Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.04899 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914164641890304 |
|---|---|
| author | Song, Sifan Yoon, Siyeop Jin, Pengfei Kim, Sekeun Tivnan, Matthew Oh, Yujin Meng, Runqi Chen, Ling Lyu, Zhiliang Wu, Dufan Guo, Ning Li, Xiang Li, Quanzheng |
| author_facet | Song, Sifan Yoon, Siyeop Jin, Pengfei Kim, Sekeun Tivnan, Matthew Oh, Yujin Meng, Runqi Chen, Ling Lyu, Zhiliang Wu, Dufan Guo, Ning Li, Xiang Li, Quanzheng |
| contents | Recent advances in representation learning often rely on holistic embeddings that entangle multiple semantic components, limiting interpretability and generalization. These issues are especially critical in medical imaging, where downstream tasks depend on anatomically interpretable features. To address these limitations, we propose an Organ-Wise Tokenization (OWT) framework with a Token Group-based Reconstruction (TGR) training paradigm. Unlike conventional approaches, OWT explicitly disentangles an image into separable token groups, each corresponding to a distinct organ or semantic entity. Our design ensures each token group encapsulates organ-specific information, boosting interpretability, generalization, and efficiency while enabling fine-grained control for targeted clinical applications. Experiments on CT and MRI datasets demonstrate OWT's power: it not only achieves strong performance on standard tasks like image reconstruction and segmentation, but also unlocks novel, high-impact clinical capabilities including organ-specific tumor identification, organ-level retrieval and semantic-level generation, without requiring any additional training. These findings underscore the potential of OWT as a foundational framework for semantically disentangled representation learning, offering broad scalability and a new perspective on how representations can be leveraged. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_04899 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OWT: A Foundational Organ-Wise Tokenization Framework for Medical Imaging Song, Sifan Yoon, Siyeop Jin, Pengfei Kim, Sekeun Tivnan, Matthew Oh, Yujin Meng, Runqi Chen, Ling Lyu, Zhiliang Wu, Dufan Guo, Ning Li, Xiang Li, Quanzheng Computer Vision and Pattern Recognition Recent advances in representation learning often rely on holistic embeddings that entangle multiple semantic components, limiting interpretability and generalization. These issues are especially critical in medical imaging, where downstream tasks depend on anatomically interpretable features. To address these limitations, we propose an Organ-Wise Tokenization (OWT) framework with a Token Group-based Reconstruction (TGR) training paradigm. Unlike conventional approaches, OWT explicitly disentangles an image into separable token groups, each corresponding to a distinct organ or semantic entity. Our design ensures each token group encapsulates organ-specific information, boosting interpretability, generalization, and efficiency while enabling fine-grained control for targeted clinical applications. Experiments on CT and MRI datasets demonstrate OWT's power: it not only achieves strong performance on standard tasks like image reconstruction and segmentation, but also unlocks novel, high-impact clinical capabilities including organ-specific tumor identification, organ-level retrieval and semantic-level generation, without requiring any additional training. These findings underscore the potential of OWT as a foundational framework for semantically disentangled representation learning, offering broad scalability and a new perspective on how representations can be leveraged. |
| title | OWT: A Foundational Organ-Wise Tokenization Framework for Medical Imaging |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.04899 |