Single-Shared Network with Prior-Inspired Loss for Parameter-Efficient Multi-Modal Imaging Skin Lesion Classification
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929294535557120 |
|---|---|
| author | Tang, Peng Lasser, Tobias |
| author_facet | Tang, Peng Lasser, Tobias |
| contents | In this study, we introduce a multi-modal approach that efficiently integrates multi-scale clinical and dermoscopy features within a single network, thereby substantially reducing model parameters. The proposed method includes three novel fusion schemes. Firstly, unlike current methods that usually employ two individual models for for clinical and dermoscopy modalities, we verified that multimodal feature can be learned by sharing the parameters of encoder while leaving the individual modal-specific classifiers. Secondly, the shared cross-attention module can replace the individual one to efficiently interact between two modalities at multiple layers. Thirdly, different from current methods that equally optimize dermoscopy and clinical branches, inspired by prior knowledge that dermoscopy images play a more significant role than clinical images, we propose a novel biased loss. This loss guides the single-shared network to prioritize dermoscopy information over clinical information, implicitly learning a better joint feature representation for the modal-specific task. Extensive experiments on a well-recognized Seven-Point Checklist (SPC) dataset and a collected dataset demonstrate the effectiveness of our method on both CNN and Transformer structures. Furthermore, our method exhibits superiority in both accuracy and model parameters compared to currently advanced methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_19203 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Single-Shared Network with Prior-Inspired Loss for Parameter-Efficient Multi-Modal Imaging Skin Lesion Classification Tang, Peng Lasser, Tobias Image and Video Processing Computer Vision and Pattern Recognition In this study, we introduce a multi-modal approach that efficiently integrates multi-scale clinical and dermoscopy features within a single network, thereby substantially reducing model parameters. The proposed method includes three novel fusion schemes. Firstly, unlike current methods that usually employ two individual models for for clinical and dermoscopy modalities, we verified that multimodal feature can be learned by sharing the parameters of encoder while leaving the individual modal-specific classifiers. Secondly, the shared cross-attention module can replace the individual one to efficiently interact between two modalities at multiple layers. Thirdly, different from current methods that equally optimize dermoscopy and clinical branches, inspired by prior knowledge that dermoscopy images play a more significant role than clinical images, we propose a novel biased loss. This loss guides the single-shared network to prioritize dermoscopy information over clinical information, implicitly learning a better joint feature representation for the modal-specific task. Extensive experiments on a well-recognized Seven-Point Checklist (SPC) dataset and a collected dataset demonstrate the effectiveness of our method on both CNN and Transformer structures. Furthermore, our method exhibits superiority in both accuracy and model parameters compared to currently advanced methods. |
| title | Single-Shared Network with Prior-Inspired Loss for Parameter-Efficient Multi-Modal Imaging Skin Lesion Classification |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.19203 |