ACE: Anatomically Consistent Embeddings in Composition and Decomposition
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915107500457984 |
|---|---|
| author | Zhou, Ziyu Luo, Haozhe Taher, Mohammad Reza Hosseinzadeh Pang, Jiaxuan Ding, Xiaowei Gotway, Michael Liang, Jianming |
| author_facet | Zhou, Ziyu Luo, Haozhe Taher, Mohammad Reza Hosseinzadeh Pang, Jiaxuan Ding, Xiaowei Gotway, Michael Liang, Jianming |
| contents | Medical images acquired from standardized protocols show consistent macroscopic or microscopic anatomical structures, and these structures consist of composable/decomposable organs and tissues, but existing self-supervised learning (SSL) methods do not appreciate such composable/decomposable structure attributes inherent to medical images. To overcome this limitation, this paper introduces a novel SSL approach called ACE to learn anatomically consistent embedding via composition and decomposition with two key branches: (1) global consistency, capturing discriminative macro-structures via extracting global features; (2) local consistency, learning fine-grained anatomical details from composable/decomposable patch features via corresponding matrix matching. Experimental results across 6 datasets 2 backbones, evaluated in few-shot learning, fine-tuning, and property analysis, show ACE's superior robustness, transferability, and clinical potential. The innovations of our ACE lie in grid-wise image cropping, leveraging the intrinsic properties of compositionality and decompositionality of medical images, bridging the semantic gap from high-level pathologies to low-level tissue anomalies, and providing a new SSL method for medical imaging. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_10131 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ACE: Anatomically Consistent Embeddings in Composition and Decomposition Zhou, Ziyu Luo, Haozhe Taher, Mohammad Reza Hosseinzadeh Pang, Jiaxuan Ding, Xiaowei Gotway, Michael Liang, Jianming Computer Vision and Pattern Recognition Medical images acquired from standardized protocols show consistent macroscopic or microscopic anatomical structures, and these structures consist of composable/decomposable organs and tissues, but existing self-supervised learning (SSL) methods do not appreciate such composable/decomposable structure attributes inherent to medical images. To overcome this limitation, this paper introduces a novel SSL approach called ACE to learn anatomically consistent embedding via composition and decomposition with two key branches: (1) global consistency, capturing discriminative macro-structures via extracting global features; (2) local consistency, learning fine-grained anatomical details from composable/decomposable patch features via corresponding matrix matching. Experimental results across 6 datasets 2 backbones, evaluated in few-shot learning, fine-tuning, and property analysis, show ACE's superior robustness, transferability, and clinical potential. The innovations of our ACE lie in grid-wise image cropping, leveraging the intrinsic properties of compositionality and decompositionality of medical images, bridging the semantic gap from high-level pathologies to low-level tissue anomalies, and providing a new SSL method for medical imaging. |
| title | ACE: Anatomically Consistent Embeddings in Composition and Decomposition |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.10131 |