MedROV: Towards Real-Time Open-Vocabulary Detection Across Diverse Medical Imaging Modalities
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_ | 1866911286684549120 |
|---|---|
| author | Sheikh, Tooba Tehreem Lahoud, Jean Anwer, Rao Muhammad Khan, Fahad Shahbaz Khan, Salman Cholakkal, Hisham |
| author_facet | Sheikh, Tooba Tehreem Lahoud, Jean Anwer, Rao Muhammad Khan, Fahad Shahbaz Khan, Salman Cholakkal, Hisham |
| contents | Traditional object detection models in medical imaging operate within a closed-set paradigm, limiting their ability to detect objects of novel labels. Open-vocabulary object detection (OVOD) addresses this limitation but remains underexplored in medical imaging due to dataset scarcity and weak text-image alignment. To bridge this gap, we introduce MedROV, the first Real-time Open Vocabulary detection model for medical imaging. To enable open-vocabulary learning, we curate a large-scale dataset, Omnis, with 600K detection samples across nine imaging modalities and introduce a pseudo-labeling strategy to handle missing annotations from multi-source datasets. Additionally, we enhance generalization by incorporating knowledge from a large pre-trained foundation model. By leveraging contrastive learning and cross-modal representations, MedROV effectively detects both known and novel structures. Experimental results demonstrate that MedROV outperforms the previous state-of-the-art foundation model for medical image detection with an average absolute improvement of 40 mAP50, and surpasses closed-set detectors by more than 3 mAP50, while running at 70 FPS, setting a new benchmark in medical detection. Our source code, dataset, and trained model are available at https://github.com/toobatehreem/MedROV. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_20650 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MedROV: Towards Real-Time Open-Vocabulary Detection Across Diverse Medical Imaging Modalities Sheikh, Tooba Tehreem Lahoud, Jean Anwer, Rao Muhammad Khan, Fahad Shahbaz Khan, Salman Cholakkal, Hisham Computer Vision and Pattern Recognition Artificial Intelligence Traditional object detection models in medical imaging operate within a closed-set paradigm, limiting their ability to detect objects of novel labels. Open-vocabulary object detection (OVOD) addresses this limitation but remains underexplored in medical imaging due to dataset scarcity and weak text-image alignment. To bridge this gap, we introduce MedROV, the first Real-time Open Vocabulary detection model for medical imaging. To enable open-vocabulary learning, we curate a large-scale dataset, Omnis, with 600K detection samples across nine imaging modalities and introduce a pseudo-labeling strategy to handle missing annotations from multi-source datasets. Additionally, we enhance generalization by incorporating knowledge from a large pre-trained foundation model. By leveraging contrastive learning and cross-modal representations, MedROV effectively detects both known and novel structures. Experimental results demonstrate that MedROV outperforms the previous state-of-the-art foundation model for medical image detection with an average absolute improvement of 40 mAP50, and surpasses closed-set detectors by more than 3 mAP50, while running at 70 FPS, setting a new benchmark in medical detection. Our source code, dataset, and trained model are available at https://github.com/toobatehreem/MedROV. |
| title | MedROV: Towards Real-Time Open-Vocabulary Detection Across Diverse Medical Imaging Modalities |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2511.20650 |