Integrating Vision-Language Models and Multi-Agent LLM Systems for Clinical Reasoning in Brain Tumor Analysis

Domain:

healthcare

Record type:

paper

Creator:

Hou

Editor:

Cen

Publisher:

OSF

Host:

This preprint presents a multi-agent clinical reasoning system for brain tumor MRI analysis, integrating MedViT visual embeddings, FAISS similarity retrieval, U-Net segmentation, Grad-CAM explainability, and LLaMA 3 70B report synthesis within a LangChain pipeline. Evaluated on BraTS 2020. Developed at ESPRIT University, Tunisia.

Tasks

computer vision

Lightweight Deep Learning Models for Brain Tumor Classification

Differentiating brain tumours by MRI using computer algorithms remains a huge challenge in clinical

MaRVL: Multicultural Reasoning over Vision and Language

Multicultural Reasoning over Vision and <

184 Evaluating Reasoning-Tuned Large Language Models for Clinical Decision-Making in Spine Surgery

Abstract Large language models (LLMs) such as OpenAI o1 and DeepSeek-R1 are desi

Multi-Agent Systems Requirements Analysis for Patient-centered Healthcare Consultancy Service

Agents are currently being discussed in nearly every domain of science and engineering. Through the

Harnessing Machine Learning and Multi Agent Systems for Health Crisis Analysis in North Africa

The COVID-19 pandemic has presented a significant global health challenge, including in Morocco. The

TIBSTC-CoT: A Multi-Domain Instruction Dataset for Chain-of-Thought Reasoning in Language Models

To address the severe data scarcity in Tibetan, a low-resource language spoken by over six million p