Weakly-supervised Learning for Single-step Quantitative Susceptibility Mapping

• URL: http://arxiv.org/abs/2008.06187v1
• Date: Fri, 14 Aug 2020 04:28:08 GMT
• Title: Weakly-supervised Learning for Single-step Quantitative Susceptibility Mapping
• Authors: Juan Liu and Kevin M Koch
• Abstract summary: We propose a weakly-supervised single-step QSM reconstruction method, denoted as wTFI, to directly reconstruct QSM from the total field without BFR. wTFI uses the BFR method RESHARP local fields as supervision to perform a multi-task learning of local tissue fields and QSM. We show that wTFI can generate high-quality local field and susceptibility maps in a variety of contexts.
• Score: 5.590406494337628
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Quantitative susceptibility mapping (QSM) utilizes MRI phase information to estimate tissue magnetic susceptibility. The generation of QSM requires solving ill-posed background field removal (BFR) and field-to-source inversion problems. Because current QSM techniques struggle to generate reliable QSM in clinical contexts, QSM clinical translation is greatly hindered. Recently, deep learning (DL) approaches for QSM reconstruction have shown impressive performance. Due to inherent non-existent ground-truth, these DL techniques use either calculation of susceptibility through multiple orientation sampling (COSMOS) maps or synthetic data for training, which are constrained by the availability and accuracy of COSMOS maps or domain shift when training data and testing data have different domains. To address these limitations, we propose a weakly-supervised single-step QSM reconstruction method, denoted as wTFI, to directly reconstruct QSM from the total field without BFR. wTFI uses the BFR method RESHARP local fields as supervision to perform a multi-task learning of local tissue fields and QSM, and is capable of recovering magnetic susceptibility estimates near the edges of the brain where are eroded in RESHARP and realize whole brain QSM estimation. Quantitative and qualitative evaluation shows that wTFI can generate high-quality local field and susceptibility maps in a variety of neuroimaging contexts.

Related papers

• IR2QSM: Quantitative Susceptibility Mapping via Deep Neural Networks with Iterative Reverse Concatenations and Recurrent Modules [14.228884847425011]
  We propose a novel deep learning-based IR2QSM method for QSM reconstruction. It is designed by iterating four times of a reverse concatenations and middle recurrent modules enhanced U-net. Simulated and in vivo experiments were conducted to compare IR2QSM with several traditional algorithms and state-of-the-art deep learning methods.
  arXiv  Detail & Related papers  (2024-06-18T06:17:45Z)
• Neuro-mimetic Task-free Unsupervised Online Learning with Continual Self-Organizing Maps [56.827895559823126]
  Self-organizing map (SOM) is a neural model often used in clustering and dimensionality reduction. We propose a generalization of the SOM, the continual SOM, which is capable of online unsupervised learning under a low memory budget. Our results, on benchmarks including MNIST, Kuzushiji-MNIST, and Fashion-MNIST, show almost a two times increase in accuracy.
  arXiv  Detail & Related papers  (2024-02-19T19:11:22Z)
• Learning Federated Visual Prompt in Null Space for MRI Reconstruction [83.71117888610547]
  We propose a new algorithm, FedPR, to learn federated visual prompts in the null space of global prompt for MRI reconstruction. FedPR significantly outperforms state-of-the-art FL algorithms with 6% of communication costs when given the limited amount of local training data.
  arXiv  Detail & Related papers  (2023-03-28T17:46:16Z)
• fMRI from EEG is only Deep Learning away: the use of interpretable DL to unravel EEG-fMRI relationships [68.8204255655161]
  We present an interpretable domain grounded solution to recover the activity of several subcortical regions from multichannel EEG data. We recover individual spatial and time-frequency patterns of scalp EEG predictive of the hemodynamic signal in the subcortical nuclei.
  arXiv  Detail & Related papers  (2022-10-23T15:11:37Z)
• Reducing Catastrophic Forgetting in Self Organizing Maps with Internally-Induced Generative Replay [67.50637511633212]
  A lifelong learning agent is able to continually learn from potentially infinite streams of pattern sensory data. One major historic difficulty in building agents that adapt is that neural systems struggle to retain previously-acquired knowledge when learning from new samples. This problem is known as catastrophic forgetting (interference) and remains an unsolved problem in the domain of machine learning to this day.
  arXiv  Detail & Related papers  (2021-12-09T07:11:14Z)
• Complex-valued Federated Learning with Differential Privacy and MRI Applications [51.34714485616763]
  We introduce the complex-valued Gaussian mechanism, whose behaviour we characterise in terms of $f$-DP, $(varepsilon, delta)$-DP and R'enyi-DP. We present novel complex-valued neural network primitives compatible with DP. Experimentally, we showcase a proof-of-concept by training federated complex-valued neural networks with DP on a real-world task.
  arXiv  Detail & Related papers  (2021-10-07T14:03:00Z)
• Improved Padding in CNNs for Quantitative Susceptibility Mapping [5.421615560456378]
  We propose an improved padding technique which utilizes the neighboring valid voxels to estimate the invalid voxels of feature maps at volume boundaries in the neural networks. Studies using simulated and in-vivo data show that the proposed padding greatly improves estimation accuracy and reduces artifacts in the results in the tasks of background field removal, field-to-source inversion, and single-step QSM reconstruction.
  arXiv  Detail & Related papers  (2021-06-21T01:35:00Z)
• Interpretable Deep Learning for the Remote Characterisation of Ambulation in Multiple Sclerosis using Smartphones [3.5547766520356547]
  Deep convolutional neural networks (DCNN) applied to smartphone inertial sensor data were shown to better distinguish healthy from MS participant ambulation. A transfer learning (TL) model from similar large open-source datasets was proposed. A lack of transparency of "black-box" deep networks remains one of the largest stumbling blocks to the wider acceptance of deep learning for clinical applications.
  arXiv  Detail & Related papers  (2021-03-16T16:15:49Z)
• MoG-QSM: Model-based Generative Adversarial Deep Learning Network for Quantitative Susceptibility Mapping [10.898053030099023]
  We propose a model-based framework that permeates benefits from generative adversarial networks to train a regularization term. A residual network leveraging a mixture of least-squares (LS) GAN and the L1 cost was trained as the generator to learn the prior information. MoG-QSM generates highly accurate susceptibility maps from single orientation phase maps.
  arXiv  Detail & Related papers  (2021-01-21T02:52:05Z)
• Statistical control for spatio-temporal MEG/EEG source imaging with desparsified multi-task Lasso [102.84915019938413]
  Non-invasive techniques like magnetoencephalography (MEG) or electroencephalography (EEG) offer promise of non-invasive techniques. The problem of source localization, or source imaging, poses however a high-dimensional statistical inference challenge. We propose an ensemble of desparsified multi-task Lasso (ecd-MTLasso) to deal with this problem.
  arXiv  Detail & Related papers  (2020-09-29T21:17:16Z)
• Learned Proximal Networks for Quantitative Susceptibility Mapping [9.061630971752464]
  We present a Learned Proximal Convolutional Neural Network (LP-CNN) for solving the ill-posed QSM dipole inversion problem. This framework is believed to be the first deep learning QSM approach that can naturally handle an arbitrary number of phase input measurements.
  arXiv  Detail & Related papers  (2020-08-11T22:35:24Z)

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.