A multi-task deep learning pipeline integrating vessel segmentation and radiomics for multiclass retinal disease classification
This multi-task pipeline demonstrates the potential of combining transformer-based segmentation with radiomics for accurate, interpretable retinal disease classification, showing strong generalizability for future clinical applications.
Authors
- Feng Yan (ORCID: https://orcid.org/0000-0001-9269-7025)
- Yanxia Liu (ORCID: https://orcid.org/0000-0002-5113-037X)
- Qingsong Zhao
- Geng He (ORCID: https://orcid.org/0009-0002-4077-5495)
Institutions
- Jiuquan Iron & Steel (China) (CN)
- Chifeng Municipal Hospital (CN)
- Dongguan People’s Hospital (CN)
- Inner Mongolia Autonomous Region Hospital of Traditional Chinese Medicine (CN)
Publication Details
- Journal
- Photodiagnosis and Photodynamic Therapy
- Published
- 2025-09-04
- DOI
- https://doi.org/10.1016/j.pdpdt.2025.105209
- Citations
- 1
- Primary Topic
- Retinal Imaging and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 1.36