Dehua Tang1, Lei Wang1, Jingwei Jiang1, Yuting Liu2, Muhan Ni1, Yiwei Fu3, Huimin Guo1, Zhengwen Wang2, Fangmei An4, Kaihua Zhang2, Yanxing Hu5, Qiang Zhan4, Guifang Xu1, Xiaoping Zou1. 1. Department of Gastroenterology, Nanjing University Medical School Affiliated Drum Tower Hospital, Nanjing, Jiangsu, China. 2. Jiangsu Key Laboratory of Big Data Analysis Technology (B-DAT), Nanjing University of Information Science and Technology, Nanjing, China. 3. Department of Gastroenterology, Taizhou People's Hospital, Taizhou, Jiangsu, China. 4. Department of Gastroenterology, Wuxi People's Hospital Affiliated to Nanjing Medical University, Wuxi, Jiangsu, China. 5. Xiamen Innovision, Xiamen Software Park Phase III, Xiamen, Fujian, China.
Abstract
INTRODUCTION: This study aims to construct a real-time deep convolutional neural networks (DCNNs) system to diagnose early esophageal squamous cell carcinoma (ESCC) with white light imaging endoscopy. METHODS: A total of 4,002 images from 1,078 patients were used to train and cross-validate the DCNN model for diagnosing early ESCC. The performance of the model was further tested with independent internal and external validation data sets containing 1,033 images from 243 patients. The performance of the model was then compared with endoscopists. The accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and Cohen kappa coefficient were measured to assess performance. RESULTS: The DCNN model had excellent performance in diagnosing early ESCC with a sensitivity of 0.979, a specificity of 0.886, a positive predictive value of 0.777, a negative predictive value of 0.991, and an area under curve of 0.954 in the internal validation data set. The model also depicted a tremendously generalized performance in 2 external data sets and exhibited superior performance compared with endoscopists. The performance of the endoscopists was markedly elevated after referring to the predictions of the DCNN model. An open-accessed website of the DCNN system was established to facilitate associated research. DISCUSSION: A real-time DCNN system, which was constructed to diagnose early ESCC, showed good performance in validation data sets. However, more prospective validation is needed to understand its true clinical significance in the real world.
INTRODUCTION: This study aims to construct a real-time deep convolutional neural networks (DCNNs) system to diagnose early esophageal squamous cell carcinoma (ESCC) with white light imaging endoscopy. METHODS: A total of 4,002 images from 1,078 patients were used to train and cross-validate the DCNN model for diagnosing early ESCC. The performance of the model was further tested with independent internal and external validation data sets containing 1,033 images from 243 patients. The performance of the model was then compared with endoscopists. The accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and Cohen kappa coefficient were measured to assess performance. RESULTS: The DCNN model had excellent performance in diagnosing early ESCC with a sensitivity of 0.979, a specificity of 0.886, a positive predictive value of 0.777, a negative predictive value of 0.991, and an area under curve of 0.954 in the internal validation data set. The model also depicted a tremendously generalized performance in 2 external data sets and exhibited superior performance compared with endoscopists. The performance of the endoscopists was markedly elevated after referring to the predictions of the DCNN model. An open-accessed website of the DCNN system was established to facilitate associated research. DISCUSSION: A real-time DCNN system, which was constructed to diagnose early ESCC, showed good performance in validation data sets. However, more prospective validation is needed to understand its true clinical significance in the real world.
Authors: Мikhail Davydov; Vera V Delektorskaya; Yuri P Kuvshinov; Mikhail Lisovsky; Sergey S Pirogov; Harushi Udagawa; Masaki Ueno; Guiqi Wang Journal: Ann N Y Acad Sci Date: 2014-09 Impact factor: 5.691
Authors: Eun Jeong Gong; Chang Seok Bang; Kyoungwon Jung; Su Jin Kim; Jong Wook Kim; Seung In Seo; Uhmyung Lee; You Bin Maeng; Ye Ji Lee; Jae Ick Lee; Gwang Ho Baik; Jae Jun Lee Journal: J Pers Med Date: 2022-06-27