EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

A Deep Learning Model for Classifying Histological Types of Colorectal Polyps

Vasileios Panteris, Dimitris Kalles, Vassilios S Verykios, Stefani Vgenopoulou, Aikaterini Pierrakou, Ilias Dalainas, Georgios Feretzakis

Studies in Health Technology and Informatics · 2023

DOI: 10.3233/shti230555 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2023. Verfasst von Vasileios Panteris und 6 weiteren Autor:innen. Beteiligte Einrichtung: Gastroenterology Department, Sismanogleio General Hospital, Marousi, Greece. Hauptthemen laut MEDLINE: Colonic Polyps, Deep Learning. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this study a deep learning architecture based on a convolutional neural network has been evaluated for the classification of white light images of colorectal polyps acquired during the process of a colonoscopy, to estimate the accuracy of the optical recognition of histologic types of polyps. Convolutional neural networks (CNNs), a subclass of artificial neural networks that have gained dominance in several computer vision tasks, are gaining popularity in many medical fields, including endoscopy. The TensorFlow framework was used for implementing EfficientNetB7, which was trained with 924 images, drawn from 86 patients. 55% of the polyps were adenomas, 22% were hyperplastic, and 17% were lesions with sessile serrations. The validation loss, accuracy, and AUC ROC were 0.4845, 0.7778, and 0.8881 respectively.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Colonic PolypsDeep LearningHumansColonoscopyNeural Networks, Computer

Stichwörter der Autor:innen

Deep learningconvolutional neural networksendoscopypolyps

Autor:innen und Institutionen

  • Gastroenterology Department, Sismanogleio General Hospital, Marousi, Greece.
  • Hellenic Society of Gastrointestinal Oncology, Greece.
  • School of Science and Technology, Hellenic Open University, Patras, Greece.
  • Pathology Department, Sismanogleio General Hospital, Marousi, Greece.
  • Administration, Sismanogleio General Hospital, Marousi, Greece.
  • Sismanogleio General Hospital, Department of Quality Control, Research and Continuing Education, Marousi, Greece.

Zitieren

APA

Panteris, V., Kalles, D., Verykios, V. S., Vgenopoulou, S., Pierrakou, A., Dalainas, I., & Feretzakis, G. (2023). A Deep Learning Model for Classifying Histological Types of Colorectal Polyps. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti230555

Vancouver

Panteris V, Kalles D, Verykios VS, Vgenopoulou S, Pierrakou A, Dalainas I, et al. A Deep Learning Model for Classifying Histological Types of Colorectal Polyps. Studies in Health Technology and Informatics. 2023. doi:10.3233/shti230555

BibTeX
@article{Panteris2023,
  author = {Panteris, Vasileios and Kalles, Dimitris and Verykios, Vassilios S and Vgenopoulou, Stefani and Pierrakou, Aikaterini and Dalainas, Ilias and Feretzakis, Georgios},
  title = {A Deep Learning Model for Classifying Histological Types of Colorectal Polyps},
  journal = {Studies in Health Technology and Informatics},
  year = {2023},
  doi = {10.3233/shti230555}
}
Kostenlos starten →