Universal Medical Image Representation Learning with Compositional Decoders
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_ | 1866909338148274176 |
|---|---|
| author | Wang, Kaini Yang, Ling Zhou, Siping Zhou, Guangquan Zhang, Wentao Cui, Bin Li, Shuo |
| author_facet | Wang, Kaini Yang, Ling Zhou, Siping Zhou, Guangquan Zhang, Wentao Cui, Bin Li, Shuo |
| contents | Visual-language models have advanced the development of universal models, yet their application in medical imaging remains constrained by specific functional requirements and the limited data. Current general-purpose models are typically designed with task-specific branches and heads, which restricts the shared feature space and the flexibility of model. To address these challenges, we have developed a decomposed-composed universal medical imaging paradigm (UniMed) that supports tasks at all levels. To this end, we first propose a decomposed decoder that can predict two types of outputs -- pixel and semantic, based on a defined input queue. Additionally, we introduce a composed decoder that unifies the input and output spaces and standardizes task annotations across different levels into a discrete token format. The coupled design of these two components enables the model to flexibly combine tasks and mutual benefits. Moreover, our joint representation learning strategy skilfully leverages large amounts of unlabeled data and unsupervised loss, achieving efficient one-stage pretraining for more robust performance. Experimental results show that UniMed achieves state-of-the-art performance on eight datasets across all three tasks and exhibits strong zero-shot and 100-shot transferability. We will release the code and trained models upon the paper's acceptance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_19890 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Universal Medical Image Representation Learning with Compositional Decoders Wang, Kaini Yang, Ling Zhou, Siping Zhou, Guangquan Zhang, Wentao Cui, Bin Li, Shuo Computer Vision and Pattern Recognition Visual-language models have advanced the development of universal models, yet their application in medical imaging remains constrained by specific functional requirements and the limited data. Current general-purpose models are typically designed with task-specific branches and heads, which restricts the shared feature space and the flexibility of model. To address these challenges, we have developed a decomposed-composed universal medical imaging paradigm (UniMed) that supports tasks at all levels. To this end, we first propose a decomposed decoder that can predict two types of outputs -- pixel and semantic, based on a defined input queue. Additionally, we introduce a composed decoder that unifies the input and output spaces and standardizes task annotations across different levels into a discrete token format. The coupled design of these two components enables the model to flexibly combine tasks and mutual benefits. Moreover, our joint representation learning strategy skilfully leverages large amounts of unlabeled data and unsupervised loss, achieving efficient one-stage pretraining for more robust performance. Experimental results show that UniMed achieves state-of-the-art performance on eight datasets across all three tasks and exhibits strong zero-shot and 100-shot transferability. We will release the code and trained models upon the paper's acceptance. |
| title | Universal Medical Image Representation Learning with Compositional Decoders |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.19890 |