Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.09886 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912536250548224 |
|---|---|
| author | Chen, Lingyu Zeng, Yawen Wang, Yue Wan, Peng Ning, Guo-chen Liao, Hongen Zhang, Daoqiang Chen, Fang |
| author_facet | Chen, Lingyu Zeng, Yawen Wang, Yue Wan, Peng Ning, Guo-chen Liao, Hongen Zhang, Daoqiang Chen, Fang |
| contents | Conventional single-dataset training often fails with new data distributions, especially in ultrasound (US) image analysis due to limited data, acoustic shadows, and speckle noise. Therefore, constructing a universal framework for multi-heterogeneous US datasets is imperative. However, a key challenge arises: how to effectively mitigate inter-dataset interference while preserving dataset-specific discriminative features for robust downstream task? Previous approaches utilize either a single source-specific decoder or a domain adaptation strategy, but these methods experienced a decline in performance when applied to other domains. Considering this, we propose a Universal Collaborative Mixture of Heterogeneous Source-Specific Experts (COME). Specifically, COME establishes dual structure-semantic shared experts that create a universal representation space and then collaborate with source-specific experts to extract discriminative features through providing complementary features. This design enables robust generalization by leveraging cross-datasets experience distributions and providing universal US priors for small-batch or unseen data scenarios. Extensive experiments under three evaluation modes (single-dataset, intra-organ, and inter-organ integration datasets) demonstrate COME's superiority, achieving significant mean AP improvements over state-of-the-art methods. Our project is available at: https://universalcome.github.io/UniversalCOME/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_09886 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | COME: Dual Structure-Semantic Learning with Collaborative MoE for Universal Lesion Detection Across Heterogeneous Ultrasound Datasets Chen, Lingyu Zeng, Yawen Wang, Yue Wan, Peng Ning, Guo-chen Liao, Hongen Zhang, Daoqiang Chen, Fang Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Conventional single-dataset training often fails with new data distributions, especially in ultrasound (US) image analysis due to limited data, acoustic shadows, and speckle noise. Therefore, constructing a universal framework for multi-heterogeneous US datasets is imperative. However, a key challenge arises: how to effectively mitigate inter-dataset interference while preserving dataset-specific discriminative features for robust downstream task? Previous approaches utilize either a single source-specific decoder or a domain adaptation strategy, but these methods experienced a decline in performance when applied to other domains. Considering this, we propose a Universal Collaborative Mixture of Heterogeneous Source-Specific Experts (COME). Specifically, COME establishes dual structure-semantic shared experts that create a universal representation space and then collaborate with source-specific experts to extract discriminative features through providing complementary features. This design enables robust generalization by leveraging cross-datasets experience distributions and providing universal US priors for small-batch or unseen data scenarios. Extensive experiments under three evaluation modes (single-dataset, intra-organ, and inter-organ integration datasets) demonstrate COME's superiority, achieving significant mean AP improvements over state-of-the-art methods. Our project is available at: https://universalcome.github.io/UniversalCOME/. |
| title | COME: Dual Structure-Semantic Learning with Collaborative MoE for Universal Lesion Detection Across Heterogeneous Ultrasound Datasets |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2508.09886 |