Convolutional Neural Networks for Optical Discrimination Between Histological Types of Colorectal Polyps Based on White Light Endoscopic Images.
Stud Health Technol Inform
; 302: 576-580, 2023 May 18.
Article
in En
| MEDLINE
| ID: mdl-37203751
ABSTRACT
The objective of this study was to compare different convolutional neural networks (CNNs), as employed in a Python-produced deep learning process, used on white light images of colorectal polyps acquired during the process of a colonoscopy, in order to estimate the accuracy of the optical recognition of particular histologic types of polyps. The TensorFlow framework was used for Inception V3, ResNet50, DenseNet121, and NasNetLarge, which were trained with 924 images, drawn from 86 patients.
Key words
Full text:
1
Collection:
01-internacional
Database:
MEDLINE
Main subject:
Colonic Polyps
Type of study:
Prognostic_studies
Limits:
Humans
Language:
En
Journal:
Stud Health Technol Inform
Journal subject:
INFORMATICA MEDICA
/
PESQUISA EM SERVICOS DE SAUDE
Year:
2023
Type:
Article
Affiliation country:
Greece