Keiko Hirai1, Takamichi Kuwahara2,3, Kazuhiro Furukawa1, Naomi Kakushima1, Satoshi Furune1, Hideko Yamamoto4, Takahiro Marukawa5, Hiromitsu Asai6, Kenichi Matsui7, Yoji Sasaki8, Daisuke Sakai9, Koji Yamada10, Takahiro Nishikawa11, Daijuro Hayashi12, Tomohiko Obayashi13, Takuma Komiyama14, Eri Ishikawa1, Tsunaki Sawada15, Keiko Maeda15, Takeshi Yamamura1, Takuya Ishikawa1, Eizaburo Ohno1, Masanao Nakamura1, Hiroki Kawashima15, Masatoshi Ishigami1, Mitsuhiro Fujishiro1. 1. Department of Gastroenterology and Hepatology, Nagoya University Graduate School of Medicine, 65 Tsurumai-cho, Showa-ku, Nagoya, 466-8550, Japan. 2. Department of Gastroenterology and Hepatology, Nagoya University Graduate School of Medicine, 65 Tsurumai-cho, Showa-ku, Nagoya, 466-8550, Japan. kuwa_tak@aichi-cc.jp. 3. Department of Gastroenterology, Aichi Cancer Center Hospital, Nagoya, Japan. kuwa_tak@aichi-cc.jp. 4. Department of Gastroenterology, Toyohashi Municipal Hospital, Toyohashi, Japan. 5. Department of Gastroenterology and Hepatology, Japanese Red Cross Aichi Medical Center Nagoya Daiichi Hospital, Nagoya, Japan. 6. Department of Gastroenterology, Handa City Hospital, Handa, Japan. 7. Department of Gastroenterology, Toyota Kosei Hospital, Toyota, Japan. 8. Department of Gastroenterology, Konan Kosei Hospital, Konan, Japan. 9. Department of Gastroenterology, Ichinomiya Municipal Hospital, Ichinomiya, Japan. 10. Department of Gastroenterology, Okazaki City Hospital, Okazaki, Japan. 11. Department of Gastroenterology, Daido Hospital, Nagoya, Japan. 12. Department of Gastroenterology, Anjo Kosei Hospital, Anjo, Japan. 13. Department of Gastroenterology, Meitetsu Hospital, Nagoya, Japan. 14. Department of Gastroenterology, Komaki City Hospital, Komaki, Japan. 15. Department of Endoscopy, Nagoya University Hospital, Nagoya, Japan.
Abstract
BACKGROUND: Endoscopic ultrasonography (EUS) is useful for the differential diagnosis of subepithelial lesions (SELs); however, not all of them are easy to distinguish. Gastrointestinal stromal tumors (GISTs) are the commonest SELs, are considered potentially malignant, and differentiating them from benign SELs is important. Artificial intelligence (AI) using deep learning has developed remarkably in the medical field. This study aimed to investigate the efficacy of an AI system for classifying SELs on EUS images. METHODS: EUS images of pathologically confirmed upper gastrointestinal SELs (GIST, leiomyoma, schwannoma, neuroendocrine tumor [NET], and ectopic pancreas) were collected from 12 hospitals. These images were divided into development and test datasets in the ratio of 4:1 using random sampling; the development dataset was divided into training and validation datasets. The same test dataset was diagnosed by two experts and two non-experts. RESULTS: A total of 16,110 images were collected from 631 cases for the development and test datasets. The accuracy of the AI system for the five-category classification (GIST, leiomyoma, schwannoma, NET, and ectopic pancreas) was 86.1%, which was significantly higher than that of all endoscopists. The sensitivity, specificity, and accuracy of the AI system for differentiating GISTs from non-GISTs were 98.8%, 67.6%, and 89.3%, respectively. Its sensitivity and accuracy were significantly higher than those of all the endoscopists. CONCLUSION: The AI system, classifying SELs, showed higher diagnostic performance than that of the experts and may assist in improving the diagnosis of SELs in clinical practice.
BACKGROUND: Endoscopic ultrasonography (EUS) is useful for the differential diagnosis of subepithelial lesions (SELs); however, not all of them are easy to distinguish. Gastrointestinal stromal tumors (GISTs) are the commonest SELs, are considered potentially malignant, and differentiating them from benign SELs is important. Artificial intelligence (AI) using deep learning has developed remarkably in the medical field. This study aimed to investigate the efficacy of an AI system for classifying SELs on EUS images. METHODS: EUS images of pathologically confirmed upper gastrointestinal SELs (GIST, leiomyoma, schwannoma, neuroendocrine tumor [NET], and ectopic pancreas) were collected from 12 hospitals. These images were divided into development and test datasets in the ratio of 4:1 using random sampling; the development dataset was divided into training and validation datasets. The same test dataset was diagnosed by two experts and two non-experts. RESULTS: A total of 16,110 images were collected from 631 cases for the development and test datasets. The accuracy of the AI system for the five-category classification (GIST, leiomyoma, schwannoma, NET, and ectopic pancreas) was 86.1%, which was significantly higher than that of all endoscopists. The sensitivity, specificity, and accuracy of the AI system for differentiating GISTs from non-GISTs were 98.8%, 67.6%, and 89.3%, respectively. Its sensitivity and accuracy were significantly higher than those of all the endoscopists. CONCLUSION: The AI system, classifying SELs, showed higher diagnostic performance than that of the experts and may assist in improving the diagnosis of SELs in clinical practice.