Clinical Endoscopy

  • 제55권3호
  • /
  • Pages.390-400
  • /
  • 2022
  • /
  • 2234-2400(pISSN)
  • /
  • 2234-2443(eISSN)
대한소화기내시경학회 (The Korean Society of Gastrointestinal Endoscopy)
권호 표지
DOI QR코드

DOI QR Code

Real-time semantic segmentation of gastric intestinal metaplasia using a deep learning approach

  • Vitchaya Siripoppohn (Department of Computer Engineering, Faculty of Engineering, Chulalongkorn University) ;
  • Rapat Pittayanon (Division of Gastroenterology, Department of Medicine, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital) ;
  • Kasenee Tiankanon (Division of Gastroenterology, Department of Medicine, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital) ;
  • Natee Faknak (Division of Gastroenterology, Department of Medicine, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital) ;
  • Anapat Sanpavat (Department of Pathology, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital) ;
  • Naruemon Klaikaew (Department of Pathology, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital) ;
  • Peerapon Vateekul (Department of Computer Engineering, Faculty of Engineering, Chulalongkorn University) ;
  • Rungsun Rerknimitr (Division of Gastroenterology, Department of Medicine, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital)
  • 투고 : 2021.11.24
  • 심사 : 2022.01.26
  • 발행 : 2022.05.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Background/Aims: Previous artificial intelligence (AI) models attempting to segment gastric intestinal metaplasia (GIM) areas have failed to be deployed in real-time endoscopy due to their slow inference speeds. Here, we propose a new GIM segmentation AI model with inference speeds faster than 25 frames per second that maintains a high level of accuracy. Methods: Investigators from Chulalongkorn University obtained 802 histological-proven GIM images for AI model training. Four strategies were proposed to improve the model accuracy. First, transfer learning was employed to the public colon datasets. Second, an image preprocessing technique contrast-limited adaptive histogram equalization was employed to produce clearer GIM areas. Third, data augmentation was applied for a more robust model. Lastly, the bilateral segmentation network model was applied to segment GIM areas in real time. The results were analyzed using different validity values. Results: From the internal test, our AI model achieved an inference speed of 31.53 frames per second. GIM detection showed sensitivity, specificity, positive predictive, negative predictive, accuracy, and mean intersection over union in GIM segmentation values of 93%, 80%, 82%, 92%, 87%, and 57%, respectively. Conclusions: The bilateral segmentation network combined with transfer learning, contrast-limited adaptive histogram equalization, and data augmentation can provide high sensitivity and good accuracy for GIM detection and segmentation.

키워드

과제정보

This research was funded by the National Research Council of Thailand (NRCT; N42A640330), Chulalongkorn University (CU-GRS-64), and Chulalongkorn University (CU-GRS-62-02-30-01) and supported by the Center of Excellence in Gastrointestinal Oncology, Chulalongkorn University annual grant. It was also funded by the University Technology Center (UTC) at Chulalongkorn University.

참고문헌

  1. Fox JG, Wang TC. Inflammation, atrophy, and gastric cancer. J Clin Invest 2007;117:60-69.  https://doi.org/10.1172/JCI30111
  2. Lim JH, Kim N, Lee HS, et al. Correlation between endoscopic and histological diagnoses of gastric intestinal metaplasia. Gut Liver 2013;7:41-50.  https://doi.org/10.5009/gnl.2013.7.1.41
  3. Panteris V, Nikolopoulou S, Lountou A, et al. Diagnostic capabilities of high-definition white light endoscopy for the diagnosis of gastric intestinal metaplasia and correlation with histologic and clinical data. Eur J Gastroenterol Hepatol 2014;26:594-601.  https://doi.org/10.1097/MEG.0000000000000097
  4. Dixon MF, Genta RM, Yardley JH, et al. Classification and grading of gastritis. The updated Sydney System. International Workshop on the Histopathology of Gastritis, Houston 1994. Am J Surg Pathol 1996;20:1161-1181.  https://doi.org/10.1097/00000478-199610000-00001
  5. Ang TL, Pittayanon R, Lau JY, et al. A multicenter randomized comparison between high-definition white light endoscopy and narrow band imaging for detection of gastric lesions. Eur J Gastroenterol Hepatol 2015;27:1473-1478.  https://doi.org/10.1097/MEG.0000000000000478
  6. Wu C, Namasivayam V, Li JW, et al. A prospective randomized tandem gastroscopy pilot study of linked color imaging versus white light imaging for detection of upper gastrointestinal lesions. J Gastroenterol Hepatol 2021;36:2562-2567.  https://doi.org/10.1111/jgh.15515
  7. Savarino E, Corbo M, Dulbecco P, et al. Narrow-band imaging with magnifying endoscopy is accurate for detecting gastric intestinal metaplasia. World J Gastroenterol 2013;19:2668-2675.  https://doi.org/10.3748/wjg.v19.i17.2668
  8. Pittayanon R, Rerknimitr R, Wisedopas N, et al. The learning curve of gastric intestinal metaplasia interpretation on the images obtained by probe-based confocal laser endomicroscopy. Diagn Ther Endosc 2012;2012:278045. 
  9. Sun M, Zhang G, Dang H, et al. Accurate gastric cancer segmentation in digital pathology images using deformable convolution and multi-scale embedding networks. IEEE Access 2019;7:75530-75541.  https://doi.org/10.1109/ACCESS.2019.2918800
  10. Li Y, Xie X, Liu S, et al. GT-Net: a deep learning network for gastric tumor diagnosis. In: 2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI); 2018 Nov 5-7; Volos, Greece. p. 20-24. 
  11. Chen LC, Zhu Y, Papandreou G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Computer Vision (ECCV 2018); p. 833-851. 
  12. Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention (MICCAI 2015). p. 234-241. 
  13. Read P, Meyer MP. Restoration of motion picture film. Oxford: Butterworth-Heinemann; 2000. 
  14. Rodriguez-Diaz E, Baffy G, Lo WK, et al. Real-time artificial intelligence-based histologic classification of colorectal polyps with augmented visualization. Gastrointest Endosc 2021;93:662-670.  https://doi.org/10.1016/j.gie.2020.09.018
  15. Wang C, Li Y, Yao J, et al. Localizing and identifying intestinal metaplasia based on deep learning in oesophagoscope. In: 2019 8th International Symposium on Next Generation Electronics (ISNE); 2019 Oct 9-10; Zhengzhou, China. p. 1-4. 
  16. Sun X, Zhang P, Wang D, et al. Colorectal polyp segmentation by U-Net with dilation convolution. In: 2019 18th IEEE International Conference on Machine Learning and Applications (ICMLA); 2019 Dec 16-19; Boca Raton, FL. p. 851-858. 
  17. Yosinski J, Clune J, Bengio Y, et al. How transferable are features in deep neural networks? In: NIPS 14: Proceedings of the 27th International Conference on Neural Information Processing Systems; 2014 Dec 8-13; Montreal, Canada. p. 3320-3328. 
  18. Russell BC, Torralba A, Murphy KP, et al. LabelMe: a database and web-based tool for image annotation. Int J Comput Vis 2008;77:157-173.  https://doi.org/10.1007/s11263-007-0090-8
  19. Bernal J, Sanchez FJ, Fernandez-Esparrach G, et al. WM-DOVA maps for accurate polyp highlighting in colonoscopy: validation vs. saliency maps from physicians. Comput Med Imaging Graph 2015;43:99-111.  https://doi.org/10.1016/j.compmedimag.2015.02.007
  20. Jha D, Smedsrud PH, Riegler MA, et al. Kvasir-SEG: a segmented polyp dataset. In: MultiMedia Modeling: 26th International Conference, MMM 2020; 2020 Jan 5-8; Daejeon, Korea. p. 451-462. 
  21. Zuiderveld K. Contrast limited adaptive histogram equalization. In: Heckbert PS, editor. Graphics gems IV. San Diego (CA): Academic Press; 1994. p. 474-485. 
  22. Yu C, Wang J, Peng C, et al. BiSeNet: bilateral segmentation network for real-time semantic segmentation. In: Computer Vision-ECCV 2018; p. 334-349. 
  23. Lecun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition. Proc IEEE 1998;86:2278-2324.  https://doi.org/10.1109/5.726791
  24. Goncalves W, Dos Santos M, Lobato F, et al. Deep learning in gastric tissue diseases: a systematic review. BMJ Open Gastroenterol 2020;7:e000371. 
  25. Mori Y, Neumann H, Misawa M, et al. Artificial intelligence in colonoscopy: now on the market. What's next? J Gastroenterol Hepatol 2021;36:7-11.  https://doi.org/10.1111/jgh.15339
  26. Hirasawa T, Aoyama K, Tanimoto T, et al. Application of artificial intelligence using a convolutional neural network for detecting gastric cancer in endoscopic images. Gastric Cancer 2018;21:653-660.  https://doi.org/10.1007/s10120-018-0793-2
  27. Li L, Chen Y, Shen Z, et al. Convolutional neural network for the diagnosis of early gastric cancer based on magnifying narrow band imaging. Gastric Cancer 2020;23:126-132.  https://doi.org/10.1007/s10120-019-00992-2
  28. Zhang L, Zhang Y, Wang L, et al. Diagnosis of gastric lesions through a deep convolutional neural network. Dig Endosc 2021;33:788-796.  https://doi.org/10.1111/den.13844
  29. Suzuki H, Yoshitaka T, Yoshio T, et al. Artificial intelligence for cancer detection of the upper gastrointestinal tract. Dig Endosc 2021;33:254-262.  https://doi.org/10.1111/den.13897
  30. Xu M, Zhou W, Wu L, et al. Artificial intelligence in the diagnosis of gastric precancerous conditions by image-enhanced endoscopy: a multicenter, diagnostic study (with video). Gastrointest Endosc 2021;94:540-548.  https://doi.org/10.1016/j.gie.2021.03.013
  31. He K, Zhang X, Ren S, et al. Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2016 Jun 27-30; Las Vegas, NV. p. 770-778. 
  32. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. In: 2015 International Conference on Learning Representations (ICLR); 2015 May 7-9; San Diego, CA. 
  33. Huang G, Liu Z, van der Maaten L, et al. Densely connected convolutional networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2017 Jul 21-26; Honolulu, HI. p. 2261-2269. 
  34. Tan M, Le QV. EfficientNet: rethinking model scaling for convolutional neural networks. In: 36th International Conference on Machine Learning (ICML 2019); 2019 Jun 9-15; Long Beach, CA. p. 6105-6114. 
  35. ASGE Technology Committee, Abu Dayyeh BK, Thosani N, et al. ASGE Technology Committee systematic review and meta-analysis assessing the ASGE PIVI thresholds for adopting real-time endoscopic assessment of the histology of diminutive colorectal polyps. Gastrointest Endosc 2015;81:502. e1-502.e16.  https://doi.org/10.1016/j.gie.2014.12.022
  36. Banks M, Graham D, Jansen M, et al. British Society of Gastroenterology guidelines on the diagnosis and management of patients at risk of gastric adenocarcinoma. Gut 2019;68:1545-1575. https://doi.org/10.1136/gutjnl-2018-318126