Efficacy of endoscopic ultrasound with artificial intelligence for the diagnosis of gastrointestinal stromal tumors
- PDF / 857,769 Bytes
- 8 Pages / 595.276 x 790.866 pts Page_size
- 35 Downloads / 252 Views
ORIGINAL ARTICLE—ALIMENTARY TRACT
Efficacy of endoscopic ultrasound with artificial intelligence for the diagnosis of gastrointestinal stromal tumors Yosuke Minoda1 • Eikichi Ihara1,2 • Keishi Komori1 • Haruei Ogino1 Yoshihiro Otsuka1 • Takatoshi Chinen1 • Yasuo Tsuda3 • Koji Ando3 • Hidetaka Yamamoto4 • Yoshihiro Ogawa1
•
Received: 25 May 2020 / Accepted: 15 August 2020 Ó Japanese Society of Gastroenterology 2020
Abstract Background Although endoscopic ultrasound (EUS) is reported to be suitable for determining the layer from which subepithelial lesions (SELs) originate, it is difficult to distinguish gastrointestinal stromal tumor (GIST) from non-GIST using only EUS images. If artificial intelligence (AI) can be used for the diagnosis of SELs, it should provide several benefits, including objectivity, simplicity, and quickness. In this pilot study, we propose an AI diagnostic system for SELs and evaluate its efficacy. Methods Thirty sets each of EUS images with SELs C 20 mm or \ 20 mm were prepared for diagnosis by an EUS diagnostic system with AI (EUS-AI) and three EUS experts. The EUS-AI and EUS experts diagnosed the SELs using solely the EUS images. The concordance rates of the
Electronic supplementary material The online version of this article (https://doi.org/10.1007/s00535-020-01725-4) contains supplementary material, which is available to authorized users. & Eikichi Ihara [email protected] 1
Department of Medicine and Bioregulatory Science, Graduate School of Medical Sciences, Kyushu University, 31-1 Maidashi, Higashi-ku, Fukuoka 812-8582, Japan
2
Department of Gastroenterology and Metabolism, Graduate School of Medical Sciences, Kyushu University, 3-1-1 Maidashi, Higashi-ku, Fukuoka 812-8582, Japan
3
Department of Surgery and Science, Graduate School of Medical Sciences, Kyushu University, 3-1-1 Maidashi, Higashi-ku, Fukuoka 812-8582, Japan
4
Department of Pathological Sciences, Graduate School of Medical Sciences, Kyushu University, 3-1-1 Maidashi, Higashi-ku, Fukuoka 812-8582, Japan
EUS-AI and EUS experts’ diagnoses were compared with the pathological findings of the SELs. Results The accuracy, sensitivity, and specificity for SELs \ 20 mm were 86.3, 86.3, and 62.5%, respectively for the EUS-AI, and 73.3, 68.2, and 87.5%, respectively, for the EUS experts. In contrast, accuracy, sensitivity, and specificity for SELs C 20 mm were 90.0, 91.7, and 83.3%, respectively, for the EUS-AI, and 53.3, 50.0, and 83.3%, respectively, for the EUS experts. The area under the curve for the diagnostic yield of the EUS-AI for SELs C 20 mm (0.965) was significantly higher than that (0.684) of the EUS experts (P = 0.007). Conclusion EUS-AI had a good diagnostic yield for SELs C 20 mm. EUS-AI has potential as a good option for the diagnosis of SELs. Keywords Artificial intelligence Convolutional neural network Deep learning Endoscopic ultrasound Gastrointestinal tumors Subepithelial lesion
Introduction Gastrointestinal stromal tumor (GIST) is a common type of subepithelial lesion (S
Data Loading...
