Journal of Gastric Cancer

  • 제24권3호
  • /
  • Pages.327-340
  • /
  • 2024
  • /
  • 2093-582X(pISSN)
  • /
  • 2093-5641(eISSN)
대한위암학회 (The Korean Gastric Cancer Association)
권호 표지
DOI QR코드

DOI QR Code

Real-World Application of Artificial Intelligence for Detecting Pathologic Gastric Atypia and Neoplastic Lesions

  • Young Hoon Chang (Department of Internal Medicine, Seoul National University Bundang Hospital) ;
  • Cheol Min Shin (Department of Internal Medicine, Seoul National University Bundang Hospital) ;
  • Hae Dong Lee (Department of Internal Medicine, Seoul National University Bundang Hospital) ;
  • Jinbae Park (Ainex Co., LTD.) ;
  • Jiwoon Jeon (Ainex Co., LTD.) ;
  • Soo-Jeong Cho (Department of Internal Medicine and Liver Research Institute, Seoul National University College of Medicine) ;
  • Seung Joo Kang (Department of Internal Medicine and Healthcare Research Institute, Healthcare System Gangnam Center, Seoul National University Hospital) ;
  • Jae-Yong Chung (Department of Clinical Pharmacology and Therapeutics, Seoul National University Bundang Hospital) ;
  • Yu Kyung Jun (Department of Internal Medicine, Seoul National University Bundang Hospital) ;
  • Yonghoon Choi (Department of Internal Medicine, Seoul National University Bundang Hospital) ;
  • Hyuk Yoon (Department of Internal Medicine, Seoul National University Bundang Hospital) ;
  • Young Soo Park (Department of Internal Medicine, Seoul National University Bundang Hospital) ;
  • Nayoung Kim (Department of Internal Medicine, Seoul National University Bundang Hospital) ;
  • Dong Ho Lee (Department of Internal Medicine, Seoul National University Bundang Hospital)
  • 투고 : 2024.04.23
  • 심사 : 2024.06.17
  • 발행 : 2024.07.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Purpose: Results of initial endoscopic biopsy of gastric lesions often differ from those of the final pathological diagnosis. We evaluated whether an artificial intelligence-based gastric lesion detection and diagnostic system, ENdoscopy as AI-powered Device Computer Aided Diagnosis for Gastroscopy (ENAD CAD-G), could reduce this discrepancy. Materials and Methods: We retrospectively collected 24,948 endoscopic images of early gastric cancers (EGCs), dysplasia, and benign lesions from 9,892 patients who underwent esophagogastroduodenoscopy between 2011 and 2021. The diagnostic performance of ENAD CAD-G was evaluated using the following real-world datasets: patients referred from community clinics with initial biopsy results of atypia (n=154), participants who underwent endoscopic resection for neoplasms (Internal video set, n=140), and participants who underwent endoscopy for screening or suspicion of gastric neoplasm referred from community clinics (External video set, n=296). Results: ENAD CAD-G classified the referred gastric lesions of atypia into EGC (accuracy, 82.47%; 95% confidence interval [CI], 76.46%-88.47%), dysplasia (88.31%; 83.24%-93.39%), and benign lesions (83.12%; 77.20%-89.03%). In the Internal video set, ENAD CAD-G identified dysplasia and EGC with diagnostic accuracies of 88.57% (95% CI, 83.30%-93.84%) and 91.43% (86.79%-96.07%), respectively, compared with an accuracy of 60.71% (52.62%-68.80%) for the initial biopsy results (P<0.001). In the External video set, ENAD CAD-G classified EGC, dysplasia, and benign lesions with diagnostic accuracies of 87.50% (83.73%-91.27%), 90.54% (87.21%-93.87%), and 88.85% (85.27%-92.44%), respectively. Conclusions: ENAD CAD-G is superior to initial biopsy for the detection and diagnosis of gastric lesions that require endoscopic resection. ENAD CAD-G can assist community endoscopists in identifying gastric lesions that require endoscopic resection.

키워드

과제정보

This research was supported by Ainex Co. Ltd.

참고문헌

  1. Siegel RL, Miller KD, Jemal A. Cancer statistics, 2018. CA Cancer J Clin 2018;68:7-30.
  2. Bray F, Ferlay J, Soerjomataram I, Siegel RL, Torre LA, Jemal A. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin 2018;68:394-424.
  3. Imagawa A, Okada H, Kawahara Y, Takenaka R, Kato J, Kawamoto H, et al. Endoscopic submucosal dissection for early gastric cancer: results and degrees of technical difficulty as well as success. Endoscopy 2006;38:987-990.
  4. Amin MB, Greene FL, Edge SB, Compton CC, Gershenwald JE, Brookland RK, et al. The Eighth Edition AJCC Cancer Staging Manual: Continuing to build a bridge from a population-based to a more "personalized" approach to cancer staging. CA Cancer J Clin 2017;67:93-99.
  5. Sano T, Coit DG, Kim HH, Roviello F, Kassab P, Wittekind C, et al. Proposal of a new stage grouping of gastric cancer for TNM classification: International Gastric Cancer Association staging project. Gastric Cancer 2017;20:217-225.
  6. Pimenta-Melo AR, Monteiro-Soares M, Libanio D, Dinis-Ribeiro M. Missing rate for gastric cancer during upper gastrointestinal endoscopy: a systematic review and meta-analysis. Eur J Gastroenterol Hepatol 2016;28:1041-1049.
  7. Veitch AM, Uedo N, Yao K, East JE. Optimizing early upper gastrointestinal cancer detection at endoscopy. Nat Rev Gastroenterol Hepatol 2015;12:660-667.
  8. Chiu PW, Uedo N, Singh R, Gotoda T, Ng EK, Yao K, et al. An Asian consensus on standards of diagnostic upper endoscopy for neoplasia. Gut 2019;68:186-197.
  9. Hamashima C; Systematic Review Group and Guideline Development Group for Gastric Cancer Screening Guidelines. Update version of the Japanese Guidelines for Gastric Cancer Screening. Jpn J Clin Oncol 2018;48:673-683.
  10. Nakanishi H, Doyama H, Ishikawa H, Uedo N, Gotoda T, Kato M, et al. Evaluation of an e-learning system for diagnosis of gastric lesions using magnifying narrow-band imaging: a multicenter randomized controlled study. Endoscopy 2017;49:957-967.
  11. Luo Q, Yang H, Hu B. Application of artificial intelligence in the endoscopic diagnosis of early gastric cancer, atrophic gastritis, and Helicobacter pylori infection. J Dig Dis 2022;23:666-674.
  12. Renna F, Martins M, Neto A, Cunha A, Libanio D, Dinis-Ribeiro M, et al. Artificial intelligence for upper gastrointestinal endoscopy: a roadmap from technology development to clinical practice. Diagnostics (Basel) 2022;12:1278.
  13. Sharma P, Hassan C. Artificial intelligence and deep learning for upper gastrointestinal neoplasia. Gastroenterology 2022;162:1056-1066.
  14. Wu L, He X, Liu M, Xie H, An P, Zhang J, et al. Evaluation of the effects of an artificial intelligence system on endoscopy quality and preliminary testing of its performance in detecting early gastric cancer: a randomized controlled trial. Endoscopy 2021;53:1199-1207.
  15. Nam JY, Chung HJ, Choi KS, Lee H, Kim TJ, Soh H, et al. Deep learning model for diagnosing gastric mucosal lesions using endoscopic images: development, validation, and method comparison. Gastrointest Endosc 2022;95:258-268.e10.
  16. Gong EJ, Bang CS, Lee JJ, Baik GH, Lim H, Jeong JH, et al. Deep learning-based clinical decision support system for gastric neoplasms in real-time endoscopy: development and validation study. Endoscopy 2023;55:701-708.
  17. Wu L, Wang J, He X, Zhu Y, Jiang X, Chen Y, et al. Deep learning system compared with expert endoscopists in predicting early gastric cancer and its invasion depth and differentiation status (with videos). Gastrointest Endosc 2022;95:92-104.e3.
  18. Tan M, Le Q. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. In: Kamalika C, Ruslan S, eds. Proceedings of the 36th International Conference on Machine Learning, PMLR, Volume 97; 2019 June 9-15; Long Beach, CA, USA. MLResearchPress, 2019:6105-6114.
  19. Karras T, Laine S, Aittala M, Hellsten J, Lehtinen J, Aila T. Analyzing and improving the image quality of StyleGAN. arXiv. Forthcoming 2020.
  20. Cao J, Pang J, Weng X, Khirodkar R, Kitani K. Observation-centric SORT: rethinking SORT for robust multi-object tracking. arXiv. Forthcoming 2022.
  21. Wu L, Xu M, Jiang X, He X, Zhang H, Ai Y, et al. Real-time artificial intelligence for detecting focal lesions and diagnosing neoplasms of the stomach by white-light endoscopy (with videos). Gastrointest Endosc 2022;95:269-280.e6.
  22. Wei MT, Shankar U, Parvin R, Abbas SH, Chaudhary S, Friedlander Y, et al. Evaluation of computer-aided detection during colonoscopy in the community (AI-SEE): a multicenter randomized clinical trial. Am J Gastroenterol 2023;118:1841-1847.
  23. Won CS, Cho MY, Kim HS, Kim HJ, Suk KT, Kim MY, et al. Upgrade of lesions initially diagnosed as low-grade gastric dysplasia upon forceps biopsy following endoscopic resection. Gut Liver 2011;5:187-193. 
  24. You A, Kim JK, Ryu IH, Yoo TK. Application of generative adversarial networks (GAN) for ophthalmology image domains: a survey. Eye Vis (Lond) 2022;9:6.
  25. Kanayama T, Kurose Y, Tanaka K, Aida K, Satoh S, Kitsuregawa M, et al. Gastric cancer detection from endoscopic images using synthesis by GAN. In: Medical Image Computing and Computer Assisted Intervention - MICCAI 2019: 22nd International Conference; 2019 October 13-17; Shenzhen, China. Shenzhen: Springer-Verlag, 2019:530-538.
  26. Shumailov I, Shumaylov Z, Zhao Y, Gal Y, Papernot N, Anderson R. The curse of recursion: training on generated data makes models forget. arXiv. Forthcoming 2023.
  27. Horiuchi Y, Hirasawa T, Ishizuka N, Tokai Y, Namikawa K, Yoshimizu S, et al. Performance of a computeraided diagnosis system in diagnosing early gastric cancer using magnifying endoscopy videos with narrow-band imaging (with videos). Gastrointest Endosc 2020;92:856-865.e1.
  28. Wu L, Shang R, Sharma P, Zhou W, Liu J, Yao L, et al. Effect of a deep learning-based system on the miss rate of gastric neoplasms during upper gastrointestinal endoscopy: a single-centre, tandem, randomised controlled trial. Lancet Gastroenterol Hepatol 2021;6:700-708.
  29. Kim JH, Nam SJ, Park SC. Usefulness of artificial intelligence in gastric neoplasms. World J Gastroenterol 2021;27:3543-3555.