To investigate the diagnostic performance of blue laser imaging (BLI) combined with JNET classification for analyzing invasive depth of colorectal lesions.

A collection of 694 cases of colorectal lesions under BLI in our hospital from August 2016 to July 2018 was performed. The imagings of lesions were analyzed to assess their pathological properties and invasive depth according to JNET classification. The pathological diagnosis of biopsy tissue was the gold standard. The sensitivity, specificity, positive predictive value, negative predictive value, and diagnostic accuracy were observed.

In all lesions, there were 500 polypoid lesions and 194 superficial lesions. In all lesions, polypoid lesions and superficial lesions, the diagnostic accuracy of Type 1 was 99.1%, 99.2% and 99.0% respectively; the diagnostic accuracy of Type 2A was 80.7%, 81.4% and 78.9% respectively; the diagnostic accuracy of Type 2B was 78.0%, 78.8%, and 75.8% respectively. The diagnostic accuracy of Type 3 was 96.4%, 96.6%, and 95.9% respectively, which was similar to the diagnosis accuracy of NBI. There was no significant difference in the diagnostic accuracy between polypoid lesions and superficial lesions.

Blue laser imaging combined with JNET classification is an effective tool for judging the depth of invasion of colorectal lesions. Morphological differences in colorectal lesions are not factors that influence the application of JNET classification in colorectal lesions.