用多模态大模型实现新生儿脑龄精准预测与可解释说明
Accurate and Interpretable Postmenstrual Age Prediction via Multimodal Large Language Model
- 基于大模型指令微调与低秩适配，融合脑部影像特征进行预测
- 预测误差95%置信区间为0.78至1.52周，精度高且稳定
- 生成临床可理解的发育特征解释，适合医生辅助决策
准确估计扫描时的产后月龄（PMA）对评估新生儿发育与健康至关重要。尽管深度学习模型在从脑部MRI预测PMA方面已取得高精度，但通常作为黑箱运行，临床决策支持中透明度和可解释性有限。本文通过适配多模态大语言模型（MLLM），同时实现高精度的PMA预测与临床相关解释生成，解决准确性与可解释性的双重挑战。我们采用参数高效微调（PEFT）策略，结合指令微调与低秩适配（LoRA），对Qwen2.5-VL-7B模型进行训练，输入为来自新生儿MRI的四张二维皮层投影图。通过训练与推理使用不同提示，模型在训练中完成回归任务，在推理中生成基于发育特征的可解释输出。微调后模型达到0.78至1.52周的95%置信区间预测误差，显著提升产前神经科学中AI系统的透明性与可信度。
原文摘要 · Abstract (English)
Accurate estimation of postmenstrual age (PMA) at scan is crucial for assessing neonatal development and health. While deep learning models have achieved high accuracy in predicting PMA from brain MRI, they often function as black boxes, offering limited transparency and interpretability in clinical decision support. In this work, we address the dual challenge of accuracy and interpretability by adapting a multimodal large language model (MLLM) to perform both precise PMA prediction and clinically relevant explanation generation. We introduce a parameter-efficient fine-tuning (PEFT) strategy using instruction tuning and Low-Rank Adaptation (LoRA) applied to the Qwen2.5-VL-7B model. The model is trained on four 2D cortical surface projection maps derived from neonatal MRI scans. By employing distinct prompts for training and inference, our approach enables the MLLM to handle a regression task during training and generate clinically relevant explanations during inference. The fine-tuned model achieves a low prediction error with a 95 percent confidence interval of 0.78 to 1.52 weeks, while producing interpretable outputs grounded in developmental features, marking a significant step toward transparent and trustworthy AI systems in perinatal neuroscience.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。