AnatoMask: Enhancing Medical Image Segmentation with Reconstruction-guided Self-masking
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929423634137088 |
|---|---|
| author | Li, Yuheng Luan, Tianyu Wu, Yizhou Pan, Shaoyan Chen, Yenho Yang, Xiaofeng |
| author_facet | Li, Yuheng Luan, Tianyu Wu, Yizhou Pan, Shaoyan Chen, Yenho Yang, Xiaofeng |
| contents | Due to the scarcity of labeled data, self-supervised learning (SSL) has gained much attention in 3D medical image segmentation, by extracting semantic representations from unlabeled data. Among SSL strategies, Masked image modeling (MIM) has shown effectiveness by reconstructing randomly masked images to learn detailed representations. However, conventional MIM methods require extensive training data to achieve good performance, which still poses a challenge for medical imaging. Since random masking uniformly samples all regions within medical images, it may overlook crucial anatomical regions and thus degrade the pretraining efficiency. We propose AnatoMask, a novel MIM method that leverages reconstruction loss to dynamically identify and mask out anatomically significant regions to improve pretraining efficacy. AnatoMask takes a self-distillation approach, where the model learns both how to find more significant regions to mask and how to reconstruct these masked regions. To avoid suboptimal learning, Anatomask adjusts the pretraining difficulty progressively using a masking dynamics function. We have evaluated our method on 4 public datasets with multiple imaging modalities (CT, MRI, and PET). AnatoMask demonstrates superior performance and scalability compared to existing SSL methods. The code is available at https://github.com/ricklisz/AnatoMask. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_06468 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AnatoMask: Enhancing Medical Image Segmentation with Reconstruction-guided Self-masking Li, Yuheng Luan, Tianyu Wu, Yizhou Pan, Shaoyan Chen, Yenho Yang, Xiaofeng Computer Vision and Pattern Recognition Due to the scarcity of labeled data, self-supervised learning (SSL) has gained much attention in 3D medical image segmentation, by extracting semantic representations from unlabeled data. Among SSL strategies, Masked image modeling (MIM) has shown effectiveness by reconstructing randomly masked images to learn detailed representations. However, conventional MIM methods require extensive training data to achieve good performance, which still poses a challenge for medical imaging. Since random masking uniformly samples all regions within medical images, it may overlook crucial anatomical regions and thus degrade the pretraining efficiency. We propose AnatoMask, a novel MIM method that leverages reconstruction loss to dynamically identify and mask out anatomically significant regions to improve pretraining efficacy. AnatoMask takes a self-distillation approach, where the model learns both how to find more significant regions to mask and how to reconstruct these masked regions. To avoid suboptimal learning, Anatomask adjusts the pretraining difficulty progressively using a masking dynamics function. We have evaluated our method on 4 public datasets with multiple imaging modalities (CT, MRI, and PET). AnatoMask demonstrates superior performance and scalability compared to existing SSL methods. The code is available at https://github.com/ricklisz/AnatoMask. |
| title | AnatoMask: Enhancing Medical Image Segmentation with Reconstruction-guided Self-masking |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.06468 |