Single patient convolutional neural networks for real-time MR reconstruction: coherent low-resolution versus incoherent undersampling

Phys Med Biol. 2020 Apr 23;65(8):08NT03. doi: 10.1088/1361-6560/ab7d13.


Accelerated MRI involves undersampling k-space, creating unwanted artifacts when reconstructing the data. While the strategy of incoherent k-space acquisition is proven for techniques such as compressed sensing, it may not be optimal for all techniques. This study compares the use of coherent low-resolution (coherent-LR) and incoherent undersampling phase-encoding for real-time 3D CNN image reconstruction. Data were acquired with our 3 T Philips Achieva system. A retrospective analysis was performed on six non-small cell lung cancer patients who received dynamic acquisitions consisting of 650 free breathing images using a bSSFP sequence. We retrospectively undersampled the data by 5x and 10x acceleration using the two phase-encoding schemes. A quantitative analysis was conducted evaluating the tumor segmentations from the CNN reconstructed data using the Dice coefficient (DC) and centroid displacement. The reconstruction noise was evaluated using the structural similarity index (SSIM). Furthermore, we qualitatively investigated the CNN reconstruction using prospectively undersampled data, where the fully sampled training data set is acquired separately from the accelerated undersampled data. The patient averaged DC, centroid displacement, and SSIM for the tumor segmentation at 5x and 10x was superior using coherent low-resolution undersampling. Furthermore, the patient-specific CNN can be trained in under 6 h and the reconstruction time was 54 ms per image. Both the incoherent and coherent-LR prospective CNN reconstructions yielded qualitatively acceptable images; however, the coherent-LR reconstruction appeared superior to the incoherent reconstruction. We have demonstrated that coherent-LR undersampling for real-time CNN image reconstruction performs quantitatively better for the retrospective case of lung tumor segmentation, and qualitatively better for the prospective case. The tumor segmentation mean DC increased for all six patients at 5x acceleration and the temporal (dynamic) variance of the segmentation was reduced. The reconstruction speed achieved for our current implementation was 54 ms, providing an acceptable frame rate for real-time on-the-fly MR imaging.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Artifacts
  • Carcinoma, Non-Small-Cell Lung / diagnostic imaging
  • Carcinoma, Non-Small-Cell Lung / physiopathology
  • Humans
  • Image Processing, Computer-Assisted / methods*
  • Lung Neoplasms / diagnostic imaging
  • Lung Neoplasms / physiopathology
  • Magnetic Resonance Imaging*
  • Neural Networks, Computer*
  • Respiration
  • Retrospective Studies
  • Signal-To-Noise Ratio*
  • Time Factors