy combined with intestinal metaplasia (IM) and low-grade neoplasia, the diagnostic accuracy was 0.90 (85/94). The sensitivity, specificity, PLR, NLR, and overall accuracy of the model to distinguish EGC from non-cancerous lesions were 0.91 (48/53), 0.78 (50/64), 4.14, 0.12, and 0.84 (98/117), respectively. No significant difference was observed in the overall diagnostic accuracy between the computer-aided model and experts. A good level of kappa values was found between the model and experts, which meant that the kappa value was 0.63.ConclusionsThe performance of the computer-aided model for the diagnosis of EGC is comparable to that of experts. Magnifying the optical enhancement model alone may not be able to deal with all lesions in the stomach, especially when near the focus on severe atrophy with IM. These results warrant further validation in prospective studies with more patients. A ClinicalTrials.gov registration was obtained (identifier number: NCT04563416).Clinical Trial RegistrationClinicalTrials.gov, identifier NCT04563416.
Keywords
- early gastric cancer
- image-enhanced endoscopy
- convolutional neural network
- deep learning
- tumor diagnosis
