Deep Skin Lesion Segmentation with Transformer-CNN Fusion: Toward Intelligent Skin Cancer Analysis
This work addresses automated segmentation for skin cancer analysis, but it is incremental as it builds on the TransUNet architecture with specific enhancements.
The paper tackles the challenge of segmenting skin lesions with complex structures and blurred boundaries by proposing an improved TransUNet architecture that integrates transformers and CNNs, achieving higher mIoU, mDice, and mAcc scores compared to existing methods.
This paper proposes a high-precision semantic segmentation method based on an improved TransUNet architecture to address the challenges of complex lesion structures, blurred boundaries, and significant scale variations in skin lesion images. The method integrates a transformer module into the traditional encoder-decoder framework to model global semantic information, while retaining a convolutional branch to preserve local texture and edge features. This enhances the model's ability to perceive fine-grained structures. A boundary-guided attention mechanism and multi-scale upsampling path are also designed to improve lesion boundary localization and segmentation consistency. To verify the effectiveness of the approach, a series of experiments were conducted, including comparative studies, hyperparameter sensitivity analysis, data augmentation effects, input resolution variation, and training data split ratio tests. Experimental results show that the proposed model outperforms existing representative methods in mIoU, mDice, and mAcc, demonstrating stronger lesion recognition accuracy and robustness. In particular, the model achieves better boundary reconstruction and structural recovery in complex scenarios, making it well-suited for the key demands of automated segmentation tasks in skin lesion analysis.