利用高阶交互信息提升脑疾病诊断准确率
MvHo-IB: Multi-View Higher-Order Information Bottleneck for Brain Disorder Diagnosis
- 结合信息论与瑞尼熵估计，提取脑影像中的高阶交互特征
- 在三个基准数据集上表现优于现有方法，显著提升诊断精度
- 适合从事医学影像分析与脑疾病智能诊断的研究者
近期研究表明，建模功能磁共振成像（fMRI）数据中的高阶交互（HOIs）可提升机器学习系统的诊断准确性。然而，有效提取和利用HOIs仍是重大挑战。本文提出MvHo-IB，一种新型多视图学习框架，同时整合成对交互与高阶交互进行诊断决策，并自动压缩与任务无关的冗余信息。MvHo-IB引入三项关键创新：(1) 基于信息论的O-信息与矩阵型瑞尼α阶熵估计器相结合，量化并提取HOIs；(2) 专为脑影像设计的Brain3DCNN编码器，高效利用这些交互特征；(3) 新型多视图信息瓶颈目标函数，增强表征学习能力。在三个基准fMRI数据集上的实验表明，MvHo-IB达到当前最优性能，显著优于以往方法，包括近期基于超图的技术。代码已公开于https://github.com/zky04/MvHo-IB。
原文摘要 · Abstract (English)
Recent evidence suggests that modeling higher-order interactions (HOIs) in functional magnetic resonance imaging (fMRI) data can enhance the diagnostic accuracy of machine learning systems. However, effectively extracting and utilizing HOIs remains a significant challenge. In this work, we propose MvHo-IB, a novel multi-view learning framework that integrates both pairwise interactions and HOIs for diagnostic decision-making, while automatically compressing task-irrelevant redundant information. MvHo-IB introduces several key innovations: (1) a principled method that combines O-information from information theory with a matrix-based Renyi alpha-order entropy estimator to quantify and extract HOIs, (2) a purpose-built Brain3DCNN encoder to effectively utilize these interactions, and (3) a new multi-view learning information bottleneck objective to enhance representation learning. Experiments on three benchmark fMRI datasets demonstrate that MvHo-IB achieves state-of-the-art performance, significantly outperforming previous methods, including recent hypergraph-based techniques. The implementation of MvHo-IB is available at https://github.com/zky04/MvHo-IB.
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。