arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.24846cs.CVcs.AIcs.LG
收藏

NeuroVLM-Bench:评估用于神经系统疾病临床推理的视觉增强大语言模型

NeuroVLM-Bench: Evaluation of Vision-Enabled Large Language Models for Clinical Reasoning in Neurological Disorders

Katarina Trojachanec Dineva, Stefan Andonov, Ilinka Ivanoska, Ivan Kitanovski, Sasho Gramatikov, Tamara Kostova, Monika Simjanoska Misheva, Kostadin Mishev

AI总结:

本文评估了视觉增强大语言模型在神经疾病临床推理中的性能,通过多模态模型在MRI和CT数据集上进行基准测试,发现影像属性基本解决,但诊断推理仍具挑战性。

摘要:

近期多模态大语言模型的进步为基于图像的决策支持提供了新可能。然而,其在神经影像中的可靠性及操作权衡尚不充分。本文提出了一个全面的基准测试研究,利用 curated MRI 和 CT 数据集,涵盖多发性硬化症、中风、脑肿瘤等疾病。模型需同时生成多个输出,包括诊断、亚型、影像模态、专用序列和解剖平面。性能评估涵盖四个方向:判别分类、校准、结构化输出有效性及计算效率。多阶段框架确保公平比较并控制选择偏差。在二十种前沿多模态模型中,结果显示影像属性基本解决,但诊断推理尤其是亚型预测仍具挑战性。肿瘤分类最为可靠,中风中等可解,而多发性硬化症和罕见异常仍难。少样本提示提升部分模型性能,但增加 token 使用、延迟和成本。Gemini-2.5-Pro 和 GPT-5-Chat 在整体诊断性能最强,Gemini-2.5-Flash 提供最佳效率性能权衡。在开源架构中,MedGemma-1.5-4B 表现最突出,少样本提示下接近部分专有模型的零样本性能,同时保持完美结构化输出。这些发现为性能、可靠性及效率权衡提供实用见解,支持多模态 LLM 在神经影像中的标准化评估。

英文摘要:

Recent advances in multimodal large language models enable new possibilities for image-based decision support. However, their reliability and operational trade-offs in neuroimaging remain insufficiently understood. We present a comprehensive benchmarking study of vision-enabled large language models for 2D neuroimaging using curated MRI and CT datasets covering multiple sclerosis, stroke, brain tumors, other abnormalities, and normal controls. Models are required to generate multiple outputs simultaneously, including diagnosis, diagnosis subtype, imaging modality, specialized sequence, and anatomical plane. Performance is evaluated across four directions: discriminative classification with abstention, calibration, structured-output validity, and computational efficiency. A multi-phase framework ensures fair comparison while controlling for selection bias. Across twenty frontier multimodal models, the results show that technical imaging attributes such as modality and plane are nearly solved, whereas diagnostic reasoning, especially subtype prediction, remains challenging. Tumor classification emerges as the most reliable task, stroke is moderately solvable, while multiple sclerosis and rare abnormalities remain difficult. Few-shot prompting improves performance for several models but increases token usage, latency, and cost. Gemini-2.5-Pro and GPT-5-Chat achieve the strongest overall diagnostic performance, while Gemini-2.5-Flash offers the best efficiency-performance trade-off. Among open-weight architectures, MedGemma-1.5-4B demonstrates the most promising results, as under few-shot prompting, it approaches the zero-shot performance of several proprietary models, while maintaining perfect structured output. These findings provide practical insights into performance, reliability, and efficiency trade-offs, supporting standardized evaluation of multimodal LLMs in neuroimaging.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑