Computer-aided diagnosis for optical diagnosis of diminutive colorectal polyps including sessile serrated lesions: a real-time comparison with screening endoscopists.

BACKGROUND : We aimed to compare the accuracy of the optical diagnosis of diminutive colorectal polyps, including sessile serrated lesions (SSLs), between a computer-aided diagnosis (CADx) system and endoscopists during real-time colonoscopy. METHODS : We developed the POLyp Artificial Recognition (POLAR) system, which was capable of performing real-time characterization of diminutive colorectal polyps. For pretraining, the Microsoft-COCO dataset with over 300 000 nonpolyp object images was used. For training, eight hospitals prospectively collected 2637 annotated images from 1339 polyps (i. e. publicly available online POLAR database). For clinical validation, POLAR was tested during colonoscopy in patients with a positive fecal immunochemical test (FIT), and compared with the performance of 20 endoscopists from eight hospitals. Endoscopists were blinded to the POLAR output. Primary outcome was the comparison of accuracy of the optical diagnosis of diminutive colorectal polyps between POLAR and endoscopists (neoplastic [adenomas and SSLs] versus non-neoplastic [hyperplastic polyps]). Histopathology served as the reference standard. RESULTS : During clinical validation, 423 diminutive polyps detected in 194 FIT-positive individuals were included for analysis (300 adenomas, 41 SSLs, 82 hyperplastic polyps). POLAR distinguished neoplastic from non-neoplastic lesions with 79 % accuracy, 89 % sensitivity, and 38 % specificity. The endoscopists achieved 83 % accuracy, 92 % sensitivity, and 44 % specificity. The optical diagnosis accuracy between POLAR and endoscopists was not significantly different (P = 0.10). The proportion of polyps in which POLAR was able to provide an optical diagnosis was 98 % (i. e. success rate). CONCLUSIONS : We developed a CADx system that differentiated neoplastic from non-neoplastic diminutive polyps during endoscopy, with an accuracy comparable to that of screening endoscopists and near-perfect success rate.

Smokeless Tobacco and Cigar and/or Pipe Are Risk Factors for Barrett Esophagus in Male Patients With Gastroesophageal Reflux Disease.

OBJECTIVE: To investigate the effect of smokeless tobacco (ST), cigar and/or pipe smoking (CP) on the development of Barrett esophagus (BE) in white male patients with gastroesophageal reflux disease (GERD). PATIENTS AND METHODS: A total of 1015 records of white male adults with BE (cases; n=508) or GERD (controls, n=507) were reviewed for lifestyle factors. Logistic regression analyses were performed after adjusting for lifestyle factors to assess the effects of ST and CP on the risk of developing BE. Differences between patients with BE and those with GERD were compared using chi-square and t tests. RESULTS: Patients with BE were significantly older than patients with GERD (mean age, 66±12 years for patients with BE and 55±15 years for patients with GERD; P<.001). The odds of developing BE in patients who used CS were 1.7 times higher than that in patients who never smoked cigarettes (odds ratio [OR], 1.7; 95% CI, 1.3-2.2). It was observed that when CS use was combined with either ST or CP use, the odds of having BE significantly increased (OR, 2.5; 95% CI, 1.2-5.2; P=.01 and OR, 1.9; 95% CI, 1.03-3.58; P=.04) in comparison to CS alone. There were no significant differences in body mass index and alcohol consumption between BE and GERD groups. CONCLUSION: This study suggests that there is indeed an association between CS and BE. We believe that this is the first time that ST and CP were associated with an even higher odds of developing BE. Further studies are needed to investigate whether the use of ST and CP is also associated with an increased risk of developing BE-associated adenocarcinoma.