AI RESEARCH
LoGSAM: Parameter-Efficient Cross-Modal Grounding for MRI Segmentation
arXiv CS.CV
•
ArXi:2603.17576v1 Announce Type: new Precise localization and delineation of brain tumors using Magnetic Resonance Imaging (MRI) are essential for planning therapy and guiding surgical decisions. However, most existing approaches rely on task-specific supervised models and are constrained by the limited availability of annotated data. To address this, we propose LoGSAM, a parameter-efficient, detection-driven framework that transforms radiologist dictation into text prompts for foundation-model-based localization and segmentation.