Current state-of-the-art reconstruction for quantitative tissue maps from fast, compressive, Magnetic Resonance Fingerprinting (MRF), use supervised deep learning, with the drawback of requiring high-fidelity ground truth tissue map training data which is limited. This paper proposes NonLinear Equivariant Imaging (NLEI), a self-supervised learning approach to eliminate the need for ground truth for deep MRF image reconstruction. NLEI extends the recent Equivariant Imaging framework to nonlinear inverse problems such as MRF. Only fast, compressed-sampled MRF scans are used for training. NLEI learns tissue mapping using spatiotemporal priors: spatial priors are obtained from the invariance of MRF data to a group of geometric image transformations, while temporal priors are obtained from a nonlinear Bloch response model approximated by a pre-trained neural network. Tested retrospectively on two acquisition settings, we observe that NLEI (self-supervised learning) closely approaches the performance of supervised learning, despite not using ground truth during training.
翻译:目前,从快速、压缩、磁共振指纹(MRF)中对定量组织图进行最新重建,从快速、压缩、磁共振指纹(MRF)中进行定量组织图,使用有监督的深层学习,而要求高纤维地面真相组织图培训数据是有限的,本文建议采用非利萨-静态图像成像(NLEI),这是一种由自我监督的学习方法,以消除深度MRF图像重建对地面真相的需求。NLEI将最近的平等成像框架扩大到非线性的问题,如MRF。只有快速、压缩的MRF扫描才用于培训。 NLEI利用SPOTomotimal时间学前程来学习组织图谱:空间前科是从MRF数据的变化到一组几何图像变异中获取的,而时间前科则是从一个经过预先训练的神经网络所近似非线性布洛奇反应模型中获得的。我们观察到,尽管在培训期间没有利用地面的真相,但NLEI(自我监督学习)接近监督学习的绩效。