Clinical value of JNET classification for non-real-time diagnosis of colorectal lesions

Abstract

Objective To study the diagnostic value of Japan narrow band imaging expert team (JNET) classification for differentiating pathological type of colorectal lesions. Methods A total of 418 colorectal lesions were retrospectively diagnosed by magnifying endoscopy with narrow band imaging (ME-NBI) using JNET classification by two inexperienced doctors after a short time of training in JNET classification. Then lesions were diagnosed with Sano classification by the two doctors. Diagnostic results were compared with histologic findings as a golden standard. Results The sensitivity, specificity, and accuracy of JNET classification and Sano classification for neoplastic lesion differentiation were 98.2% VS 98.5%, 77.8% VS 66.7%, and 96.9% VS 96.4%, respectively (all P>0.05). These indicators for diagnosing cancerous lesions, including high grade intraepithelial neoplasia, intramucosal carcinoma and submucosal carcinoma, were 66.7% VS 80.2% (P=0.023), 87.6% VS 79.5% (P=0.006), and 82.1% VS 79.7% (P=0.379), respectively, and those for predicting submucosal deep invasive cancers were 34.8% VS 39.1%, 100.0% VS 99.0%, and 96.4% VS 96.3%, respectively (all P>0.05). The diagnostic accuracy of JNET classification for differentiating neoplastic lesions were 95.2% in those with diameter <10 mm, 97.0% in 10~<20 mm, and 97.8% in ≥20 mm (P=0.483), this finding were 95.2%, 85.1% and 72.1% for cancer, respectively (P<0.000 1), and 100%, 96.3%, and 94.4% for submucosal deep invasive cancer, respectively (P=0.026). Shape and location of colorectal lesions showed no significant effect on the diagnostic efficacy of JNET classification. Conclusion JNET classification is valuable for doctors without experience of ME-NBI in diagnosing colorectal lesions and the efficiency is slightly superior to Sano classification. However, the accuracy of diagnosis for cancer with diameter ≥20 mm need to be improved. Key words: Intestinal polyp; Diagnostic techniques, digestive system; Diagnostic imaging; JNET classification