SCALABLE MAGNETIC RESONANCE FINGERPRINTING: INCREMENTAL INFERENCE OF HIGH-DIMENSIONAL ELLIPTICAL MIXTURES FROM LARGE DATA VOLUMES

• 成果类型: Article
• 署名作者: Oudoumanessah, Geoffroy; Coudert, Thomas; Lartizien, Carole; Dojat, Michel; Christen, Thomas; Forbes, Florence
• 署名单位: Communaute Universite Grenoble Alpes; Centre National de la Recherche Scientifique (CNRS); Inria; Institut National Polytechnique de Grenoble; Universite Grenoble Alpes (UGA); Communaute Universite Grenoble Alpes; CHU Grenoble Alpes; Institut National de la Sante et de la Recherche Medicale (Inserm); Universite Grenoble Alpes (UGA); Centre National de la Recherche Scientifique (CNRS); Institut National des Sciences Appliquees de Lyon - INSA Lyon; Universite Lyon 1; Institut National de la Sante et de la Recherche Medicale (Inserm); CNRS - Institute for Engineering & Systems Sciences (INSIS)
• 刊物名称: ANNALS OF APPLIED STATISTICS
• ISSN/ISSBN: 1932-6157; 1941-7330
• DOI: 10.1214/25-AOAS2124
• 发表日期: 2026-03
• 页码: 578-603
• 关键词: dimension reduction; clustering; incremental learning; high-dimensional mixture models; elliptical distributions; expectation maximization algorithm; maximum-likelihood; PCA; distributions; oxygenation; regression; algorithm; brain; em

摘要

Magnetic Resonance Fingerprinting (MRF) is an emerging technology with the potential to revolutionize radiology and medical diagnostics. In comparison to traditional magnetic resonance imaging (MRI), MRF enables the rapid, simultaneous, noninvasive acquisition and reconstruction of multiple tissue parameters, paving the way for novel diagnostic techniques. In the original matching approach, reconstruction is based on the search for the best matches between in vivo acquired signals and a dictionary of high-dimensional simulated signals (fingerprints) with known tissue properties. A critical and limiting challenge is that the size of the simulated dictionary increases exponentially with the number of parameters, leading to an extremely costly matching. In this work we propose to address this scalability issue by considering probabilistic mixtures of high-dimensional elliptical distributions to learn more efficient dictionary representations. Mixture components are modelled as flexible elliptical shapes in low-dimensional subspaces. They are exploited to cluster similar signals and reduce their dimension locally cluster-wise limiting information loss. To estimate such a mixture model, we provide a new incremental algorithm capable of handling large numbers of signals, allowing us to go far beyond the hardware limitations encountered by standard implementations. We demonstrate, on simulated and real data, that our method effectively manages large volumes of MRF data with maintained accuracy. It offers a more efficient solution for accurate tissue characterization and significantly reduces the computational burden, making the clinical application of MRF more practical and accessible.