Value of artificial intelligence with novel tumor tracking technology in the diagnosis of gastric submucosal tumors by contrast‐enhanced harmonic endoscopic ultrasonography
-
- Hidekazu Tanaka
- Department of Gastroenterology and Hepatology Kindai University Hospital Osaka Japan
-
- Ken Kamata
- Department of Gastroenterology and Hepatology Kindai University Hospital Osaka Japan
-
- Rika Ishihara
- Department of Informatics Kindai University Osaka Japan
-
- Hisashi Handa
- Department of Informatics Kindai University Osaka Japan
-
- Yasuo Otsuka
- Department of Gastroenterology and Hepatology Kindai University Hospital Osaka Japan
-
- Akihiro Yoshida
- Department of Gastroenterology and Hepatology Kindai University Hospital Osaka Japan
-
- Tomoe Yoshikawa
- Department of Gastroenterology and Hepatology Kindai University Hospital Osaka Japan
-
- Rei Ishikawa
- Department of Gastroenterology and Hepatology Kindai University Hospital Osaka Japan
-
- Ayana Okamoto
- Department of Gastroenterology and Hepatology Kindai University Hospital Osaka Japan
-
- Tomohiro Yamazaki
- Department of Gastroenterology and Hepatology Kindai University Hospital Osaka Japan
-
- Atsushi Nakai
- Department of Gastroenterology and Hepatology Kindai University Hospital Osaka Japan
-
- Shunsuke Omoto
- Department of Gastroenterology and Hepatology Kindai University Hospital Osaka Japan
-
- Kosuke Minaga
- Department of Gastroenterology and Hepatology Kindai University Hospital Osaka Japan
-
- Kentaro Yamao
- Department of Gastroenterology and Hepatology Kindai University Hospital Osaka Japan
-
- Mamoru Takenaka
- Department of Gastroenterology and Hepatology Kindai University Hospital Osaka Japan
-
- Tomohiro Watanabe
- Department of Gastroenterology and Hepatology Kindai University Hospital Osaka Japan
-
- Naoshi Nishida
- Department of Gastroenterology and Hepatology Kindai University Hospital Osaka Japan
-
- Masatoshi Kudo
- Department of Gastroenterology and Hepatology Kindai University Hospital Osaka Japan
説明
<jats:title>Abstract</jats:title><jats:sec><jats:title>Background and Aim</jats:title><jats:p>Contrast‐enhanced harmonic endoscopic ultrasonography (CH‐EUS) is useful for the diagnosis of lesions inside and outside the digestive tract. This study evaluated the value of artificial intelligence (AI) in the diagnosis of gastric submucosal tumors by CH‐EUS.</jats:p></jats:sec><jats:sec><jats:title>Methods</jats:title><jats:p>This retrospective study included 53 patients with gastrointestinal stromal tumors (GISTs) and leiomyomas, all of whom underwent CH‐EUS between June 2015 and February 2020. A novel technology, SiamMask, was used to track and trim the lesions in CH‐EUS videos. CH‐EUS was evaluated by AI using deep learning involving a residual neural network and leave‐one‐out cross‐validation. The diagnostic accuracy of AI in discriminating between GISTs and leiomyomas was assessed and compared with that of blind reading by two expert endosonographers.</jats:p></jats:sec><jats:sec><jats:title>Results</jats:title><jats:p>Of the 53 patients, 42 had GISTs and 11 had leiomyomas. Mean tumor size was 26.4 mm. The consistency rate of the segment range of the tumor image extracted by SiamMask and marked by the endosonographer was 96% with a Dice coefficient. The sensitivity, specificity, and accuracy of AI in diagnosing GIST were 90.5%, 90.9%, and 90.6%, respectively, whereas those of blind reading were 90.5%, 81.8%, and 88.7%, respectively (<jats:italic>P</jats:italic> = 0.683). The <jats:ext-link xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="http://www.med.osaka-u.ac.jp/pub/kid/clinicaljournalclub12.html">κ</jats:ext-link> coefficient between the two reviewers was 0.713.</jats:p></jats:sec><jats:sec><jats:title>Conclusions</jats:title><jats:p>The diagnostic ability of CH‐EUS results evaluated by AI to distinguish between GISTs and leiomyomas was comparable with that of blind reading by expert endosonographers.</jats:p></jats:sec>
収録刊行物
-
- Journal of Gastroenterology and Hepatology
-
Journal of Gastroenterology and Hepatology 37 (5), 841-846, 2022-01-31
Wiley
- Tweet
詳細情報 詳細情報について
-
- CRID
- 1360017282226747008
-
- ISSN
- 14401746
- 08159319
-
- データソース種別
-
- Crossref
- KAKEN