Your browser doesn't support javascript.
loading
Convolutional Neural Networks for Optical Discrimination Between Histological Types of Colorectal Polyps Based on White Light Endoscopic Images.
Panteris, Vasileios; Feretzakis, Georgios; Karantanos, Panagiotis; Kalles, Dimitris; Verykios, Vassilios V; Panoutsakou, Maria; Karagianni, Eirini; Zoubouli, Christina; Vgenopoulou, Stefani; Pierrakou, Aikaterini; Theodorakopoulou, Maria; Papalois, Apostolos E; Thomaidis, Thomas; Dalainas, Ilias; Kouroumalis, Elias.
Affiliation
  • Panteris V; Gastroenterology Department, Sismanogleio General Hospital, Marousi, Greece.
  • Feretzakis G; Hellenic Society of Gastrointestinal Oncology.
  • Karantanos P; School of Science and Technology, Hellenic Open University, Patras, Greece.
  • Kalles D; Department of Quality Control, Research and Continuing Education, Sismanogleio General Hospital, Marousi, Greece.
  • Verykios VV; Gastroenterology Department, Sismanogleio General Hospital, Marousi, Greece.
  • Panoutsakou M; School of Science and Technology, Hellenic Open University, Patras, Greece.
  • Karagianni E; School of Science and Technology, Hellenic Open University, Patras, Greece.
  • Zoubouli C; Gastroenterology Department, Sismanogleio General Hospital, Marousi, Greece.
  • Vgenopoulou S; Gastroenterology Department, Sismanogleio General Hospital, Marousi, Greece.
  • Pierrakou A; Pathology Department, Sismanogleio General Hospital, Marousi, Greece.
  • Theodorakopoulou M; Pathology Department, Sismanogleio General Hospital, Marousi, Greece.
  • Papalois AE; Pathology Department, Sismanogleio General Hospital, Marousi, Greece.
  • Thomaidis T; Pathology Department, Sismanogleio General Hospital, Marousi, Greece.
  • Dalainas I; Special Unit for Biomedical Research and Education, School of Medicine, Aristotle University of Thessaloniki, Greece.
  • Kouroumalis E; Hellenic Society of Gastrointestinal Oncology.
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.
Subject(s)
Key words
Fulltext
Print
XML
PubMed Links
Search on Google

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
Fulltext
Print
XML
PubMed Links
Search on Google

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