AdaptDiff: Cross-Modality Domain Adaptation via Weak Conditional Semantic Diffusion for Retinal Vessel 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_ | 1866912061936631808 |
|---|---|
| author | Hu, Dewei Li, Hao Liu, Han Wang, Jiacheng Yao, Xing Lu, Daiwei Oguz, Ipek |
| author_facet | Hu, Dewei Li, Hao Liu, Han Wang, Jiacheng Yao, Xing Lu, Daiwei Oguz, Ipek |
| contents | Deep learning has shown remarkable performance in medical image segmentation. However, despite its promise, deep learning has many challenges in practice due to its inability to effectively transition to unseen domains, caused by the inherent data distribution shift and the lack of manual annotations to guide domain adaptation. To tackle this problem, we present an unsupervised domain adaptation (UDA) method named AdaptDiff that enables a retinal vessel segmentation network trained on fundus photography (FP) to produce satisfactory results on unseen modalities (e.g., OCT-A) without any manual labels. For all our target domains, we first adopt a segmentation model trained on the source domain to create pseudo-labels. With these pseudo-labels, we train a conditional semantic diffusion probabilistic model to represent the target domain distribution. Experimentally, we show that even with low quality pseudo-labels, the diffusion model can still capture the conditional semantic information. Subsequently, we sample on the target domain with binary vessel masks from the source domain to get paired data, i.e., target domain synthetic images conditioned on the binary vessel map. Finally, we fine-tune the pre-trained segmentation network using the synthetic paired data to mitigate the domain gap. We assess the effectiveness of AdaptDiff on seven publicly available datasets across three distinct modalities. Our results demonstrate a significant improvement in segmentation performance across all unseen datasets. Our code is publicly available at https://github.com/DeweiHu/AdaptDiff. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_04648 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AdaptDiff: Cross-Modality Domain Adaptation via Weak Conditional Semantic Diffusion for Retinal Vessel Segmentation Hu, Dewei Li, Hao Liu, Han Wang, Jiacheng Yao, Xing Lu, Daiwei Oguz, Ipek Computer Vision and Pattern Recognition Deep learning has shown remarkable performance in medical image segmentation. However, despite its promise, deep learning has many challenges in practice due to its inability to effectively transition to unseen domains, caused by the inherent data distribution shift and the lack of manual annotations to guide domain adaptation. To tackle this problem, we present an unsupervised domain adaptation (UDA) method named AdaptDiff that enables a retinal vessel segmentation network trained on fundus photography (FP) to produce satisfactory results on unseen modalities (e.g., OCT-A) without any manual labels. For all our target domains, we first adopt a segmentation model trained on the source domain to create pseudo-labels. With these pseudo-labels, we train a conditional semantic diffusion probabilistic model to represent the target domain distribution. Experimentally, we show that even with low quality pseudo-labels, the diffusion model can still capture the conditional semantic information. Subsequently, we sample on the target domain with binary vessel masks from the source domain to get paired data, i.e., target domain synthetic images conditioned on the binary vessel map. Finally, we fine-tune the pre-trained segmentation network using the synthetic paired data to mitigate the domain gap. We assess the effectiveness of AdaptDiff on seven publicly available datasets across three distinct modalities. Our results demonstrate a significant improvement in segmentation performance across all unseen datasets. Our code is publicly available at https://github.com/DeweiHu/AdaptDiff. |
| title | AdaptDiff: Cross-Modality Domain Adaptation via Weak Conditional Semantic Diffusion for Retinal Vessel Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.04648 |