Endoscopic diagnosis and treatment planning for colorectal polyps using a deep-learning model
Eun Mi Song, Beomhee Park, Chun-Ae Ha, Sung Wook Hwang, Sang Hyoung Park, Dong-Hoon Yang, Byong Duk Ye, Seung-Jae Myung, Suk-Kyun Yang, Namkug Kim, Jeong-Sik Byeon, Eun Mi Song, Beomhee Park, Chun-Ae Ha, Sung Wook Hwang, Sang Hyoung Park, Dong-Hoon Yang, Byong Duk Ye, Seung-Jae Myung, Suk-Kyun Yang, Namkug Kim, Jeong-Sik Byeon
Abstract
We aimed to develop a computer-aided diagnostic system (CAD) for predicting colorectal polyp histology using deep-learning technology and to validate its performance. Near-focus narrow-band imaging (NBI) pictures of colorectal polyps were retrieved from the database of our institution. Of these, 12480 image patches of 624 polyps were used as a training set to develop the CAD. The CAD performance was validated with two test datasets of 545 polyps. Polyps were classified into three histological groups: serrated polyp (SP), benign adenoma (BA)/mucosal or superficial submucosal cancer (MSMC), and deep submucosal cancer (DSMC). The overall kappa value measuring the agreement between the true polyp histology and the expected histology by the CAD was 0.614-0.642, which was higher than that of trainees (n = 6, endoscopists with experience of 100 NBI colonoscopies in <6 months; 0.368-0.401) and almost comparable with that of the experts (n = 3, endoscopists with experience of 2,500 NBI colonoscopies in ≥5 years) (0.649-0.735). The areas under the receiver operating curves for CAD were 0.93-0.95, 0.86-0.89, and 0.89-0.91 for SP, BA/MSMC, and DSMC, respectively. The overall diagnostic accuracy of the CAD was 81.3-82.4%, which was significantly higher than that of the trainees (63.8-71.8%, P < 0.01) and comparable with that of experts (82.4-87.3%). The kappa value and diagnostic accuracies of the trainees improved with CAD assistance: that is, the kappa value increased from 0.368 to 0.655, and the overall diagnostic accuracy increased from 63.8-71.8% to 82.7-84.2%. CAD using a deep-learning model can accurately assess polyp histology and may facilitate the diagnosis of colorectal polyps by endoscopists.
Conflict of interest statement
The authors declare no competing interests.
Figures
References
- Zauber AG, et al. Colonoscopic polypectomy and long-term prevention of colorectal-cancer deaths. N. Engl. J. Med. 2012;366:687–696. doi: 10.1056/NEJMoa1100370.
- Bartel MJ, Brahmbhatt BS, Wallace MB. Management of colorectal T1 carcinoma treated by endoscopic resection from the Western perspective. Dig. Endosc. 2016;28:330–341. doi: 10.1111/den.12598.
- Nakadoi K, et al. Management of T1 colorectal carcinoma with special reference to criteria for curative endoscopic resection. Journal of gastroenterology and hepatology. 2012;27:1057–1062. doi: 10.1111/j.1440-1746.2011.07041.x.
- Watanabe T, et al. Japanese Society for Cancer of the Colon and Rectum (JSCCR) guidelines 2010 for the treatment of colorectal cancer. International journal of clinical oncology. 2012;17:1–29. doi: 10.1007/s10147-011-0315-2.
- Abu Dayyeh BK, 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. Gastrointestinal endoscopy. 2015;81:502.e501–502.e516. doi: 10.1016/j.gie.2014.12.022.
- Hewett DG, et al. Validation of a simple classification system for endoscopic diagnosis of small colorectal polyps using narrow-band imaging. Gastroenterology. 2012;143:599–607.e591. doi: 10.1053/j.gastro.2012.05.006.
- Pohl J, et al. Computed virtual chromoendoscopy for classification of small colorectal lesions: a prospective comparative study. The American journal of gastroenterology. 2008;103:562–569. doi: 10.1111/j.1572-0241.2007.01670.x.
- Guo CG, Ji R, Li YQ. Accuracy of i-Scan for Optical Diagnosis of Colonic Polyps: A Meta-Analysis. PloS one. 2015;10:e0126237. doi: 10.1371/journal.pone.0126237.
- Sano Y, et al. Narrow-band imaging (NBI) magnifying endoscopic classification of colorectal tumors proposed by the Japan NBI Expert Team. Digestive endoscopy: official journal of the Japan Gastroenterological Endoscopy Society. 2016;28:526–533. doi: 10.1111/den.12644.
- Hayashi N, et al. Endoscopic prediction of deep submucosal invasive carcinoma: validation of the narrow-band imaging international colorectal endoscopic (NICE) classification. Gastrointestinal endoscopy. 2013;78:625–632. doi: 10.1016/j.gie.2013.04.185.
- Kuiper Teaco, Marsman Willem A., Jansen Jeroen M., van Soest Ellert J., Haan Yentl C.L., Bakker Guido J., Fockens Paul, Dekker Evelien. Accuracy for Optical Diagnosis of Small Colorectal Polyps in Nonacademic Settings. Clinical Gastroenterology and Hepatology. 2012;10(9):1016–1020. doi: 10.1016/j.cgh.2012.05.004.
- Ignjatovic A, et al. Optical diagnosis of small colorectal polyps at routine colonoscopy (Detect InSpect ChAracterise Resect and Discard; DISCARD trial): a prospective cohort study. The Lancet. Oncology. 2009;10:1171–1178. doi: 10.1016/s1470-2045(09)70329-8.
- Dai J, et al. Evaluation of narrow-band imaging in the diagnosis of colorectal lesions: is a learning curve involved? Digestive endoscopy: official journal of the Japan Gastroenterological Endoscopy Society. 2013;25:180–188. doi: 10.1111/j.1443-1661.2012.01367.x.
- Byrne Michael F, Chapados Nicolas, Soudan Florian, Oertel Clemens, Linares Pérez Milagros, Kelly Raymond, Iqbal Nadeem, Chandelier Florent, Rex Douglas K. Real-time differentiation of adenomatous and hyperplastic diminutive colorectal polyps during analysis of unaltered videos of standard colonoscopy using a deep learning model. Gut. 2017;68(1):94–100. doi: 10.1136/gutjnl-2017-314547.
- Chen PJ, et al. Accurate Classification of Diminutive Colorectal Polyps Using Computer-Aided Analysis. Gastroenterology. 2018;154:568–575. doi: 10.1053/j.gastro.2017.10.010.
- Misawa M, et al. Artificial Intelligence-Assisted Polyp Detection for Colonoscopy: Initial Experience. Gastroenterology. 2018;154:2027–2029.e2023. doi: 10.1053/j.gastro.2018.04.003.
- Zhou, B., Khosla, A., Lapedriza, A., Oliva, A. & Torralba, A. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2921–2929.
- Takemura Y, et al. Computer-aided system for predicting the histology of colorectal tumors by using narrow-band imaging magnifying colonoscopy (with video) Gastrointestinal endoscopy. 2012;75:179–185. doi: 10.1016/j.gie.2011.08.051.
- Gross S, et al. Computer-based classification of small colorectal polyps by using narrow-band imaging with optical magnification. Gastrointestinal endoscopy. 2011;74:1354–1359. doi: 10.1016/j.gie.2011.08.001.
- Mori Y, et al. Impact of an automated system for endocytoscopic diagnosis of small colorectal lesions: an international web-based study. Endoscopy. 2016;48:1110–1118. doi: 10.1055/s-0042-113609.
- Mori Y, et al. Novel computer-aided diagnostic system for colorectal lesions by using endocytoscopy (with videos) Gastrointestinal endoscopy. 2015;81:621–629. doi: 10.1016/j.gie.2014.09.008.
- Kominami Y, et al. Computer-aided diagnosis of colorectal polyp histology by using a real-time image recognition system and narrow-band imaging magnifying colonoscopy. Gastrointestinal endoscopy. 2016;83:643–649. doi: 10.1016/j.gie.2015.08.004.
- Khalid O, et al. Reinterpretation of histology of proximal colon polyps called hyperplastic in 2001. World journal of gastroenterology. 2009;15:3767–3770. doi: 10.3748/wjg.15.3767.
- East JE, Vieth M, Rex DK. Serrated lesions in colorectal cancer screening: detection, resection, pathology and surveillance. Gut. 2015;64:991–1000. doi: 10.1136/gutjnl-2014-309041.
- He, K., Zhang, X., Ren, S. & Sun, J. In Proceedings of the IEEE conference on computer vision and pattern recognition. 770–778.
- Huang, G., Liu, Z., Weinberger, K. Q. & van der Maaten, L. In Proceedings of the IEEE conference on computer vision and pattern recognition. 3.
- Deng, J. et al. In Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on. 248-255 (IEEE).
- Bottou, L. In Proceedings of COMPSTAT'2010 177-186 (Springer, 2010).
Source: PubMed