Transformer-based Parameter Fitting of Models derived from Bloch-McConnell Equations for CEST MRI Analysis

• URL: http://arxiv.org/abs/2602.06574v1
• Date: Fri, 06 Feb 2026 10:15:39 GMT
• Title: Transformer-based Parameter Fitting of Models derived from Bloch-McConnell Equations for CEST MRI Analysis
• Authors: Christof Duhme, Chris Lippe, Verena Hoerr, Xiaoyi Jiang,
• Abstract summary: Chemical exchange saturation transfer (CEST) MRI is a non-invasive imaging modality for detecting metabolites.<n>Here, we introduce a transformer-based neural network to fit parameters such as metabolite concentrations, exchange and relaxation rates of a physical model.<n>We show that our self-supervised trained neural network clearly outperforms the solution of classical gradient-based solver.
• Score: 2.1768638312234043
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Chemical exchange saturation transfer (CEST) MRI is a non-invasive imaging modality for detecting metabolites. It offers higher resolution and sensitivity compared to conventional magnetic resonance spectroscopy (MRS). However, quantification of CEST data is challenging because the measured signal results from a complex interplay of many physiological variables. Here, we introduce a transformer-based neural network to fit parameters such as metabolite concentrations, exchange and relaxation rates of a physical model derived from Bloch-McConnell equations to in-vitro CEST spectra. We show that our self-supervised trained neural network clearly outperforms the solution of classical gradient-based solver.

Related papers

• Multiparameter Uncertainty Mapping in Quantitative Molecular MRI using a Physics-Structured Variational Autoencoder (PS-VAE) [0.0]
  We describe a physics-structured variational autoencoder (PS-VAE) designed for rapid extraction of voxelwise multi- parameter posterior distributions.<n>The method was validated in a multi-proton pool chemical exchange saturation transfer (CEST) and semisolid magnetization transfer (MT) molecular MRF study.
  arXiv  Detail & Related papers  (2026-02-03T09:46:55Z)
• Physics-Informed Sylvester Normalizing Flows for Bayesian Inference in Magnetic Resonance Spectroscopy [13.797945335120056]
  This work introduces a Bayesian inference framework using normalizing flows (SNFs) to approximate posterior distributions over metabolite concentrations.<n>A physics-based decoder incorporates prior knowledge of MRS signal formation, ensuring realistic distribution representations.
  arXiv  Detail & Related papers  (2025-05-06T14:50:14Z)
• Deep-Unrolling Multidimensional Harmonic Retrieval Algorithms on Neuromorphic Hardware [78.17783007774295]
  This paper explores the potential of conversion-based neuromorphic algorithms for highly accurate and energy-efficient single-snapshot multidimensional harmonic retrieval.<n>A novel method for converting the complex-valued convolutional layers and activations into spiking neural networks (SNNs) is developed.<n>The converted SNNs achieve almost five-fold power efficiency at moderate performance loss compared to the original CNNs.
  arXiv  Detail & Related papers  (2024-12-05T09:41:33Z)
• Multi-Parameter Molecular MRI Quantification using Physics-Informed Self-Supervised Learning [0.0]
  We present a generic computational approach for solving the parameter extraction inverse problem posed by ordinary differential equation (ODE) modeling.<n>This is achieved by formulating a numerical ODE solver to function as a step-wise analytical one, thereby making it compatible with automatic differentiation-based optimization.<n>The neural-network-based train-by-fit pipeline was used to quantify semisolid magnetization transfer (MT) and chemical exchange saturation transfer (CEST) amide proton exchange parameters in the human brain.
  arXiv  Detail & Related papers  (2024-11-10T12:40:33Z)
• A Multi-Resolution Physics-Informed Recurrent Neural Network: Formulation and Application to Musculoskeletal Systems [1.978587235008588]
  This work presents a physics-informed recurrent neural network (MR PI-RNN) for simultaneous prediction of musculoskeletal (MSK) motion. The proposed method utilizes the fast wavelet transform to decompose the mixed frequency input sEMG and output joint motion signals into nested multi-resolution signals. The framework is also capable of identifying muscle parameters that are physiologically consistent with the subject's kinematics data.
  arXiv  Detail & Related papers  (2023-05-26T02:51:39Z)
• Capturing dynamical correlations using implicit neural representations [85.66456606776552]
  We develop an artificial intelligence framework which combines a neural network trained to mimic simulated data from a model Hamiltonian with automatic differentiation to recover unknown parameters from experimental data. In doing so, we illustrate the ability to build and train a differentiable model only once, which then can be applied in real-time to multi-dimensional scattering data.
  arXiv  Detail & Related papers  (2023-04-08T07:55:36Z)
• Negligible effect of brain MRI data preprocessing for tumor segmentation [36.89606202543839]
  We conduct experiments on three publicly available datasets and evaluate the effect of different preprocessing steps in deep neural networks. Our results demonstrate that most popular standardization steps add no value to the network performance. We suggest that image intensity normalization approaches do not contribute to model accuracy because of the reduction of signal variance with image standardization.
  arXiv  Detail & Related papers  (2022-04-11T17:29:36Z)
• Mixed Precision Low-bit Quantization of Neural Network Language Models for Speech Recognition [67.95996816744251]
  State-of-the-art language models (LMs) represented by long-short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming increasingly complex and expensive for practical applications. Current quantization methods are based on uniform precision and fail to account for the varying performance sensitivity at different parts of LMs to quantization errors. Novel mixed precision neural network LM quantization methods are proposed in this paper.
  arXiv  Detail & Related papers  (2021-11-29T12:24:02Z)
• A deep learning driven pseudospectral PCE based FFT homogenization algorithm for complex microstructures [68.8204255655161]
  It is shown that the proposed method is able to predict central moments of interest while being magnitudes faster to evaluate than traditional approaches. It is shown, that the proposed method is able to predict central moments of interest while being magnitudes faster to evaluate than traditional approaches.
  arXiv  Detail & Related papers  (2021-10-26T07:02:14Z)
• Physics-informed neural networks for myocardial perfusion MRI quantification [3.318100528966778]
  This study introduces physics-informed neural networks (PINNs) as a means to perform myocardial perfusion MR quantification. PINNs can be trained to fit the observed perfusion MR data while respecting the underlying physical conservation laws.
  arXiv  Detail & Related papers  (2020-11-25T16:02:52Z)
• Provably Efficient Neural Estimation of Structural Equation Model: An Adversarial Approach [144.21892195917758]
  We study estimation in a class of generalized Structural equation models (SEMs) We formulate the linear operator equation as a min-max game, where both players are parameterized by neural networks (NNs), and learn the parameters of these neural networks using a gradient descent. For the first time we provide a tractable estimation procedure for SEMs based on NNs with provable convergence and without the need for sample splitting.
  arXiv  Detail & Related papers  (2020-07-02T17:55:47Z)
• Lesion Mask-based Simultaneous Synthesis of Anatomic and MolecularMR Images using a GAN [59.60954255038335]
  The proposed framework consists of a stretch-out up-sampling module, a brain atlas encoder, a segmentation consistency module, and multi-scale label-wise discriminators. Experiments on real clinical data demonstrate that the proposed model can perform significantly better than the state-of-the-art synthesis methods.
  arXiv  Detail & Related papers  (2020-06-26T02:50:09Z)

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.