PRS-Med: Position Reasoning Segmentation in Medical Imaging

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Trinh, Quoc-Huy, Nguyen, Minh-Van, Zeng, Jun, Jha, Debesh, Bagci, Ulas
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