Real-time artificial intelligence–based histologic classification of colorectal polyps with augmented visualization - 12/02/21
Abstract |
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 model 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 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.
Le texte complet de cet article est disponible en PDF.Abbreviations : AI, CADx, HCR, NBI, NICE, NPV, PIVI, RTH, SSAP
Plan
| DISCLOSURE: The following authors received research support for this study from the U.S. Department of Veterans Affairs as a collaboration as part of the VA Colorectal Cancer Cellgenomics Consortium (“VA4C”): S. S. Mohapatra (Research Career Scientist Award IK6BX003778) and S. K. Singh (CSR&D and BLR&D Merit Review Awards CX001146 and BX004455). This material is the result of work supported with resources and use of facilities at the VA Boston Healthcare System. The contents do not represent the views of the U.S. Department of Veterans Affairs or the U.S. Government. All other authors disclosed no financial relationships. |
|
| See CME section, p. 727. |
|
| If you would like to chat with an author of this article, you may contact Dr Singh at satish.singh@va.gov. |
Vol 93 - N° 3
P. 662-670 - mars 2021 Retour au numéro
Article précédent
- Turn down the heat on large serrated polyps
- Christopher M. Navas, Heiko Pohl
- Evaluation of colorectal endoscopic submucosal dissection using a multifunctional snare: a prospective clinical feasibility study (with videos)
- Jun Arimoto, Ken Ohata, Hideyuki Chiba, Jun Tachikawa, Naoya Okada, Hiroki Kuwabara, Michiko Nakaoka, Keiichi Ashikari, Rindo Ishii, Yohei Minato, Maiko Takita, Eiji Sakai, Takashi Muramoto, Nobuyuki Matsuhashi, Tohru Goto, Atsushi Nakajima
Bienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.
Déjà abonné à cette revue ?