Paper
LoGSAM: Parameter-Efficient Cross-Modal Grounding for MRI Segmentation
Authors
Mohammad Robaitul Islam Bhuiyan, Sheethal Bhat, Melika Qahqaie, Tri-Thien Nguyen, Paula Andrea Pérez Toro, Tomas Arias Vergara, Andreas Maier
Abstract
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. Radiologist speech is first transcribed and translated using a pretrained Whisper ASR model, followed by negation-aware clinical NLP to extract tumor-specific textual prompts. These prompts guide text-conditioned tumor localization via a LoRA-adapted vision-language detection model, Grounding DINO (GDINO). The LoRA adaptation updates using 5% of the model parameters, thereby enabling computationally efficient domain adaptation while preserving pretrained cross-modal knowledge. The predicted bounding boxes are used as prompts for MedSAM to generate pixel-level tumor masks without any additional fine-tuning. Conditioning the frozen MedSAM on LoGSAM-derived priors yields a state-of-the-art dice score of 80.32% on BRISC 2025. In addition, we evaluate the full pipeline using German dictations from a board-certified radiologist on 12 unseen MRI scans, achieving 91.7% case-level accuracy. These results highlight the feasibility of constructing a modular, speech-to-segmentation pipeline by intelligently leveraging pretrained foundation models with minimal parameter updates.
Metadata
Related papers
Vibe Coding XR: Accelerating AI + XR Prototyping with XR Blocks and Gemini
Ruofei Du, Benjamin Hersh, David Li, Nels Numan, Xun Qian, Yanhe Chen, Zhongy... • 2026-03-25
Comparing Developer and LLM Biases in Code Evaluation
Aditya Mittal, Ryan Shar, Zichu Wu, Shyam Agarwal, Tongshuang Wu, Chris Donah... • 2026-03-25
The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
Biplab Pal, Santanu Bhattacharya • 2026-03-25
Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
Saahil Mathur, Ryan David Rittner, Vedant Ajit Thakur, Daniel Stuart Schiff, ... • 2026-03-25
MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
Zhuo Li, Yupeng Zhang, Pengyu Cheng, Jiajun Song, Mengyu Zhou, Hao Li, Shujie... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.17576v1</id>\n <title>LoGSAM: Parameter-Efficient Cross-Modal Grounding for MRI Segmentation</title>\n <updated>2026-03-18T10:33:32Z</updated>\n <link href='https://arxiv.org/abs/2603.17576v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.17576v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>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. Radiologist speech is first transcribed and translated using a pretrained Whisper ASR model, followed by negation-aware clinical NLP to extract tumor-specific textual prompts. These prompts guide text-conditioned tumor localization via a LoRA-adapted vision-language detection model, Grounding DINO (GDINO). The LoRA adaptation updates using 5% of the model parameters, thereby enabling computationally efficient domain adaptation while preserving pretrained cross-modal knowledge. The predicted bounding boxes are used as prompts for MedSAM to generate pixel-level tumor masks without any additional fine-tuning. Conditioning the frozen MedSAM on LoGSAM-derived priors yields a state-of-the-art dice score of 80.32% on BRISC 2025. In addition, we evaluate the full pipeline using German dictations from a board-certified radiologist on 12 unseen MRI scans, achieving 91.7% case-level accuracy. These results highlight the feasibility of constructing a modular, speech-to-segmentation pipeline by intelligently leveraging pretrained foundation models with minimal parameter updates.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n <published>2026-03-18T10:33:32Z</published>\n <arxiv:comment>10 pages, 3 figures</arxiv:comment>\n <arxiv:primary_category term='cs.CV'/>\n <author>\n <name>Mohammad Robaitul Islam Bhuiyan</name>\n </author>\n <author>\n <name>Sheethal Bhat</name>\n </author>\n <author>\n <name>Melika Qahqaie</name>\n </author>\n <author>\n <name>Tri-Thien Nguyen</name>\n </author>\n <author>\n <name>Paula Andrea Pérez Toro</name>\n </author>\n <author>\n <name>Tomas Arias Vergara</name>\n </author>\n <author>\n <name>Andreas Maier</name>\n </author>\n </entry>"
}