DEEP LEARNING TECHNIQUES FOR MAGNETIC RESONANCE IMAGE RECONSTRUCTION

• Main Authors: LAZARUS CAROLE, KUNDU PRANTIK, SOFKA MICHAL, WANG ZIYI, MOSHEN SALEHI SEYED, ROTHBERG JONATHAN, DYVORNE HADRIEN A, SACOLICK LAURA, O'HALLORAN RAFAEL, SCHLEMPER JO
• Format: Patent
• Language: Chinese; English
• Published: 14.12.2021
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DIAGNOSIS; HUMAN NECESSITIES; HYGIENE; IDENTIFICATION; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; MEASURING; MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES; MEDICAL OR VETERINARY SCIENCE; PHYSICS; SURGERY; TESTING

A magnetic resonance imaging (MRI) system, comprising: a magnetics system comprising: a Bo magnet configured to provide a Bo field for the MRI system; gradient coils configured to provide gradient fields for the MRI system; and at least one RF coil configured to detect magnetic resonance (MR) signals; and a controller configured to: control the magnetics system to acquire MR spatial frequency data using non-Cartesian sampling; and generate an MR image from the acquired MR spatial frequency data using a neural network model comprising one or more neural network blocks including a first neural network block, wherein the first neural network block is configured to perform data consistency processing using a non-uniform Fourier transformation. 一种磁共振成像(MRI)系统，包括：磁系统，包括：B0磁体，其被配置成为MRI系统提供B0场；梯度线圈，其被配置成为MRI系统提供梯度场；以及至少一个RF线圈，其被配置为检测磁共振(MR)信号；以及控制器，其被配置为：控制磁系统以使用非笛卡尔采样来获取MR空间频率数据；以及使用神经网络模型根据所获取的MR空间频率数据生成MR图像，该神经网络模型包括一个或多个神经网络块，该一个或多个神经网络块包括第一神经网络块，其中，第一神经网络块被配置为使用非均匀傅立叶变换来进行数据一致性处理。