Endoscopy 2019; 51(03): 261-265
DOI: 10.1055/a-0732-5250
Innovations and brief communications
© Georg Thieme Verlag KG Stuttgart · New York

Computer-aided prediction of polyp histology on white light colonoscopy using surface pattern analysis

Cristina Sánchez-Montes
1  Endoscopy Unit, Gastroenterology Department, Hospital Clínic, IDIBAPS, CIBEREHD, University of Barcelona, Barcelona, Spain
,
Francisco Javier Sánchez
2  Computer Science Department, Universitat Autònoma de Barcelona and Computer Vision Center, Barcelona, Spain
,
Jorge Bernal
2  Computer Science Department, Universitat Autònoma de Barcelona and Computer Vision Center, Barcelona, Spain
,
Henry Córdova
1  Endoscopy Unit, Gastroenterology Department, Hospital Clínic, IDIBAPS, CIBEREHD, University of Barcelona, Barcelona, Spain
,
María López-Cerón
1  Endoscopy Unit, Gastroenterology Department, Hospital Clínic, IDIBAPS, CIBEREHD, University of Barcelona, Barcelona, Spain
,
Miriam Cuatrecasas
3  Pathology Department, Centre de Diagnòstic Biomèdic, Hospital Clínic, IDIBAPS, CIBEREHD, University of Barcelona, Barcelona, Spain
4  Banc de Tumors-Biobanc Clínic, IDIBAPS-XBTC, Barcelona, Spain
,
Cristina Rodríguez de Miguel
1  Endoscopy Unit, Gastroenterology Department, Hospital Clínic, IDIBAPS, CIBEREHD, University of Barcelona, Barcelona, Spain
,
Ana García-Rodríguez
1  Endoscopy Unit, Gastroenterology Department, Hospital Clínic, IDIBAPS, CIBEREHD, University of Barcelona, Barcelona, Spain
,
Rodrigo Garcés-Durán
1  Endoscopy Unit, Gastroenterology Department, Hospital Clínic, IDIBAPS, CIBEREHD, University of Barcelona, Barcelona, Spain
,
María Pellisé
1  Endoscopy Unit, Gastroenterology Department, Hospital Clínic, IDIBAPS, CIBEREHD, University of Barcelona, Barcelona, Spain
,
Josep Llach
1  Endoscopy Unit, Gastroenterology Department, Hospital Clínic, IDIBAPS, CIBEREHD, University of Barcelona, Barcelona, Spain
,
Glòria Fernández-Esparrach
1  Endoscopy Unit, Gastroenterology Department, Hospital Clínic, IDIBAPS, CIBEREHD, University of Barcelona, Barcelona, Spain
› Author Affiliations
Further Information

Publication History

submitted 23 November 2017

accepted after revision 13 August 2018

Publication Date:
25 October 2018 (eFirst)

Abstract

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.