Unveiling the black box: Explainable transfer learning for ocular disorder diagnosis
Accuracy alone is insufficient for trustworthy medical AI. Explainable AI is essential for model selection. EfficientNetB3 offers the best balance between performance and interpretability, and glaucoma diagnosis requires more advanced, segmentation-aware pipelines.
Authors
- Tehseen Mazhar (ORCID: https://orcid.org/0000-0002-4649-2376)
- Arfan Jaffar (ORCID: https://orcid.org/0000-0002-7003-4498)
- Muhammad Amir Khan (ORCID: https://orcid.org/0009-0001-6402-6942)
- Zaib un Nisa
- Habib Hamam
- Ines Hilali Jaghdam
Institutions
- Princess Nourah bint Abdulrahman University (SA)
- Université de Moncton (CA)
- University of Johannesburg (ZA)
- Government of Pakistan (PK)
- Omar Bongo University (GA)
- University of Ha'il (SA)
- Superior University (PK)
- National College of Business Administration and Economics (PK)
- Universiti Teknologi MARA (MY)
Publication Details
- Journal
- Digital Health
- Published
- 2026-02-01
- DOI
- https://doi.org/10.1177/20552076261423994
- Primary Topic
- Retinal Imaging and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 0.00