Validation of Probe-based Confocal Laser Endomicroscopy (pCLE) Criteria for Diagnosing Colon Polyp Histology

BACKGROUND: Validated probe-based confocal endomicroscopy (pCLE) criteria for distinguishing hyperplastic polyps (HPs) and tubular adenomas (TA) have not yet been developed. AIM: To develop pCLE criteria for distinguishing HP from TA and evaluate its performance characteristics among experts. METHODS: pCLE criteria for colon polyp histology were developed and tested in 2 phases prospectively. Phase I: 8 preliminary criteria were developed and tested internally. Criteria achieving an accuracy of >75% (epithelial surface: regular vs. irregular; goblet cells: increased vs. decreased; gland axis: horizontal vs. vertical; gland shape: slit/stellate vs. villiform; image scale: gray vs. dark) were evaluated in Phase II of study wherein external assessors evaluated these criteria in a separate set of pCLE videos. Accuracy and interobserver agreement (95% confidence intervals) were determined for colon histology prediction. RESULTS: Phase I (criteria development/internal testing): 8 criteria were assessed by 4 pCLE experts using 28 videos (14 HP/14 TA). Five of 8 pCLE criteria met selection for phase II (accuracy >75%). Phase II (external validation): 36 pCLE colon polyp videos (HP 16/TA 20) were evaluated by 8 external assessors. Overall accuracy in diagnosis of colon polyp histology was 84.9% (95% confidence interval, 81.7-87.7). Of predictions made with high confidence (75%), histology was predicted with an accuracy of 91%, sensitivity 83%, specificity 100%, negative predictive value 87% and positive predictive value 98%. Interobserver agreement was substantial (κ=0.73). CONCLUSIONS: We demonstrate the development and validation of pCLE criteria for prediction of colon polyp histology. Using these criteria, overall accuracy in differentiating TA from HP was high with substantial interobserver agreement.