DeepASL: Kinetic Model Incorporated Loss for Denoising Arterial Spin Labeled MRI via Deep Residual Learning

Arterial spin labeling (ASL) allows to quantify the cerebral blood flow (CBF) by magnetic labeling of the arterial blood water. ASL is increasingly used in clinical studies due to its noninvasiveness, repeatability and benefits in quantification. However, ASL suffers from an inherently low-signal-to-noise ratio (SNR) requiring repeated measurements of control/spin-labeled (C/L) pairs to achieve a reasonable image quality, which in return increases motion sensitivity. This leads to clinically prolonged scanning times increasing the risk of motion artifacts. Thus, there is an immense need of advanced imaging and processing techniques in ASL. In this paper, we propose a novel deep learning based approach to improve the perfusion-weighted image quality obtained from a subset of all available pairwise C/L subtractions. Specifically, we train a deep fully convolutional network (FCN) to learn a mapping from noisy perfusion-weighted image and its subtraction (residual) from the clean image. Additionally, we incorporate the CBF estimation model in the loss function during training, which enables the network to produce high quality images while simultaneously enforcing the CBF estimates to be as close as reference CBF values. Extensive experiments on synthetic and clinical ASL datasets demonstrate the effectiveness of our method in terms of improved ASL image quality, accurate CBF parameter estimation and considerably small computation time during testing.

• Publication year

  2018

• Venue

  International Conference on Medical Image Computing and Computer-Assisted Intervention

• Publication date

  2018-04-08

• Fields of study

  Medicine, Computer Science, Engineering

• Identifiers
  DOI 10.1007/978-3-030-00928-1_4arXiv 1804.02755
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Anatomy-Driven Modelling of Spatial Correlation for Regularisation of Arterial Spin Labelling Images

  2017cited by this paper
• Improving Arterial Spin Labeling by Using Deep Learning.

  2017influential reference
• Spatio‐temporal TGV denoising for ASL perfusion imaging

  2017influential reference
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising

  2016cited by this paper
• Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification

  2015cited by this paper
• Recommended implementation of arterial spin-labeled perfusion MRI for clinical applications: A consensus of the ISMRM perfusion study group and the European consortium for ASL in dementia.

  2015influential reference
• Voxel-Wise Functional Connectomics Using Arterial Spin Labeling Functional Magnetic Resonance Imaging: The Role of Denoising

  2015cited by this paper
• Deep Residual Learning for Image Recognition

  2015cited by this paper
• A spatio-temporal low-rank total variation approach for denoising arterial spin labeling MRI data

  2015cited by this paper
• Residual interpolation for color image demosaicking

  2013cited by this paper
• Reduction of errors in ASL cerebral perfusion and arterial transit time maps using image de‐noising

  2010cited by this paper
• Denoising of arterial spin labeling data: wavelet-domain filtering compared with Gaussian smoothing

  2010cited by this paper
• A general kinetic model for quantitative perfusion imaging with arterial spin labeling

  1998cited by this paper

• Arterial Spin Labeling-Based CBF Map Generation Using a Vector Quantized Variational Autoencoder

  2025cites this paper
• Transformer-based arterial spin labeling perfusion MRI denoising

  2025cites this paper
• Dual independent pathway‐densely connected residual network with dilated convolution‐based arterial spin labeling MRI image reconstruction with minimum label‐control pairs

  2024cites this paper
• Genetic Programming for Feature Learning and Feature Construction in Glioma Survival Prediction

  2024cites this paper
• A Review on Explainable Artificial Intelligence for Healthcare: Why, How, and When?

  2023cites this paper
• Deeply Accelerated Arterial Spin Labeling Perfusion MRI for Measuring Cerebral Blood Flow and Arterial Transit Time

  2023cites this paper
• MCP-Net: Introducing Patlak Loss Optimization to Whole-Body Dynamic PET Inter-Frame Motion Correction

  2023cites this paper
• MRI assessment of cerebral perfusion in clinical trials.

  2023cites this paper
• Automated generation of cerebral blood flow and arterial transit time maps from multiple delay arterial spin‐labeled MRI

  2022cites this paper
• Patch tensor decomposition and non-local means filter-based hybrid ASL image denoising.

  2022cites this paper
• Physics-Driven Deep Learning for Computational Magnetic Resonance Imaging: Combining physics and machine learning for improved medical imaging

  2022cites this paper
• Denoising of Three-Dimensional Fast Spin Echo Magnetic Resonance Images of Knee Joints using Spatial-Variant Noise-Relevant Residual Learning of Convolution Neural Network

  2022cites this paper
• Acceleration of cerebral blood flow and arterial transit time maps estimation from multiple post-labeling delay arterial spin-labeled MRI via deep learning

  2022cites this paper
• Deep Learning for Image Enhancement and Correction in Magnetic Resonance Imaging—State-of-the-Art and Challenges

  2022cites this paper
• A comprehensive survey of deep learning research on medical image analysis with focus on transfer learning.

  2022cites this paper
• Improving Sensitivity of Arterial Spin Labeling Perfusion MRI in Alzheimer's Disease Using Transfer Learning of Deep Learning‐Based ASL Denoising

  2021cites this paper
• Automated Generation of Cerebral Blood Flow Maps Using Deep Learning and Multiple Delay Arterial Spin-Labelled MRI

  2021cites this paper
• The classification and denoising of image noise based on deep neural networks

  2020cites this paper
• Denoising arterial spin labeling perfusion MRI with deep machine learning.

  2020cites this paper
• A Learning-from-noise Dilated Wide Activation Network for denoising Arterial Spin Labeling (ASL) Perfusion Images

  2020cites this paper
• Super Resolution of Arterial Spin Labeling MR Imaging Using Unsupervised Multi-Scale Generative Adversarial Network

  2020cites this paper
• Advances of Neuroimaging and Data Analysis

  2020cites this paper
• Accelerating GluCEST imaging using deep learning for B0 correction

  2020cites this paper
• Combined Denoising and Suppression of Transient Artifacts in Arterial Spin Labeling MRI Using Deep Learning

  2020cites this paper
• A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI

  2019influential citation
• Applications of Deep Learning to Neuro-Imaging Techniques

  2019cites this paper
• Arterial spin labeling MR image denoising and reconstruction using unsupervised deep learning

  2019cites this paper
• Spatially adaptive unsupervised multispectral nonlocal filtering for improved cerebral blood flow mapping using arterial spin labeling magnetic resonance imaging.

  2018cites this paper