# MediSee: Reasoning-based Pixel-level Perception in Medical Images Source: [MediSee: Reasoning-based Pixel-level Perception in Medical Images]() Collection index: [llms.txt]() Data updated: 2025-10-26T04:34:18.624Z Authors: Qinyue Tong, Ziqian Lu, Jun Liu, Yangming Zheng, Zheming Lu Published: 2025-04-15T09:28:53.000Z ## Abstract Despite remarkable advancements in pixel-level medical image perception, existing methods are either limited to specific tasks or heavily rely on accurate bounding boxes or text labels as input prompts. However, the medical knowledge required for input is a huge obstacle for general public, which greatly reduces the universality of these methods. Compared with these domain-specialized auxiliary information, general users tend to rely on oral queries that require logical reasoning. In this paper, we introduce a novel medical vision task: Medical Reasoning Segmentation and Detection (MedSD), which aims to comprehend implicit queries about medical images and generate the corresponding segmentation mask and bounding box for the target object. To accomplish this task, we first introduce a Multi-perspective, Logic-driven Medical Reasoning Segmentation and Detection (MLMR-SD) dataset, which encompasses a substantial collection of medical entity targets along with their corresponding reasoning. Furthermore, we propose MediSee, an effective baseline model designed for medical reasoning segmentation and detection. The experimental results indicate that the proposed method can effectively address MedSD with implicit colloquial queries and outperform traditional medical referring segmentation methods. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Medical Referring Segmentation on MR-MedSeg (val)](): Medical Referring Segmentation; MR-MedSeg (val); Dice Score: 61.2. - [Medical Reasoning Segmentation on MR-MedSeg regular case (test)](): Medical Reasoning Segmentation; MR-MedSeg regular case (test); Dice: 45.6. - [Medical Reasoning Segmentation on MR-MedSeg hard case (test)](): Medical Reasoning Segmentation; MR-MedSeg hard case (test); Dice: 45.1. - [Lesion Segmentation on ComLesion-14K 1.0 (test)](): Lesion Segmentation; ComLesion-14K 1.0 (test); Mean Dice (mDice): 11.07. - [Medical Interaction Segmentation on MR-MedSeg (val)](): Medical Interaction Segmentation; MR-MedSeg (val); Dice: 43. ## Original sources and implementation [Original paper]() [PDF]()