Development of a hybrid deep learning-based framework for liver fibrosis classification using ultrasound images
The hybrid model achieved good diagnostic results with high sensitivity, specificity, and confidence. The Grad-CAM images validated that the model was focusing on significant areas, as shown by the heat map, which proves that it has potential as a non-invasive, accurate, and interpretable tool for automated liver fibrosis staging using ultrasound images.
Authors
- Adenike Adeniji-Sofoluwe (ORCID: https://orcid.org/0000-0002-2180-9971)
- Chiagoziem A. Otuechere (ORCID: https://orcid.org/0000-0003-2393-1409)
- Benjamin S. Aribisala (ORCID: https://orcid.org/0000-0002-6290-1707)
- Funmilayo Eniola Olopade (ORCID: https://orcid.org/0000-0002-0868-9637)
- Adedotun F. Adesina
- Blessing Oluwatobi Olorunfemi
Institutions
- Lagos State University (NG)
- University of Ibadan (NG)
- University of Lagos (NG)
- Redeemer's University (NG)
- University of Chicago (US)
Publication Details
- Journal
- iLiver
- Published
- 2026-02-09
- DOI
- https://doi.org/10.1016/j.iliver.2026.100225
- Primary Topic
- Liver Disease Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 0.00