Physics-informed self-supervised deep learning reconstruction for accelerated first-pass perfusion cardiac MRI

• URL: http://arxiv.org/abs/2301.02033v1
• Date: Thu, 5 Jan 2023 12:11:17 GMT
• Title: Physics-informed self-supervised deep learning reconstruction for accelerated first-pass perfusion cardiac MRI
• Authors: Elena Mart\'in-Gonz\'alez, Ebraham Alskaf, Amedeo Chiribiri, Pablo Casaseca-de-la-Higuera, Carlos Alberola-L\'opez, Rita G Nunes and Teresa M Correia
• Abstract summary: We propose a physics-informed self-supervised deep learning FPP-CMR reconstruction approach for accelerating FPP-CMR scans. The proposed method provides high-quality FPP-CMR images from 10x undersampled data without using fully sampled reference data.
• Score: 2.023359976134555
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: First-pass perfusion cardiac magnetic resonance (FPP-CMR) is becoming an essential non-invasive imaging method for detecting deficits of myocardial blood flow, allowing the assessment of coronary heart disease. Nevertheless, acquisitions suffer from relatively low spatial resolution and limited heart coverage. Compressed sensing (CS) methods have been proposed to accelerate FPP-CMR and achieve higher spatial resolution. However, the long reconstruction times have limited the widespread clinical use of CS in FPP-CMR. Deep learning techniques based on supervised learning have emerged as alternatives for speeding up reconstructions. However, these approaches require fully sampled data for training, which is not possible to obtain, particularly high-resolution FPP-CMR images. Here, we propose a physics-informed self-supervised deep learning FPP-CMR reconstruction approach for accelerating FPP-CMR scans and hence facilitate high spatial resolution imaging. The proposed method provides high-quality FPP-CMR images from 10x undersampled data without using fully sampled reference data.

Related papers

• Training Physics-Driven Deep Learning Reconstruction without Raw Data Access for Equitable Fast MRI [2.512491726995032]
  Physics-driven deep learning (PD-DL) approaches have become popular for improved reconstruction of fast magnetic resonance imaging (MRI) scans. PD-DL offers higher acceleration rates compared to existing clinical fast MRI techniques, but their use has been limited outside specialized MRI centers. One impediment for their deployment is the difficulties with generalization to pathologies or population groups that are not well-represented in training sets. CUPID achieves similar quality compared to well-established PD-DL training strategies that require raw k-space data access.
  arXiv  Detail & Related papers  (2024-11-20T03:53:41Z)
• On the Foundation Model for Cardiac MRI Reconstruction [6.284878525302227]
  We propose a foundation model that uses adaptive unrolling, channel-shifting, and Pattern and Contrast-Prompt-UNet to tackle the problem. The PCP-UNet is equipped with an image contrast and sampling pattern prompt.
  arXiv  Detail & Related papers  (2024-11-15T18:15:56Z)
• Accelerating Cardiac MRI Reconstruction with CMRatt: An Attention-Driven Approach [8.904269561863103]
  This study aims to explore the untapped potential of attention mechanisms incorporated with a deep learning model within the context of cardiac image reconstruction. Our primary goal is to identify the strengths and potential limitations of attention algorithms when integrated with a convolutional backbone model such as a U-Net. We propose a new, simple yet effective, attention pipeline specifically optimised for the task of cardiac image reconstruction.
  arXiv  Detail & Related papers  (2024-04-10T11:47:51Z)
• CMRxRecon: An open cardiac MRI dataset for the competition of accelerated image reconstruction [62.61209705638161]
  There has been growing interest in deep learning-based CMR imaging algorithms. Deep learning methods require large training datasets. This dataset includes multi-contrast, multi-view, multi-slice and multi-coil CMR imaging data from 300 subjects.
  arXiv  Detail & Related papers  (2023-09-19T15:14:42Z)
• Unsupervised reconstruction of accelerated cardiac cine MRI using Neural Fields [3.684766600912547]
  We propose an unsupervised approach based on implicit neural field representations for cardiac cine MRI (so called NF-cMRI) The proposed method was evaluated in in-vivo undersampled golden-angle radial multi-coil acquisitions for undersampling factors of 26x and 52x.
  arXiv  Detail & Related papers  (2023-07-24T23:31:36Z)
• A Long Short-term Memory Based Recurrent Neural Network for Interventional MRI Reconstruction [50.1787181309337]
  We propose a convolutional long short-term memory (Conv-LSTM) based recurrent neural network (RNN), or ConvLR, to reconstruct interventional images with golden-angle radial sampling. The proposed algorithm has the potential to achieve real-time i-MRI for DBS and can be used for general purpose MR-guided intervention.
  arXiv  Detail & Related papers  (2022-03-28T14:03:45Z)
• Towards performant and reliable undersampled MR reconstruction via diffusion model sampling [67.73698021297022]
  DiffuseRecon is a novel diffusion model-based MR reconstruction method. It guides the generation process based on the observed signals. It does not require additional training on specific acceleration factors.
  arXiv  Detail & Related papers  (2022-03-08T02:25:38Z)
• Multi-institutional Collaborations for Improving Deep Learning-based Magnetic Resonance Image Reconstruction Using Federated Learning [62.17532253489087]
  Deep learning methods have been shown to produce superior performance on MR image reconstruction. These methods require large amounts of data which is difficult to collect and share due to the high cost of acquisition and medical data privacy regulations. We propose a federated learning (FL) based solution in which we take advantage of the MR data available at different institutions while preserving patients' privacy.
  arXiv  Detail & Related papers  (2021-03-03T03:04:40Z)
• ShuffleUNet: Super resolution of diffusion-weighted MRIs using deep learning [47.68307909984442]
  Single Image Super-Resolution (SISR) is a technique aimed to obtain high-resolution (HR) details from one single low-resolution input image. Deep learning extracts prior knowledge from big datasets and produces superior MRI images from the low-resolution counterparts.
  arXiv  Detail & Related papers  (2021-02-25T14:52:23Z)
• Efficient and Phase-aware Video Super-resolution for Cardiac MRI [23.5319835123499]
  We propose a novel end-to-end trainable network to solve CMR video super-resolution problem. We incorporate the cardiac knowledge into our model to assist in utilizing the temporal information.
  arXiv  Detail & Related papers  (2020-05-21T13:29:03Z)
• Multifold Acceleration of Diffusion MRI via Slice-Interleaved Diffusion Encoding (SIDE) [50.65891535040752]
  We propose a diffusion encoding scheme, called Slice-Interleaved Diffusion. SIDE, that interleaves each diffusion-weighted (DW) image volume with slices encoded with different diffusion gradients. We also present a method based on deep learning for effective reconstruction of DW images from the highly slice-undersampled data.
  arXiv  Detail & Related papers  (2020-02-25T14:48:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.