Genetic InfoMax: Exploring Mutual Information Maximization in High-Dimensional Imaging Genetics Studies
Genetic InfoMax: Exploring Mutual Information Maximization in High-Dimensional Imaging Genetics Studies
复制标题
DOI：
10.48550/arxiv.2309.15132
复制
发表时间：
2023-09
期刊：
影响因子：
--
通讯作者：
Yaochen Xie;Z. Xie;Sheikh Muhammad Saiful Islam;D. Zhi;Shuiwang Ji
中科院分区：
文献类型：
--
作者：
Yaochen Xie;Z. Xie;Sheikh Muhammad Saiful Islam;D. Zhi;Shuiwang Ji
全基因组关联研究（GWAS）用于确定遗传变异与特定性状之间的关系。当应用于高维医学成像数据时，关键的一步是提取数据的低维，但信息表示作为特征。由于与典型的视觉表征学习相比，GWAS带来了独特的挑战，因此成像遗传学的表征学习在很大程度上尚未得到充分探索。在本研究中，我们通过识别现有方法的主要局限性，从互信息（MI）的角度解决了这个问题。我们引入了一个跨模式学习框架Genetic InfoMax (GIM)，包括一个正则化MI估计器和一个新的遗传信息转换器，以解决GWAS的具体挑战。我们在人脑三维MRI数据上评估GIM，并建立标准化的评估方案，将其与现有方法进行比较。我们的结果证明了GIM的有效性，并显著提高了GWAS的性能。
Genome-wide association studies (GWAS) are used to identify relationships between genetic variations and specific traits. When applied to high-dimensional medical imaging data, a key step is to extract lower-dimensional, yet informative representations of the data as traits. Representation learning for imaging genetics is largely under-explored due to the unique challenges posed by GWAS in comparison to typical visual representation learning. In this study, we tackle this problem from the mutual information (MI) perspective by identifying key limitations of existing methods. We introduce a trans-modal learning framework Genetic InfoMax (GIM), including a regularized MI estimator and a novel genetics-informed transformer to address the specific challenges of GWAS. We evaluate GIM on human brain 3D MRI data and establish standardized evaluation protocols to compare it to existing approaches. Our results demonstrate the effectiveness of GIM and a significantly improved performance on GWAS.