Hiromu Fukuda1, Ryu Ishihara1, Yusuke Kato2, Takashi Matsunaga3, Tsutomu Nishida4, Takuya Yamada5, Hideharu Ogiyama6, Mai Horie7, Kazuo Kinoshita8, Tomohiro Tada9. 1. Department of Gastrointestinal Oncology, Osaka International Cancer Institute, Osaka, Japan. 2. AI Medical Service Inc, Tokyo, Japan. 3. Department of Medical Informatics, Osaka International Cancer Institute, Osaka, Japan. 4. Department of Gastroenterology, Toyonaka Municipal Hospital, Osaka, Japan. 5. Department of Gastroenterology, Osaka Rosai Hospital, Osaka, Japan. 6. Department of Gastroenterology, Itami City Hospital, Hyogo, Japan. 7. Department of Gastroenterology, Osaka Police Hospital, Osaka, Japan. 8. Department of Gastroenterology, Otemae Hospital, Osaka, Japan. 9. AI Medical Service Inc, Tokyo, Japan; Tada Tomohiro Institute of Gastroenterology and Proctology, Saitama, Japan; Department of Surgical Oncology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan.
Abstract
BACKGROUND AND AIMS: Narrow-band imaging (NBI) is currently regarded as the standard modality for diagnosing esophageal squamous cell carcinoma (SCC). We developed a computerized image-analysis system for diagnosing esophageal SCC by NBI and estimated its performance with video images. METHODS: Altogether, 23,746 images from 1544 pathologically proven superficial esophageal SCCs and 4587 images from 458 noncancerous and normal tissue were used to construct an artificial intelligence (AI) system. Five- to 9-second video clips from 144 patients captured by NBI or blue-light imaging were used as the validation dataset. These video images were diagnosed by the AI system and 13 board-certified specialists (experts). RESULTS: The diagnostic process was divided into 2 parts: detection (identify suspicious lesions) and characterization (differentiate cancer from noncancer). The sensitivities, specificities, and accuracies for the detection of SCC were, respectively, 91%, 51%, and 63% for the AI system and 79%, 72%, and 75% for the experts. The sensitivity of the AI system was significantly higher than that of the experts, but its specificity was significantly lower. Sensitivities, specificities, and accuracy for the characterization of SCC were, respectively, 86%, 89%, and 88% for the AI system and 74%, 76%, and 75% for the experts. The receiver operating characteristic curve showed that the AI system had significantly better diagnostic performance than the experts. CONCLUSIONS: Our AI system showed significantly higher sensitivity for detecting SCC and higher accuracy for characterizing SCC from noncancerous tissue than endoscopic experts.
BACKGROUND AND AIMS: Narrow-band imaging (NBI) is currently regarded as the standard modality for diagnosing esophageal squamous cell carcinoma (SCC). We developed a computerized image-analysis system for diagnosing esophageal SCC by NBI and estimated its performance with video images. METHODS: Altogether, 23,746 images from 1544 pathologically proven superficial esophageal SCCs and 4587 images from 458 noncancerous and normal tissue were used to construct an artificial intelligence (AI) system. Five- to 9-second video clips from 144 patients captured by NBI or blue-light imaging were used as the validation dataset. These video images were diagnosed by the AI system and 13 board-certified specialists (experts). RESULTS: The diagnostic process was divided into 2 parts: detection (identify suspicious lesions) and characterization (differentiate cancer from noncancer). The sensitivities, specificities, and accuracies for the detection of SCC were, respectively, 91%, 51%, and 63% for the AI system and 79%, 72%, and 75% for the experts. The sensitivity of the AI system was significantly higher than that of the experts, but its specificity was significantly lower. Sensitivities, specificities, and accuracy for the characterization of SCC were, respectively, 86%, 89%, and 88% for the AI system and 74%, 76%, and 75% for the experts. The receiver operating characteristic curve showed that the AI system had significantly better diagnostic performance than the experts. CONCLUSIONS: Our AI system showed significantly higher sensitivity for detecting SCC and higher accuracy for characterizing SCC from noncancerous tissue than endoscopic experts.
Authors: Fei Kuang; Juan Du; Mengjia Zhou; Xiangdong Liu; Xinchen Luo; Yong Tang; Bo Li; Song Su Journal: Front Oncol Date: 2022-06-10 Impact factor: 5.738