Comparative Analysis of Deep Neural Networks for Automated Ulcerative Colitis Severity Assessment
This study demonstrates that multiple state-of-the-art deep neural network architectures could automate UC severity classification. Simpler architectures were found to achieve competitive results with larger models, challenging the assumption that larger networks necessarily provide better clinical outcomes.
Authors
- Iοannis Kakkos (ORCID: https://orcid.org/0000-0001-8365-2140)
- Αθανάσιος Αναστασίου (ORCID: https://orcid.org/0000-0001-6679-3590)
- Stavros-Theofanis Miloulis (ORCID: https://orcid.org/0000-0001-5091-5530)
- Ουρανία Πετροπούλου
- Ioannis Vezakis (ORCID: https://orcid.org/0000-0003-4976-4901)
- George K. Matsopoulos (ORCID: https://orcid.org/0000-0002-2600-9914)
- Andreas Vezakis (ORCID: https://orcid.org/0009-0001-7410-2689)
Institutions
- National Technical University of Athens (GR)
- University of West Attica (GR)
Publication Details
- Journal
- Bioengineering
- Published
- 2025-04-13
- DOI
- https://doi.org/10.3390/bioengineering12040413
- Citations
- 1
- Primary Topic
- Colorectal Cancer Screening and Detection
- Type
- article
- Field-Weighted Citation Impact
- 1.05