Computer-aided prediction of polyp histology on white light colonoscopy using surface pattern analysis.
Journal
Endoscopy
ISSN: 1438-8812
Titre abrégé: Endoscopy
Pays: Germany
ID NLM: 0215166
Informations de publication
Date de publication:
03 2019
03 2019
Historique:
pubmed:
26
10
2018
medline:
21
4
2020
entrez:
26
10
2018
Statut:
ppublish
Résumé
This study aimed to evaluate a new computational histology prediction system based on colorectal polyp textural surface patterns using high definition white light images. Textural elements (textons) were characterized according to their contrast with respect to the surface, shape, and number of bifurcations, assuming that dysplastic polyps are associated with highly contrasted, large tubular patterns with some degree of bifurcation. Computer-aided diagnosis (CAD) was compared with pathological diagnosis and the diagnosis made by endoscopists using Kudo and Narrow-Band Imaging International Colorectal Endoscopic classifications. Images of 225 polyps were evaluated (142 dysplastic and 83 nondysplastic). The CAD system correctly classified 205 polyps (91.1 %): 131/142 dysplastic (92.3 %) and 74/83 (89.2 %) nondysplastic. For the subgroup of 100 diminutive polyps (≤ 5 mm), CAD correctly classified 87 polyps (87.0 %): 43/50 (86.0 %) dysplastic and 44/50 (88.0 %) nondysplastic. There were no statistically significant differences in polyp histology prediction between the CAD system and endoscopist assessment. A computer vision system based on the characterization of the polyp surface in white light accurately predicted colorectal polyp histology.
Sections du résumé
BACKGROUND
This study aimed to evaluate a new computational histology prediction system based on colorectal polyp textural surface patterns using high definition white light images.
METHODS
Textural elements (textons) were characterized according to their contrast with respect to the surface, shape, and number of bifurcations, assuming that dysplastic polyps are associated with highly contrasted, large tubular patterns with some degree of bifurcation. Computer-aided diagnosis (CAD) was compared with pathological diagnosis and the diagnosis made by endoscopists using Kudo and Narrow-Band Imaging International Colorectal Endoscopic classifications.
RESULTS
Images of 225 polyps were evaluated (142 dysplastic and 83 nondysplastic). The CAD system correctly classified 205 polyps (91.1 %): 131/142 dysplastic (92.3 %) and 74/83 (89.2 %) nondysplastic. For the subgroup of 100 diminutive polyps (≤ 5 mm), CAD correctly classified 87 polyps (87.0 %): 43/50 (86.0 %) dysplastic and 44/50 (88.0 %) nondysplastic. There were no statistically significant differences in polyp histology prediction between the CAD system and endoscopist assessment.
CONCLUSION
A computer vision system based on the characterization of the polyp surface in white light accurately predicted colorectal polyp histology.
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
261-265Commentaires et corrections
Type : CommentIn
Informations de copyright
© Georg Thieme Verlag KG Stuttgart · New York.
Déclaration de conflit d'intérêts
María Pellisé has been consultant for Norgine Iberia from 2012 to 2017. She has received speaker fees from Norgine Iberia, Casen Recordati and Olympus Spain in the last 5 years. Gloria Fernández-Esparrach has received fees for organizing courses from Norgine Iberia and Olympus Spain in the last two years and has been consultant for a trial design for CDx Diagnostics