Accuracy of computer-aided diagnosis based on narrow-band imaging endocytoscopy for diagnosing colorectal lesions: comparison with experts

• Published in: International journal for computer assisted radiology and surgery Vol. 12; no. 5; pp. 757 - 766
• Main Authors: Misawa, Masashi, Kudo, Shin-ei, Mori, Yuichi, Takeda, Kenichi, Maeda, Yasuharu, Kataoka, Shinichi, Nakamura, Hiroki, Kudo, Toyoki, Wakamura, Kunihiko, Hayashi, Takemasa, Katagiri, Atsushi, Baba, Toshiyuki, Ishida, Fumio, Inoue, Haruhiro, Nimura, Yukitaka, Oda, Msahiro, Mori, Kensaku
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01.05.2017; Springer Nature B.V
• Subjects: Accuracy; Aged; Algorithms; Cellular structure; Colonic Polyps - diagnostic imaging; Colonoscopy - methods; Colorectal Neoplasms - diagnostic imaging; Computer aided testing; Computer Imaging; Computer Science; Decision making; Diagnosis; Diagnosis, Computer-Assisted - methods; Diagnostic systems; Endoscopy - methods; Experts; Female; Health Informatics; Human performance; Humans; Image Processing, Computer-Assisted; Imaging; In vivo methods and tests; Lesions; Male; Medicine; Medicine & Public Health; Middle Aged; Narrow Band Imaging; Neoplasms; Original Article; Pattern Recognition and Graphics; Pattern Recognition, Automated; Probability; Radiology; Reproducibility of Results; Retrospective Studies; Software; Surgery; Treatment Outcome; Tumors; Vision; Colon polyp; Narrow-band imaging; Endocytoscopy; Colonoscopy; Computer-aided diagnosis; Magnifying endoscopy
• ISSN: 1861-6410; 1861-6429
• DOI: 10.1007/s11548-017-1542-4

Purpose Real-time characterization of colorectal lesions during colonoscopy is important for reducing medical costs, given that the need for a pathological diagnosis can be omitted if the accuracy of the diagnostic modality is sufficiently high. However, it is sometimes difficult for community-based gastroenterologists to achieve the required level of diagnostic accuracy. In this regard, we developed a computer-aided diagnosis (CAD) system based on endocytoscopy (EC) to evaluate cellular, glandular, and vessel structure atypia in vivo. The purpose of this study was to compare the diagnostic ability and efficacy of this CAD system with the performances of human expert and trainee endoscopists. Methods We developed a CAD system based on EC with narrow-band imaging that allowed microvascular evaluation without dye (ECV-CAD). The CAD algorithm was programmed based on texture analysis and provided a two-class diagnosis of neoplastic or non-neoplastic, with probabilities. We validated the diagnostic ability of the ECV-CAD system using 173 randomly selected EC images (49 non-neoplasms, 124 neoplasms). The images were evaluated by the CAD and by four expert endoscopists and three trainees. The diagnostic accuracies for distinguishing between neoplasms and non-neoplasms were calculated. Results ECV-CAD had higher overall diagnostic accuracy than trainees (87.8 vs 63.4%; P = 0.01 ), but similar to experts (87.8 vs 84.2%; P = 0.76 ). With regard to high-confidence cases, the overall accuracy of ECV-CAD was also higher than trainees (93.5 vs 71.7%; P < 0.001 ) and comparable to experts (93.5 vs 90.8%; P = 0.38 ). Conclusions ECV-CAD showed better diagnostic accuracy than trainee endoscopists and was comparable to that of experts. ECV-CAD could thus be a powerful decision-making tool for less-experienced endoscopists.