Comparison of deep learning schemes in grading non-alcoholic fatty liver disease using B-mode ultrasound hepatorenal window images with liver biopsy as the gold standard
All networks achieved high performance in HS assessment. DenseNet201 with the use of augmented data seems to be the most efficient supplementary tool for NAFLD diagnosis and grading.
Authors
- George C. Kagadis (ORCID: https://orcid.org/0000-0002-6983-2863)
- Stavros Tsantis (ORCID: https://orcid.org/0000-0003-1785-2712)
- Petros Drazinos
- Paraskevi Katsakiori (ORCID: https://orcid.org/0009-0001-1640-1058)
- Dimitrios Karnabatidis (ORCID: https://orcid.org/0000-0001-5950-8472)
- John D. Hazle (ORCID: https://orcid.org/0000-0003-4695-5825)
- Stavros Spiliοpoulos (ORCID: https://orcid.org/0000-0003-1860-0568)
- P.S. Zoumpoulis (ORCID: https://orcid.org/0000-0002-4985-2496)
- Ilias Gatos (ORCID: https://orcid.org/0000-0003-4949-5297)
- Ioannis Theotokas
- Efstratios Syrmas
Institutions
- The University of Texas MD Anderson Cancer Center (US)
- University of Patras (GR)
- National and Kapodistrian University of Athens (GR)
- Higher Ecclesiastical Academy of Athens (GR)
- Athens State University (US)
Publication Details
- Journal
- Physica Medica
- Published
- 2024-12-02
- DOI
- https://doi.org/10.1016/j.ejmp.2024.104862
- Citations
- 6
- Primary Topic
- Liver Disease Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 2.32