# COME: Dual Structure-Semantic Learning with Collaborative MoE for Universal Lesion Detection Across Heterogeneous Ultrasound Datasets

arXiv: https://arxiv.org/abs/2508.09886 · HTML: https://mlsanity.com/paper/2508.09886/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Medical and biomedical MoE, one of 12 directions in Mixture-of-experts.
- Builds on 31 of its 52 references that are in the map.
- First posted on arXiv 13 Aug 2025.

## Placed in

- Mixture-of-experts / [Medical and biomedical MoE](https://mlsanity.com/moe/medical-and-biomedical-moe/)

## Builds on (most cited first, 30 of 31)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs](https://mlsanity.com/paper/2303.00915/) (2023)
- [YOLOv10: Real-Time End-to-End Object Detection](https://mlsanity.com/paper/2405.14458/) (2024)
- [Tutel: Adaptive Mixture-of-Experts at Scale](https://mlsanity.com/paper/2206.03382/) (2022)
- [Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters](https://mlsanity.com/paper/2403.11549/) (2024)
- [RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths](https://mlsanity.com/paper/2305.18295/) (2023)
- [Foundation Model for Endoscopy Video Analysis via Large-scale Self-supervised Pre-train](https://mlsanity.com/paper/2306.16741/) (2023)
- [Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Images](https://mlsanity.com/paper/2403.12570/) (2024)
- [USFM: A Universal Ultrasound Foundation Model Generalized to Tasks and Organs towards Label Efficient Image Analysis](https://mlsanity.com/paper/2401.00153/) (2023)
- [LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching](https://mlsanity.com/paper/2306.11925/) (2023)
- [MedCLIP-SAMv2: Towards Universal Text-Driven Medical Image Segmentation](https://mlsanity.com/paper/2409.19483/) (2024)
- [One for All: Toward Unified Foundation Models for Earth Vision](https://mlsanity.com/paper/2401.07527/) (2024)
- [A New Dataset and A Baseline Model for Breast Lesion Detection in Ultrasound Videos](https://mlsanity.com/paper/2207.00141/) (2022)
- [DaTaSeg: Taming a Universal Multi-Dataset Multi-Task Segmentation Model](https://mlsanity.com/paper/2306.01736/) (2023)
- [HyperMoE: Towards Better Mixture of Experts via Transferring Among Experts](https://mlsanity.com/paper/2402.12656/) (2024)
- [MAPSeg: Unified Unsupervised Domain Adaptation for Heterogeneous Medical Image Segmentation Based on 3D Masked Autoencoding and Pseudo-Labeling](https://mlsanity.com/paper/2303.09373/) (2023)
- [General surgery vision transformer: A video pre-trained foundation model for general surgery](https://mlsanity.com/paper/2403.05949/) (2024)
- [Exploring the Potential of Large Foundation Models for Open-Vocabulary HOI Detection](https://mlsanity.com/paper/2404.06194/) (2024)
- [UltraSam: A Foundation Model for Ultrasound using Large Open-Access Segmentation Datasets](https://mlsanity.com/paper/2411.16222/) (2024)
- [DAMEX: Dataset-aware Mixture-of-Experts for visual understanding of mixture-of-datasets](https://mlsanity.com/paper/2311.04894/) (2023)
- [Ultrasound Report Generation with Cross-Modality Feature Alignment via Unsupervised Guidance](https://mlsanity.com/paper/2406.00644/) (2024)
- [PathoDuet: Foundation Models for Pathological Slide Analysis of H&E and IHC Stains](https://mlsanity.com/paper/2312.09894/) (2023)
- [Constructing and Exploring Intermediate Domains in Mixed Domain Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/2404.08951/) (2024)
- [Versatile Medical Image Segmentation Learned from Multi-Source Datasets via Model Self-Disambiguation](https://mlsanity.com/paper/2311.10696/) (2023)
- [Ultrasound Image-to-Video Synthesis via Latent Dynamic Diffusion Models](https://mlsanity.com/paper/2503.14966/) (2025)
- [MedUniSeg: 2D and 3D Medical Image Segmentation via a Prompt-driven Universal Model](https://mlsanity.com/paper/2410.05905/) (2024)
- [Uni2Det: Unified and Universal Framework for Prompt-Guided Multi-dataset 3D Detection](https://mlsanity.com/paper/2409.20558/) (2024)

## Built on by (most cited first, 1 of 1)

- [M-IDoL: Information Decomposition for Modality-Specific and Diverse Representation Learning in Medical Foundation Model](https://mlsanity.com/paper/2604.08936/) (2026)

## Abstract (arXiv)

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/.