De-LightSAM: Modality-Decoupled Lightweight SAM for Generalizable Medical Segmentation
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_ | 1866916817614667776 |
|---|---|
| author | Xu, Qing Li, Jiaxuan He, Xiangjian Li, Chenxin Tesem, Fiseha B. Duan, Wenting Chen, Zhen Qu, Rong Garibaldi, Jonathan M. Chen, Chang Wen |
| author_facet | Xu, Qing Li, Jiaxuan He, Xiangjian Li, Chenxin Tesem, Fiseha B. Duan, Wenting Chen, Zhen Qu, Rong Garibaldi, Jonathan M. Chen, Chang Wen |
| contents | The universality of deep neural networks across different modalities and their generalization capabilities to unseen domains play an essential role in medical image segmentation. The recent segment anything model (SAM) has demonstrated strong adaptability across diverse natural scenarios. However, the huge computational costs, demand for manual annotations as prompts and conflict-prone decoding process of SAM degrade its generalization capabilities in medical scenarios. To address these limitations, we propose a modality-decoupled lightweight SAM for domain-generalized medical image segmentation, named De-LightSAM. Specifically, we first devise a lightweight domain-controllable image encoder (DC-Encoder) that produces discriminative visual features for diverse modalities. Further, we introduce the self-patch prompt generator (SP-Generator) to automatically generate high-quality dense prompt embeddings for guiding segmentation decoding. Finally, we design the query-decoupled modality decoder (QM-Decoder) that leverages a one-to-one strategy to provide an independent decoding channel for every modality, preventing mutual knowledge interference of different modalities. Moreover, we design a multi-modal decoupled knowledge distillation (MDKD) strategy to leverage robust common knowledge to complement domain-specific medical feature representations. Extensive experiments indicate that De-LightSAM outperforms state-of-the-arts in diverse medical imaging segmentation tasks, displaying superior modality universality and generalization capabilities. Especially, De-LightSAM uses only 2.0% parameters compared to SAM-H. The source code is available at https://github.com/xq141839/De-LightSAM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_14153 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | De-LightSAM: Modality-Decoupled Lightweight SAM for Generalizable Medical Segmentation Xu, Qing Li, Jiaxuan He, Xiangjian Li, Chenxin Tesem, Fiseha B. Duan, Wenting Chen, Zhen Qu, Rong Garibaldi, Jonathan M. Chen, Chang Wen Image and Video Processing Computer Vision and Pattern Recognition The universality of deep neural networks across different modalities and their generalization capabilities to unseen domains play an essential role in medical image segmentation. The recent segment anything model (SAM) has demonstrated strong adaptability across diverse natural scenarios. However, the huge computational costs, demand for manual annotations as prompts and conflict-prone decoding process of SAM degrade its generalization capabilities in medical scenarios. To address these limitations, we propose a modality-decoupled lightweight SAM for domain-generalized medical image segmentation, named De-LightSAM. Specifically, we first devise a lightweight domain-controllable image encoder (DC-Encoder) that produces discriminative visual features for diverse modalities. Further, we introduce the self-patch prompt generator (SP-Generator) to automatically generate high-quality dense prompt embeddings for guiding segmentation decoding. Finally, we design the query-decoupled modality decoder (QM-Decoder) that leverages a one-to-one strategy to provide an independent decoding channel for every modality, preventing mutual knowledge interference of different modalities. Moreover, we design a multi-modal decoupled knowledge distillation (MDKD) strategy to leverage robust common knowledge to complement domain-specific medical feature representations. Extensive experiments indicate that De-LightSAM outperforms state-of-the-arts in diverse medical imaging segmentation tasks, displaying superior modality universality and generalization capabilities. Especially, De-LightSAM uses only 2.0% parameters compared to SAM-H. The source code is available at https://github.com/xq141839/De-LightSAM. |
| title | De-LightSAM: Modality-Decoupled Lightweight SAM for Generalizable Medical Segmentation |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.14153 |