M. Akram

Learnable Frequency-Domain Attention with Deep Supervision for Accurate Skin Lesion Segmentation and Diagnosis

A Swin Transformer framework enhanced with a novel Frequency-Aware Multi-Scale Cross-Scale Attention module, named FreqMSCSAM-SwinSegNet, which offers a robust and practical solution for clinical skin lesion segmentation, with the potential to improve diagnostic accuracy and early melanoma detection.