Hao Hu1, Lixin Gong2, Di Dong3, Liang Zhu1, Min Wang4, Jie He5, Lei Shu6, Yiling Cai7, Shilun Cai1, Wei Su1, Yunshi Zhong1, Cong Li3, Yongbei Zhu8, Mengjie Fang3, Lianzhen Zhong3, Xin Yang3, Pinghong Zhou1, Jie Tian8. 1. Endoscopy Center and Endoscopy Research Institute, Zhongshan Hospital, Fudan University, Shanghai, China. 2. College of Medicine and Biological Information Engineering School, Northeastern University, Shenyang, China; CAS Key Laboratory of Molecular Imaging, Beijing Key Laboratory of Molecular Imaging, The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China. 3. CAS Key Laboratory of Molecular Imaging, Beijing Key Laboratory of Molecular Imaging, The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China. 4. Department of Gastroenterology, Hepatology and Nutrition, Shanghai Children's Hospital, Shanghai Jiaotong University, Shanghai, China. 5. Endoscopy Center, Zhongshan Hospital (Xiamen Branch), Fudan University, Xiamen, China. 6. Department of Gastroenterology, No. 1 Hospital of Wuhan, Wuhan, China. 7. Department of Gastroenterology, The Affiliated Dongnan Hospital of Xiamen University, Zhangzhou, China. 8. CAS Key Laboratory of Molecular Imaging, Beijing Key Laboratory of Molecular Imaging, The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China; Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, School of Medicine and Engineering, Beihang University, Beijing, China.
Abstract
BACKGROUND AND AIMS: Narrow-band imaging with magnifying endoscopy (ME-NBI) has shown advantages in the diagnosis of early gastric cancer (EGC). However, proficiency in diagnostic algorithms requires substantial expertise and experience. In this study, we aimed to develop a computer-aided diagnostic model for EGM (EGCM) to analyze and assist in the diagnosis of EGC under ME-NBI. METHODS: A total of 1777 ME-NBI images from 295 cases were collected from 3 centers. These cases were randomly divided into a training cohort (n = 170), an internal test cohort (ITC, n = 73), and an external test cohort (ETC, n = 52). EGCM based on VGG-19 architecture (Visual Geometry Group [VGG], Oxford University, Oxford, UK) with a single fully connected 2-classification layer was developed through fine-tuning and validated on all cohorts. Furthermore, we compared the model with 8 endoscopists with varying experience. Primary comparison measures included accuracy, area under the receiver operating characteristic curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). RESULTS: EGCM acquired AUCs of .808 in the ITC and .813 in the ETC. Moreover, EGCM achieved similar predictive performance as the senior endoscopists (accuracy: .770 vs .755, P = .355; sensitivity: .792 vs .767, P = .183; specificity: .745 vs .742, P = .931) but better than the junior endoscopists (accuracy: .770 vs .728, P < .05). After referring to the results of EGCM, the average diagnostic ability of the endoscopists was significantly improved in terms of accuracy, sensitivity, PPV, and NPV (P < .05). CONCLUSIONS: EGCM exhibited comparable performance with senior endoscopists in the diagnosis of EGC and showed the potential value in aiding and improving the diagnosis of EGC by endoscopists.
BACKGROUND AND AIMS: Narrow-band imaging with magnifying endoscopy (ME-NBI) has shown advantages in the diagnosis of early gastric cancer (EGC). However, proficiency in diagnostic algorithms requires substantial expertise and experience. In this study, we aimed to develop a computer-aided diagnostic model for EGM (EGCM) to analyze and assist in the diagnosis of EGC under ME-NBI. METHODS: A total of 1777 ME-NBI images from 295 cases were collected from 3 centers. These cases were randomly divided into a training cohort (n = 170), an internal test cohort (ITC, n = 73), and an external test cohort (ETC, n = 52). EGCM based on VGG-19 architecture (Visual Geometry Group [VGG], Oxford University, Oxford, UK) with a single fully connected 2-classification layer was developed through fine-tuning and validated on all cohorts. Furthermore, we compared the model with 8 endoscopists with varying experience. Primary comparison measures included accuracy, area under the receiver operating characteristic curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). RESULTS:EGCM acquired AUCs of .808 in the ITC and .813 in the ETC. Moreover, EGCM achieved similar predictive performance as the senior endoscopists (accuracy: .770 vs .755, P = .355; sensitivity: .792 vs .767, P = .183; specificity: .745 vs .742, P = .931) but better than the junior endoscopists (accuracy: .770 vs .728, P < .05). After referring to the results of EGCM, the average diagnostic ability of the endoscopists was significantly improved in terms of accuracy, sensitivity, PPV, and NPV (P < .05). CONCLUSIONS:EGCM exhibited comparable performance with senior endoscopists in the diagnosis of EGC and showed the potential value in aiding and improving the diagnosis of EGC by endoscopists.