Endoscopic prediction of deeply submucosal invasive carcinoma with use of artificial intelligence

Abstract

Background and study aims We evaluated use of artificial intelligence (AI) assisted image classifier in determining the feasibility of curative endoscopic resection of large colonic lesion based on non-magnified endoscopic images

Methods AI image classifier was trained by 8,000 endoscopic images of large (≥ 2 cm) colonic lesions. The independent validation set consisted of 567 endoscopic images from 76 colonic lesions. Histology of the resected specimens was used as gold standard. Curative endoscopic resection was defined as histology no more advanced than well-differentiated adenocarcinoma, ≤ 1 mm submucosal invasion and without lymphovascular invasion, whereas non-curative resection was defined as any lesion that could not meet the above requirements. Performance of the trained AI image classifier was compared with that of endoscopists.

Results In predicting endoscopic curative resection, AI had an overall accuracy of 85.5 %. Images from narrow band imaging (NBI) had significantly higher accuracy (94.3 % vs 76.0 %; P < 0.00001) and area under the ROC curve (AUROC) (0.934 vs 0.758; P = 0.002) than images from white light imaging (WLI). AI was superior to two junior endoscopists in terms of accuracy (85.5 % vs 61.9 % or 82.0 %, P < 0.05), AUROC (0.837 vs 0.638 or 0.717, P < 0.05) and confidence level (90.1 % vs 83.7 % or 78.3 %, P < 0.05). However, there was no statistical difference in accuracy and AUROC between AI and a senior endoscopist.

Conclusions The trained AI image classifier based on non-magnified images can accurately predict probability of curative resection of large colonic lesions and is better than junior endoscopists. NBI images have better accuracy than WLI for AI prediction.

• References

• 1 Tanaka S, Kashida H, Saito Y. et al. JGES guidelines for colorectal endoscopic submucosal dissection/endoscopic mucosal resection. Digestive Endoscopy 2015; 27: 417-434
• 2 Pedro PN, Dinis-Ribeiro M, Ponchon T. et al. Endoscopic submucosal dissection: European Society of Gastrointestinal Endoscopy (ESGE) Guideline. Endoscopy 2015; 47: 829-854
• 3 Mori Y, Kudo SE, Misawa M. et al. Real-time use of artificial intelligence in identification of diminutive polyps during colonoscopy: a prospective study. Ann Intern Med 2018; DOI: 10.7326/M18-0249.
• 4 Chen PJ, Lin MC, Lai MJ. et al. Accurate classification of diminutive colorectal polyps using computer- aided analysis. Gastroenterology 2018; 154: 568-575
• 5 Matsuda T, Saito Y, Nakajima T. et al. Macroscopic estimation of submucosal invasion in the colon. Tech Gastrointest Endosc 2011; 13: 24-32
• 6 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
• 7 Hayashi N, Tanaka S, Hewett DG. et al. Endoscopic prediction of deep submucosal invasive carcinoma: validation of the narrow-band imaging international colorectal endoscopic (NICE) classification. Gastrointest Endosc 2013; 78: 625-632
• 8 Patrun J, Okreša L, Iveković H. et al. Diagnostic accuracy of NICE classification system for optical recognition of predictive morphology of colorectal polyps. Gastroenterol Res Pract 2018; 14: 7531368
• 9 Oba S, Tanaka S, Oka S. et al. Characterization of colorectal tumors using narrow-band imaging magnification: combined diagnosis with both pit pattern and microvessel features. Scand J Gastroenterol 2010; 45: 1084-1092
• 10 Kanao H, Tanaka S, Oka S. et al. Narrow-band imaging magnification predicts the histology and invasion depth of colorectal tumors. Gastrointest Endosc 2009; 69: 631-636
• 11 Hayashi N, Tanaka S, Kanao H. et al. Relationship between narrow-band imaging magnifying observation and pit pattern diagnosis in colorectal tumors. Digestion 2013; 87: 53-58
• 12 Lee SP, Kim JH, Sung IK. et al. Effect of submucosal fibrosis on endoscopic submucosal dissection of colorectal tumors: pathologic review of 173 cases. J Gastroenterol Hepatol 2015; 30: 872-878
• 13 Lee SP, Kim JH, Sung IK. et al. Effect of submucosal fibrosis on endoscopic submucosal dissection of colorectal tumors: pathologic review of 173 cases. J Gastroenterol Hepatol 2015; 30: 872-878
• 14 Higashi R, Uraoka T, Kato J. et al. Diagnostic accuracy of narrow-band imaging and pit pattern analysis significantly improved for less-experienced endoscopists after an expanded training program. Gastrointest Endosc 2010; 72: 127-35
• 15 Takeda K, Kudo SE, Mori Y. et al. Accuracy of diagnosing invasive colorectal cancer using computer-aided endocytoscopy. Endoscopy 2017; 49: 798-802
• 16 Szegedy CV, Wei L, Yangqing J. et al. IEEE conference on computer vision and pattern recognition. 2016: 2818-2826
• 17 Backes Y, Moss A, Reitsma JB. et al. Narrow band imaging, magnifying chromoendoscopy, and gross morphological features for the optical diagnosis of t1 colorectal cancer and deep submucosal invasion: a systematic review and meta-analysis. Am J Gastroenterol 2017; 112: 54-64
• 18 Zhang OW, Teng LM, Zhang XT. et al. Narrow-band imaging in the diagnosis of deep submucosal colorectal cancers: a systematic review and meta-analysis. Endoscopy 2017; 49: 564-580