MediRound: Multi-Round Entity-Level Reasoning Segmentation in Medical Images

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tong, Qinyue, Lu, Ziqian, Liu, Jun, Zuo, Rui, Lu, Zheming, Jin, Yueming
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917330711216128
author Tong, Qinyue
Lu, Ziqian
Liu, Jun
Zuo, Rui
Lu, Zheming
Jin, Yueming
author_facet Tong, Qinyue
Lu, Ziqian
Liu, Jun
Zuo, Rui
Lu, Zheming
Jin, Yueming
contents Despite recent progress in text-prompt-based medical image segmentation, these methods are limited to single-round dialogues and fail to support multi-round reasoning, which is important for medical education scenarios. In this work, we introduce Multi-Round Entity-Level Medical Reasoning Segmentation (MEMR-Seg), a new task that requires generating segmentation masks through multi-round queries with entity-level reasoning, helping learners progressively develop their understanding of medical knowledge. To support this task, we construct MR-MedSeg, a large-scale dataset of 177K multi-round medical segmentation dialogues, featuring entity-based reasoning across rounds. Furthermore, we propose MediRound, an effective baseline model designed for multi-round medical reasoning segmentation. To mitigate the inherent error propagation within the chain-like pipeline of multi-round segmentation, we introduce a lightweight yet effective Judgment & Correction Mechanism during model inference. Experimental results demonstrate that our method effectively addresses the MEMR-Seg task and outperforms conventional medical referring segmentation methods. The project is available at https://github.com/Edisonhimself/MediRound.
format Preprint
id arxiv_https___arxiv_org_abs_2511_12110
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MediRound: Multi-Round Entity-Level Reasoning Segmentation in Medical Images
Tong, Qinyue
Lu, Ziqian
Liu, Jun
Zuo, Rui
Lu, Zheming
Jin, Yueming
Computer Vision and Pattern Recognition
Artificial Intelligence
Despite recent progress in text-prompt-based medical image segmentation, these methods are limited to single-round dialogues and fail to support multi-round reasoning, which is important for medical education scenarios. In this work, we introduce Multi-Round Entity-Level Medical Reasoning Segmentation (MEMR-Seg), a new task that requires generating segmentation masks through multi-round queries with entity-level reasoning, helping learners progressively develop their understanding of medical knowledge. To support this task, we construct MR-MedSeg, a large-scale dataset of 177K multi-round medical segmentation dialogues, featuring entity-based reasoning across rounds. Furthermore, we propose MediRound, an effective baseline model designed for multi-round medical reasoning segmentation. To mitigate the inherent error propagation within the chain-like pipeline of multi-round segmentation, we introduce a lightweight yet effective Judgment & Correction Mechanism during model inference. Experimental results demonstrate that our method effectively addresses the MEMR-Seg task and outperforms conventional medical referring segmentation methods. The project is available at https://github.com/Edisonhimself/MediRound.
title MediRound: Multi-Round Entity-Level Reasoning Segmentation in Medical Images
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2511.12110