An artificial intelligence system for distinguishing between gastrointestinal stromal tumors and leiomyomas using endoscopic ultrasonography

Abstract

Background Gastrointestinal stromal tumors (GISTs) and gastrointestinal leiomyomas (GILs) are the most common subepithelial lesions (SELs). All GISTs have malignant potential; however, GILs are considered benign. Current imaging cannot effectively distinguish GISTs from GILs. We aimed to develop an artificial intelligence (AI) system to differentiate these tumors using endoscopic ultrasonography (EUS).

Methods The AI system was based on EUS images of patients with histologically confirmed GISTs or GILs. Participants from four centers were collected to develop and retrospectively evaluate the AI-based system. The system was used when endosonographers considered SELs to be GISTs or GILs. It was then used in a multicenter prospective diagnostic test to clinically explore whether joint diagnoses by endosonographers and the AI system can distinguish between GISTs and GILs to improve the total diagnostic accuracy for SELs.

Results The AI system was developed using 10 439 EUS images from 752 participants with GISTs or GILs. In the prospective test, 132 participants were histologically diagnosed (36 GISTs, 44 GILs, and 52 other types of SELs) among 508 consecutive subjects. Through joint diagnoses, the total accuracy of endosonographers in diagnosing the 132 histologically confirmed participants increased from 69.7 % (95 % confidence interval [CI] 61.4 %–76.9 %) to 78.8 % (95 %CI 71.0 %–84.9 %; P = 0.01). The accuracy of endosonographers in diagnosing the 80 participants with GISTs or GILs increased from 73.8 % (95 %CI 63.1 %–82.2 %) to 88.8 % (95 %CI 79.8 %–94.2 %; P = 0.01).

Conclusions We developed an AI-based EUS diagnostic system that can effectively distinguish GISTs from GILs and improve the diagnostic accuracy of SELs.

^* Joint first authors

Publication History

Received: 12 October 2020

Accepted: 07 April 2021

Accepted Manuscript online:
07 April 2021

Article published online:
09 June 2021

• References

• 1 Faulx AL, Kothari S. Standards of Practice C. et al. The role of endoscopy in subepithelial lesions of the GI tract. Gastrointest Endosc 2017; 85: 1117-1132
• 2 Miettinen M, Lasota J. Gastrointestinal stromal tumors: Pathology and prognosis at different sites. Semin Diagn Pathol 2006; 23: 70-83
• 3 Chandrasekhara V, Ginsberg GG. Endoscopic management of gastrointestinal stromal tumors. Curr Gastroenterol Rep 2011; 13: 532-539
• 4 Nishida T, Blay JY, Hirota S. et al. The standard diagnosis, treatment, and follow-up of gastrointestinal stromal tumors based on guidelines. Gastric Cancer 2016; 19: 3-14
• 5 Zhou P, Zhong Y, Li Q. Chinese consensus on endoscopic diagnosis and management of gastrointestinal submucosal tumor (version 2018) [In Chinese]. Zhonghua Wei Chang Wai Ke Za Zhi 2018; 21: 841-852
• 6 Nishida T, Kawai N, Yamaguchi S. et al. Submucosal tumors: comprehensive guide for the diagnosis and therapy of gastrointestinal submucosal tumors. Dig Endosc 2013; 25: 479-489
• 7 Landi B, Palazzo L. The role of endosonography in submucosal tumours. Best Pract Res Clin Gastroenterol 2009; 23: 679-701
• 8 Dumonceau JM, Deprez PH, Jenssen C. et al. Indications, results, and clinical impact of endoscopic ultrasound (EUS)-guided sampling in gastroenterology: European Society of Gastrointestinal Endoscopy (ESGE) Clinical Guideline – Updated January 2017. Endoscopy 2017; 49: 695-714
• 9 Luo H, Xu G, Li C. et al. Real-time artificial intelligence for detection of upper gastrointestinal cancer by endoscopy: a multicentre, case-control, diagnostic study. Lancet Oncol 2019; 20: 1645-1654
• 10 Byrne MF, Chapados N, Soudan F. et al. Real-time differentiation of adenomatous and hyperplastic diminutive colorectal polyps during analysis of unaltered videos of standard colonoscopy using a deep learning model. Gut 2019; 68: 94-100
• 11 Kather JN, Pearson AT, Halama N. et al. Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer. Nat Med 2019; 25: 1054-1056
• 12 Bi WL, Hosny A, Schabath MB. et al. Artificial intelligence in cancer imaging: Clinical challenges and applications. CA Cancer J Clin 2019; 69: 127-157
• 13 Song Z, Zou S, Zhou W. et al. Clinically applicable histopathological diagnosis system for gastric cancer detection using deep learning. Nat Commun 2020; 11: 4294
• 14 Ikenoyama Y, Yoshio T, Tokura J. et al. Artificial intelligence diagnostic system predicts multiple Lugol-voiding lesions in the esophagus and patients at high risk for esophageal squamous cell carcinoma. Endoscopy 2021;
• 15 Wu L, He X, Liu M. et al. Evaluating the effects of an artificial intelligence system on endoscopy quality and preliminarily testing its performance on detecting early gastric cancer: a randomized controlled trial. Endoscopy 2021;
• 16 Trister AD, Buist DSM, Lee CI. Will machine learning tip the balance in breast cancer screening?. JAMA Oncol 2017; 3: 1463-1464
• 17 Ding Z, Shi H, Zhang H. et al. Gastroenterologist-level identification of small-bowel diseases and normal variants by capsule endoscopy using a deep-learning model. Gastroenterology 2019; 157: 1044-1054
• 18 Nagtegaal ID, Odze RD, Klimstra D. et al. The 2019 WHO classification of tumours of the digestive system. Histopathology 2020; 76: 182-188
• 19 He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. 2016 IEEE Conference on Computer Vision & Pattern Recognition; 2016: 770-778
• 20 Hajian-Tilaki K. Sample size estimation in diagnostic test studies of biomedical informatics. J Biomed Inform 2014; 48: 193-204
• 21 Leisenring W, Alonzo T, Pepe MS. Comparisons of predictive values of binary medical diagnostic tests for paired designs. Biometrics 2000; 56: 345-351
• 22 Hunt GC, Smith PP, Faigel DO. Yield of tissue sampling for submucosal lesions evaluated by EUS. Gastrointest Endosc 2003; 57: 68-72
• 23 Menon L, Buscaglia JM. Endoscopic approach to subepithelial lesions. Therap Adv Gastroenterol 2014; 7: 123-130
• 24 Antonini F, Delconte G, Fuccio L. et al. EUS-guided tissue sampling with a 20-gauge core biopsy needle for the characterization of gastrointestinal subepithelial lesions: A multicenter study. Endosc Ultrasound 2019; 8: 105-110
• 25 Akahoshi K, Oya M, Koga T. et al. Clinical usefulness of endoscopic ultrasound-guided fine needle aspiration for gastric subepithelial lesions smaller than 2 cm. J Gastrointest Liver Dis 2014; 23: 405-412
• 26 Nagpal K, Foote D, Tan F. et al. Development and validation of a deep learning algorithm for Gleason grading of prostate cancer from biopsy specimens. JAMA Oncol 2020; 6: 1372-1380
• 27 Ling T, Wu L, Fu Y. et al. A deep learning-based system for identifying differentiation status and delineating margins of early gastric cancer in magnifying narrow-band imaging endoscopy. Endoscopy 2020;
• 28 Gong D, Wu L, Zhang J. et al. Detection of colorectal adenomas with a real-time computer-aided system (ENDOANGEL): a randomised controlled study. Lancet Gastroenterol Hepatol 2020; 5: 352-361
• 29 O'Sullivan JW, Banerjee A, Heneghan C. et al. Verification bias. BMJ Evid Based Med 2018; 23: 54-55
• 30 Schmidt RL, Jedrzkiewicz JD, Allred RJ. et al. Verification bias in diagnostic accuracy studies for fine- and core needle biopsy of salivary gland lesions in otolaryngology journals: a systematic review and analysis. Head Neck 2014; 36: 1654-1661