PRS-Med: Position Reasoning Segmentation in Medical Imaging
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_ | 1866912989465018368 |
|---|---|
| author | Trinh, Quoc-Huy Nguyen, Minh-Van Zeng, Jun Jha, Debesh Bagci, Ulas |
| author_facet | Trinh, Quoc-Huy Nguyen, Minh-Van Zeng, Jun Jha, Debesh Bagci, Ulas |
| contents | Prompt-based medical image segmentation has rapidly emerged, yet existing methods rely on explicit prompts like bounding boxes and struggle to reason about the spatial relationships essential for clinical diagnosis. While general-domain models attempt complex coordinate regression, these approaches often lack the structured reliability required for medical applications. In this work, we introduce PRS-Med, a unified framework that adopts an elegant, clinical-first approach to position reasoning segmentation. By utilizing a medical vision-language model integrated with a segmentation decoder, PRS-Med mimics the structured "search patterns" used by radiologists to identify pathologies within specific anatomical zones. To support this robust reasoning, we present the Medical Position Reasoning Segmentation (PosMed) dataset, comprising 116,000 expert-validated, spatially grounded question-answer pairs across six imaging modalities. Unlike previous brittle attempts at spatial reasoning, PosMed leverages a scalable, deterministic pipeline validated by board-certified radiologists to ensure clinical accuracy. Extensive experiments demonstrate that our zone-based reasoning not only improves segmentation accuracy (mean Dice improvements up to +31.2\%) but also provides a high-confidence interpretability layer that outperforms state-of-the-art complex reasoning models. By prioritizing functional reliability over unnecessary technical complexity, PRS-Med offers a practical and scalable baseline for the next generation of intelligent medical assistants. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_11872 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PRS-Med: Position Reasoning Segmentation in Medical Imaging Trinh, Quoc-Huy Nguyen, Minh-Van Zeng, Jun Jha, Debesh Bagci, Ulas Computer Vision and Pattern Recognition Prompt-based medical image segmentation has rapidly emerged, yet existing methods rely on explicit prompts like bounding boxes and struggle to reason about the spatial relationships essential for clinical diagnosis. While general-domain models attempt complex coordinate regression, these approaches often lack the structured reliability required for medical applications. In this work, we introduce PRS-Med, a unified framework that adopts an elegant, clinical-first approach to position reasoning segmentation. By utilizing a medical vision-language model integrated with a segmentation decoder, PRS-Med mimics the structured "search patterns" used by radiologists to identify pathologies within specific anatomical zones. To support this robust reasoning, we present the Medical Position Reasoning Segmentation (PosMed) dataset, comprising 116,000 expert-validated, spatially grounded question-answer pairs across six imaging modalities. Unlike previous brittle attempts at spatial reasoning, PosMed leverages a scalable, deterministic pipeline validated by board-certified radiologists to ensure clinical accuracy. Extensive experiments demonstrate that our zone-based reasoning not only improves segmentation accuracy (mean Dice improvements up to +31.2\%) but also provides a high-confidence interpretability layer that outperforms state-of-the-art complex reasoning models. By prioritizing functional reliability over unnecessary technical complexity, PRS-Med offers a practical and scalable baseline for the next generation of intelligent medical assistants. |
| title | PRS-Med: Position Reasoning Segmentation in Medical Imaging |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.11872 |