Confidence-Weighted Semi-Supervised Learning for Skin Lesion Segmentation Using Hybrid CNN-Transformer Networks
Fuente:
arXiv
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909852577562624 |
|---|---|
| author | Qamar, Saqib |
| author_facet | Qamar, Saqib |
| contents | Automated skin lesion segmentation through dermoscopic analysis is essential for early skin cancer detection, yet remains challenging due to limited annotated training data. We present MIRA-U, a semi-supervised framework that combines uncertainty-aware teacher-student pseudo-labeling with a hybrid CNN-Transformer architecture. Our approach employs a teacher network pre-trained via masked image modeling to generate confidence-weighted soft pseudo-labels, which guide a U-shaped CNN-Transformer student network featuring cross-attention skip connections. This design enhances pseudo-label quality and boundary delineation, surpassing reconstruction-based and CNN-only baselines, particularly in low-annotation regimes. Extensive evaluation on ISIC-2016 and PH2 datasets demonstrates superior performance, achieving a Dice Similarity Coefficient (DSC) of 0.9153 and Intersection over Union (IoU) of 0.8552 using only 50% labeled data. Code is publicly available on GitHub. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_15354 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Confidence-Weighted Semi-Supervised Learning for Skin Lesion Segmentation Using Hybrid CNN-Transformer Networks Qamar, Saqib Image and Video Processing Computer Vision and Pattern Recognition Automated skin lesion segmentation through dermoscopic analysis is essential for early skin cancer detection, yet remains challenging due to limited annotated training data. We present MIRA-U, a semi-supervised framework that combines uncertainty-aware teacher-student pseudo-labeling with a hybrid CNN-Transformer architecture. Our approach employs a teacher network pre-trained via masked image modeling to generate confidence-weighted soft pseudo-labels, which guide a U-shaped CNN-Transformer student network featuring cross-attention skip connections. This design enhances pseudo-label quality and boundary delineation, surpassing reconstruction-based and CNN-only baselines, particularly in low-annotation regimes. Extensive evaluation on ISIC-2016 and PH2 datasets demonstrates superior performance, achieving a Dice Similarity Coefficient (DSC) of 0.9153 and Intersection over Union (IoU) of 0.8552 using only 50% labeled data. Code is publicly available on GitHub. |
| title | Confidence-Weighted Semi-Supervised Learning for Skin Lesion Segmentation Using Hybrid CNN-Transformer Networks |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.15354 |