Under-sampling lung gas MRI reconstruction method based on multi-task complex value deep learning

Abstract

The invention discloses an under-sampling lung gas MRI reconstruction method based on multi-task complex value deep learning, and the method comprises the steps of predicting complete k-space data through employing a k-space reconstruction network, obtaining a preliminary reconstruction image through employing an image domain reconstruction network, finally further enhancing the details of the image through employing a multi-task detail enhancement network combining segmentation and reconstruction, and obtaining a finally reconstructed lung hyperpolarized gas MRI image. According to the method, the plurality of convolutional layers are adopted, and phase information in the k space is effectively utilized. Compared with a traditional reconstruction method, the imaging speed is greatly increased while the reconstruction quality is improved. Compared with a network with a single training reconstruction task, the method has the advantages that the two tasks of reconstruction and segmentation are trained at the same time, the two tasks share a feature extraction layer, the segmentation task pays more attention to details and edge parts of the image, more high-frequency features can be extracted, better image details can be reconstructed, and the reconstruction quality is improved.

Description

technical field [0001] The invention belongs to the field of imaging technology, and in particular relates to an under-sampled lung gas MRI reconstruction method for multi-task complex-valued deep learning. Background technique [0002] Magnetic resonance imaging (Magnetic Resonance Imaging, MRI) is non-invasive and non-radioactive, and has unique advantages in clinical disease diagnosis [Mehmet Steen Moeller, Sebastian et al. Magn. Reson. Med., 2019, 439:453.]. However, conventional MRI mainly detects hydrogen protons ( 1 H) Imaging, while the lung is a cavity structure with low hydrogen proton density, therefore, the lung is a "blind area" of traditional MRI. Hyperpolarized gas MRI uses spin-exchange optical pumping technology to pump noble gases (such as 3 He or 129 The polarization of Xe) is increased by 4-5 orders of magnitude, and the observation object of MR imaging is expanded from solid (tissue) and liquid to gas, so as to realize the detection of the structu...

AI Technical Summary

Problems solved by technology

Although the deep learning algorithm can obtain higher-quality reconstructed images, it requires a large number of high-quality full-sampled images as label data, and hyperpolarized gas MRI is susceptible to noise and artifacts, and high-quality lung hyperpolarized gas There are fewer MR images, and less training set data make it difficult for convolutional neural networks to extract rich image features, which will affect the final reconstruction results

Images