Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

In Gastrointestinal endoscopy ; h5-index 72.0

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 : We developed a deep learning (DL) model using semantic segmentation to delineate polyp boundaries, and a DL model to classify subregions within the segmented polyp. These subregions were classified independently, and 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 0.96, specificity of 0.84, negative predictive value (NPV) of 0.91, and high-confidence rate (HCR) of 0.88, 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 0.95, specificity of 0.84, NPV of 0.91 and HCR of 0.86.

CONCLUSIONS : The CADx model 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.

Rodriguez-Diaz Eladio, Baffy Gy├Ârgy, Lo Wai-Kit, Mashimo Hiroshi, Vidyarthi Gitanjali, Mohapatra Shyam S, Singh Satish K

2020-Sep-16

artificial intelligence, augmented visualization, colorectal neoplasm, colorectal polyps, computer-aided diagnosis, deep learning, endoscopy, histology map, machine learning, near-focus narrow-band imaging, optical biopsy, real-time polyp histology