Article

Risk Aware Prompt-Guided CNN–LLM Framework for Brain MRI Diagnostic Report Generation

2026-08-25

Abstract excerpt

<title>Abstract</title> <p>Brain MRI report generation has emerged as a core task for AI-aided radiology, which could potentially fill the gap of low efficiency among radiologists in tumour diagnosis. Yet, current methods are often too weak to fully express the clinical variances in disease and anatomical regions, which results in repetitive genetic reports. To overcome such limitations, the proposed a risk-aware...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 82a2c730-8882-5684-8842-1b2368267f39
DOI: 10.21203/rs.3.rs-10802065/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Risk Aware Prompt-Guided CNN–LLM Framework for Brain MRI Diagnostic Report GenerationDOI 10.21203/rs.3.rs-10802065/v1Read

Automating Radiology Report Generation: A Systematic Review of Deep Learning MethodsSemantic proximity Read

MRG-R3: Retrieval-Reflection-Reward via Multimodal LLMs Advances Clinical Automated Medical Report GenerationSemantic proximity Read

Current Landscape of Automatic Radiology Report Generation with Deep Learning: An Exploratory Systematic ReviewSemantic proximity Read

Reinforced Visual Interaction Fusion Radiology Report GenerationSemantic proximity Read

A multi-agent system for spine MRI report generation from multi-sequence imagingSemantic proximity Read

SMILES Challenge 2025: Multitask Learning with Contrastive and Natural Language Generation for Enhanced Medical Image ClassificationSemantic proximity Read

Towards a Holistic Framework for Multimodal Large Language Models in Three-dimensional Brain CT Report GenerationSemantic proximity Read

Health system learning achieves generalist neuroimaging modelsSemantic proximity Read

A Clinically-Informed Framework for Evaluating Vision-Language Models in Radiology Report Generation: Taxonomy of Errors and Risk-Aware MetricSemantic proximity Read

Astra: a generalizable report generation foundation model for 3D computed tomographySemantic proximity Read

UPhAIR: A Hybrid Pipeline for Generating Understandable Post-hoc AI Reports in Glioma IDH Mutation Status PredictionSemantic proximity Read

A retrospective study of a Chinese vision-language large model for emergency 3D brain CT interpretationSemantic proximity Read