用超图与提示学习提升阿尔茨海默病诊断准确率
PHGNN: A Novel Prompted Hypergraph Neural Network to Diagnose Alzheimer's Disease
- 构建超图捕捉多模态数据间高阶关系
- 在ADNI数据集上优于当前最优方法
- 适合医疗影像与临床数据融合研究者
阿尔茨海默病（AD）的精准诊断及轻度认知障碍（MCI）向痴呆转化的预判对早期干预至关重要。然而，现有跨模态方法面临输入数据异质性、模态交互探索不足、因患者脱落导致的数据缺失，以及受制于耗时昂贵的数据采集过程带来的样本量有限等挑战。本文提出一种新型提示式超图神经网络（PHGNN）框架，通过将超图学习与提示学习相结合，有效应对上述问题。超图可建模不同模态间的高阶关联，而借鉴自然语言处理领域的提示学习策略，使模型在小样本下仍具高效训练能力。在ADNI数据集上的大量实验表明，该模型在AD诊断和MCI转化预测任务中均超越现有最先进方法。
原文摘要 · Abstract (English)
The accurate diagnosis of Alzheimer's disease (AD) and prognosis of mild cognitive impairment (MCI) conversion are crucial for early intervention. However, existing multimodal methods face several challenges, from the heterogeneity of input data, to underexplored modality interactions, missing data due to patient dropouts, and limited data caused by the time-consuming and costly data collection process. In this paper, we propose a novel Prompted Hypergraph Neural Network (PHGNN) framework that addresses these limitations by integrating hypergraph based learning with prompt learning. Hypergraphs capture higher-order relationships between different modalities, while our prompt learning approach for hypergraphs, adapted from NLP, enables efficient training with limited data. Our model is validated through extensive experiments on the ADNI dataset, outperforming SOTA methods in both AD diagnosis and the prediction of MCI conversion.
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。