MM-NeuroOnco: A Multimodal Benchmark and Instruction Dataset for MRI-Based Brain Tumor Diagnosis

TL;DR

This paper introduces MM-NeuroOnco, a comprehensive multimodal MRI dataset and benchmark for brain tumor diagnosis, enabling improved diagnostic reasoning models through rich annotations and evaluation tools.

Contribution

The paper presents a large-scale multimodal MRI dataset with semantic annotations and a benchmark for evaluating diagnostic reasoning models, along with a new fine-tuned model that improves accuracy.

Findings

Strong baseline models perform poorly on diagnostic questions.

The proposed NeuroOnco-GPT improves diagnostic accuracy by 27%.

The dataset facilitates research in clinically grounded multimodal diagnosis.

Abstract

Accurate brain tumor diagnosis requires models to not only detect lesions but also generate clinically interpretable reasoning grounded in imaging manifestations, yet existing public datasets remain limited in annotation richness and diagnostic semantics. To bridge this gap, we introduce MM-NeuroOnco, a large-scale multimodal benchmark and instruction-tuning dataset for brain tumor MRI understanding, consisting of 24,726 MRI slices from 20 data sources paired with approximately 200,000 semantically enriched multimodal instructions spanning diverse tumor subtypes and imaging modalities. To mitigate the scarcity and high cost of diagnostic semantic annotations, we develop a multi-model collaborative pipeline for automated medical information completion and quality control, enabling the generation of diagnosis-related semantics beyond mask-only annotations. Building upon this dataset, we further construct MM-NeuroOnco-Bench, a manually annotated evaluation benchmark with a rejection-aware setting to reduce biases inherent in closed-ended question formats. Evaluation across ten representative models shows that even the strongest baseline, Gemini 3 Flash, achieves only 41.88% accuracy on diagnosis-related questions, highlighting the substantial challenges of multimodal brain tumor diagnostic understanding. Leveraging MM-NeuroOnco, we further propose NeuroOnco-GPT, which achieves a 27% absolute accuracy improvement on diagnostic questions following fine-tuning. This result demonstrates the effectiveness of our dataset and benchmark in advancing clinically grounded multimodal diagnostic reasoning. Code and dataset are publicly available at: https://github.com/gfnnnb/MM-NeuroOnco