TY  - JOUR 
AU  - Du, Yanglin
AU  - Villarrubia González, Gabriel
PY  - 2026
SN  - 2169-3536
UR  - http://hdl.handle.net/10366/172272
AB  - [EN]Automated skin lesion segmentation via deep learning has achieved remarkable accuracy in controlled laboratory settings, yet its clinical translation to point-of-care (PoC) edge devices remains fundamentally constrained by the computational...
LA  - eng
PB  - IEEE
KW  - Edge computing
KW  - Evaluation standardization
KW  - Knowledge distillation
KW  - Lightweight neural networks
KW  - Medical image segmentation
KW  - Point-of-care diagnostics
KW  - Skin lesion segmentation
KW  - State space models
TI  - Lightweight Skin Lesion Segmentation for Edge Deployment: A Critical Review of Architectures, Accuracy Compensation, and Clinical Translation
DO  - 10.1109/ACCESS.2026.3682487
T2  - IEEE Access
VL  - 14
M2  - 56266
ER  -