Med-DGTN: Dynamic Graph Transformer with Adaptive Wavelet Fusion for multi-label medical image classification
This investigation establishes that joint modeling of dynamic disease correlations and wavelet-optimized feature representation significantly enhances multi-label diagnostic capabilities. Med-DGTN's architecture demonstrates clinical translatability by revealing disease interaction patterns through interpretable graph structures, potentially informing precision diagnostics in multi-morbidity scenarios.
Authors
- Zongyun Gu (ORCID: https://orcid.org/0000-0002-3010-3516)
- Guanyu Zhang (ORCID: https://orcid.org/0000-0002-3108-5604)
- Jin Li (ORCID: https://orcid.org/0000-0001-9201-2321)
- Yan Li (ORCID: https://orcid.org/0000-0001-6155-0389)
- Tingting Wang (ORCID: https://orcid.org/0000-0002-2666-7159)
- Guangze Shi (ORCID: https://orcid.org/0009-0009-9979-3744)
Institutions
- Anhui University of Traditional Chinese Medicine (CN)
- National Science Centre (PL)
- Hefei First People's Hospital (CN)
Publication Details
- Journal
- Frontiers in Medicine
- Published
- 2025-07-24
- DOI
- https://doi.org/10.3389/fmed.2025.1600736
- Primary Topic
- COVID-19 diagnosis using AI
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Anhui Provincial Department of Education