Real-time artificial intelligence-based histologic classification of colorectal polyps with augmented visualization

Background and Aims: Artificial intelligence (AI)-based computer-aided diagnostic (CADx) algorithms are a promising approach for real-time histology (RTH) of colonic polyps. Our aim is to present a novel in situ CADx approach that seeks to increase transparency and interpretability of results by generating an intuitive augmented visualization of the model's predicted histology over the polyp surface. Methods: Wedeveloped a deep learningmodel using semantic segmentation to delineate polyp boundaries and a deep learning model to classify subregions within the segmented polyp. These subregions were classified independently and were subsequently aggregated to generate a histology map of the polyp's surface. We used 740 high-magnification narrow-band images from 607 polyps in 286 patients and over 65,000 subregions to train and validate the model. Results: The model achieved a sensitivity of.96, specificity of.84, negative predictive value (NPV) of.91, and high-confidence rate (HCR) of.88, distinguishing 171 neoplastic polyps from 83 non-neoplastic polyps of all sizes. Among 93 neoplastic and 75 non-neoplastic polyps <= 5 mm, the model achieved a sensitivity of.95, specificity of.84, NPV of.91, and HCR of.86. Conclusions: The CADxmodel is capable of accurately distinguishing neoplastic from non-neoplastic polyps and provides a histology map of the spatial distribution of localized histologic predictions along the delineated polyp surface. This capability may improve interpretability and transparency of AI-based RTH and offer intuitive, accurate, and user-friendly guidance in real time for the clinical management and documentation of optical histology results.

Automated summary

A novel in situ CADx approach using deep learning models was developed for real-time histology of colonic polyps, achieving high sensitivity and specificity in distinguishing neoplastic from non-neoplastic polyps and providing a histology map of the polyp's surface. The model's capability may enhance interpretability of AI-based RTH and offer intuitive, accurate, and user-friendly guidance in clinical management and documentation of optical histology results.