Preserved Edge Convolutional Neural Network for Sensitivity Enhancement of Deuterium Metabolic Imaging (DMI)

• URL: http://arxiv.org/abs/2309.04100v2
• Date: Wed, 13 Sep 2023 20:52:56 GMT
• Title: Preserved Edge Convolutional Neural Network for Sensitivity Enhancement of Deuterium Metabolic Imaging (DMI)
• Abstract summary: This work presents a deep learning method for sensitivity enhancement of Deuterium Metabolic Imaging (DMI) A convolutional neural network (CNN) was designed to estimate the 2H-labeled metabolite concentrations from low SNR. The estimation precision was further improved by fine-tuning the CNN with MRI-based edge-preserving regularization for each DMI dataset.
• Score: 10.884358837187243
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Purpose: Common to most MRSI techniques, the spatial resolution and the minimal scan duration of Deuterium Metabolic Imaging (DMI) are limited by the achievable SNR. This work presents a deep learning method for sensitivity enhancement of DMI. Methods: A convolutional neural network (CNN) was designed to estimate the 2H-labeled metabolite concentrations from low SNR and distorted DMI FIDs. The CNN was trained with synthetic data that represent a range of SNR levels typically encountered in vivo. The estimation precision was further improved by fine-tuning the CNN with MRI-based edge-preserving regularization for each DMI dataset. The proposed processing method, PReserved Edge ConvolutIonal neural network for Sensitivity Enhanced DMI (PRECISE-DMI), was applied to simulation studies and in vivo experiments to evaluate the anticipated improvements in SNR and investigate the potential for inaccuracies. Results: PRECISE-DMI visually improved the metabolic maps of low SNR datasets, and quantitatively provided higher precision than the standard Fourier reconstruction. Processing of DMI data acquired in rat brain tumor models resulted in more precise determination of 2H-labeled lactate and glutamate + glutamine levels, at increased spatial resolution (from >8 to 2 $\mu$L) or shortened scan time (from 32 to 4 min) compared to standard acquisitions. However, rigorous SD-bias analyses showed that overuse of the edge-preserving regularization can compromise the accuracy of the results. Conclusion: PRECISE-DMI allows a flexible trade-off between enhancing the sensitivity of DMI and minimizing the inaccuracies. With typical settings, the DMI sensitivity can be improved by 3-fold while retaining the capability to detect local signal variations.

Related papers

• Physics-Informed Implicit Neural Representations for Improved Myocardial Perfusion MRI Quantification [1.2835484274728046]
  Physics-informed neural networks (PINNs) have been proposed as an alternative to conventional non-linear least squares fitting methods.<n>In this work, we extend the previously proposed PINN framework with implicit neural representations (INRs) to represent the MR signal as a continuoustemporal function.<n>Our proposed PINN with INRs demonstrates improved robustness and parameter estimation accuracy over the previously established methods.
  arXiv  Detail & Related papers  (2026-08-11T11:25:22Z)
• Fine-tuning language encoding models on slow fMRI improves prediction for fast ECoG [45.06821993085712]
  We propose using non-invasive fMRI to bridge the gap in training data.<n>Using spoken language representations fine-tuned on fMRI, we build encoding models of ECoG.<n> Prediction improved in frequency bands well beyond what is directly measured in fMRI.
  arXiv  Detail & Related papers  (2026-05-19T00:49:51Z)
• Hybrid Multi-Dimensional MRI Prostate Cancer Detection via Hadamard Network-Based Bias Correction and Residual Networks [4.984516442539689]
  We propose the Hadamard-Bias Network plus ResNet18 (HBR-Net-18), a two-stage AI framework for PCa detection.<n>In the first stage, a Hadamard U-Net-based algorithm suppresses intensity inhomogeneities (bias fields) across six parametric HM-MRI maps.<n>In the second stage, a Residual Network (ResNet-18) performs patch-level classification.
  arXiv  Detail & Related papers  (2026-04-18T18:49:21Z)
• Revisiting Global Token Mixing in Task-Dependent MRI Restoration: Insights from Minimal Gated CNN Baselines [43.505945728449774]
  Global token mixing has become a popular model design choice for MRI restoration.<n>We ask whether global token mixing is actually beneficial in each individual task across three representative settings.<n>For accelerated MRI reconstruction, the minimal unrolled gated-CNN baseline is already highly competitive.<n>For super-resolution, where low-frequency k-space data are largely preserved by the controlled low-pass degradation, local gated models remain competitive.<n>For denoising with pronounced spatially heteroscedastic noise, token-mixing models achieve the strongest overall performance.
  arXiv  Detail & Related papers  (2026-03-02T04:57:52Z)
• From Promise to Practical Reality: Transforming Diffusion MRI Analysis with Fast Deep Learning Enhancement [35.368152968098194]
  FastFOD-Net is an end-to-end deep learning framework enhancing FODs with superior performance and delivering training/inference efficiency for clinical use.<n>This work will facilitate the more widespread adoption of, and build clinical trust in, deep learning based methods for diffusion MRI enhancement.
  arXiv  Detail & Related papers  (2025-08-13T17:56:29Z)
• Implicit neural representations for accurate estimation of the standard model of white matter [0.25128687379089687]
  The Standard Model (SM) of white matter aims to disentangle dMRI signal contributions from intra- and extra-axonal water compartments.<n>Due to the model its high-dimensional nature, extensive acquisition protocols with multiple b-values and diffusion shapes are typically required to mitigate parameter degeneracies.<n>This work achieves a novel estimation framework based on implicit neural representations (INRs), which incorporate regularization through the sinusoidal encoding of the input coordinates.
  arXiv  Detail & Related papers  (2025-06-18T15:40:42Z)
• HepatoGEN: Generating Hepatobiliary Phase MRI with Perceptual and Adversarial Models [33.7054351451505]
  We propose a deep learning based approach for synthesizing hepatobiliary phase (HBP) images from earlier contrast phases.<n> Quantitative evaluation using pixel-wise and perceptual metrics, combined with blinded radiologist reviews, showed that pGAN achieved the best quantitative performance.<n>In contrast, the U-Net produced consistent liver enhancement with fewer artifacts, while DDPM underperformed due to limited preservation of fine structural details.
  arXiv  Detail & Related papers  (2025-04-25T15:01:09Z)
• Equivariant Spherical CNNs for Accurate Fiber Orientation Distribution Estimation in Neonatal Diffusion MRI with Reduced Acquisition Time [1.675857332621569]
  We propose a rotationally equivariant Spherical Convolutional Neural Network (sCNN) framework tailored for neonatal dMRI. We train and evaluate the performance of our sCNN using real data from 43 neonatal dMRI datasets.
  arXiv  Detail & Related papers  (2025-04-02T17:36:51Z)
• A Flow-based Truncated Denoising Diffusion Model for Super-resolution Magnetic Resonance Spectroscopic Imaging [34.32290273033808]
  This work introduces a Flow-based Truncated Denoising Diffusion Model for super-resolution MRSI. It shortens the diffusion process by truncating the diffusion chain, and the truncated steps are estimated using a normalizing flow-based network. We demonstrate that FTDDM outperforms existing generative models while speeding up the sampling process by over 9-fold.
  arXiv  Detail & Related papers  (2024-10-25T03:42:35Z)
• A Unified Model for Compressed Sensing MRI Across Undersampling Patterns [69.19631302047569]
  Deep neural networks have shown great potential for reconstructing high-fidelity images from undersampled measurements. Our model is based on neural operators, a discretization-agnostic architecture. Our inference speed is also 1,400x faster than diffusion methods.
  arXiv  Detail & Related papers  (2024-10-05T20:03:57Z)
• Enhancing Angular Resolution via Directionality Encoding and Geometric Constraints in Brain Diffusion Tensor Imaging [70.66500060987312]
  Diffusion-weighted imaging (DWI) is a type of Magnetic Resonance Imaging (MRI) technique sensitised to the diffusivity of water molecules. This work proposes DirGeo-DTI, a deep learning-based method to estimate reliable DTI metrics even from a set of DWIs acquired with the minimum theoretical number (6) of gradient directions.
  arXiv  Detail & Related papers  (2024-09-11T11:12:26Z)
• Rotational Augmented Noise2Inverse for Low-dose Computed Tomography Reconstruction [83.73429628413773]
  Supervised deep learning methods have shown the ability to remove noise in images but require accurate ground truth. We propose a novel self-supervised framework for LDCT, in which ground truth is not required for training the convolutional neural network (CNN) Numerical and experimental results show that the reconstruction accuracy of N2I with sparse views is degrading while the proposed rotational augmented Noise2Inverse (RAN2I) method keeps better image quality over a different range of sampling angles.
  arXiv  Detail & Related papers  (2023-12-19T22:40:51Z)
• Joint MR sequence optimization beats pure neural network approaches for spin-echo MRI super-resolution [44.52688267348063]
  Current MRI super-resolution (SR) methods only use existing contrasts acquired from typical clinical sequences as input for the neural network (NN) We propose a known-operator learning approach to perform an end-to-end optimization of MR sequence and neural net-work parameters for SR-TSE.
  arXiv  Detail & Related papers  (2023-05-12T14:40:25Z)
• Generative AI for Rapid Diffusion MRI with Improved Image Quality, Reliability and Generalizability [3.6119644566822484]
  We employ a Swin UNEt Transformers model, trained on augmented Human Connectome Project data, to perform generalized denoising of dMRI. We demonstrate super-resolution with artificially downsampled HCP data in normal adult volunteers. We exceed current state-of-the-art denoising methods in accuracy and test-retest reliability of rapid diffusion tensor imaging requiring only 90 seconds of scan time.
  arXiv  Detail & Related papers  (2023-03-10T03:39:23Z)
• 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)
• DFENet: A Novel Dimension Fusion Edge Guided Network for Brain MRI Segmentation [0.0]
  We propose a novel Dimension Fusion Edge-guided network (DFENet) that can meet both of these requirements by fusing the features of 2D and 3D CNNs. The proposed model is robust, accurate, superior to the existing methods, and can be relied upon for biomedical applications.
  arXiv  Detail & Related papers  (2021-05-17T15:43:59Z)
• Deep Implicit Statistical Shape Models for 3D Medical Image Delineation [47.78425002879612]
  3D delineation of anatomical structures is a cardinal goal in medical imaging analysis. Prior to deep learning, statistical shape models that imposed anatomical constraints and produced high quality surfaces were a core technology. We present deep implicit statistical shape models (DISSMs), a new approach to delineation that marries the representation power of CNNs with the robustness of SSMs.
  arXiv  Detail & Related papers  (2021-04-07T01:15:06Z)
• 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)
• Denoising Single Voxel Magnetic Resonance Spectroscopy with Deep Learning on Repeatedly Sampled In Vivo Data [17.291672952879022]
  MRS is a noninvasive tool to reveal metabolic information. One challenge of MRS is the relatively low Signal-Noise Ratio (SNR) due to low concentrations of metabolites. Deep learning denoising approach is proposed to learn a mapping from the low SNR signal to the high SNR one.
  arXiv  Detail & Related papers  (2021-01-26T05:36:44Z)
• Probabilistic 3D surface reconstruction from sparse MRI information [58.14653650521129]
  We present a novel probabilistic deep learning approach for concurrent 3D surface reconstruction from sparse 2D MR image data and aleatoric uncertainty prediction. Our method is capable of reconstructing large surface meshes from three quasi-orthogonal MR imaging slices from limited training sets.
  arXiv  Detail & Related papers  (2020-10-05T14:18:52Z)
• DEEPMIR: A DEEP neural network for differential detection of cerebral Microbleeds and IRon deposits in MRI [3.0361336899303693]
  Cerebral microbleeds (CMBs) and localized non-hemorrhage iron deposits in the basal ganglia have been associated with brain aging, vascular disease and neurodegenerative disorders. We developed a deep learning-based segmentation method suitable for segmenting both CMBs and iron deposits.
  arXiv  Detail & Related papers  (2020-09-30T23:50:14Z)
• Going deeper with brain morphometry using neural networks [18.851541271793085]
  Deep convolutional neural networks can infer morphometric measurements within a few seconds. We propose a more accurate and efficient neural network model for brain morphometry named HerstonNet.
  arXiv  Detail & Related papers  (2020-09-07T07:57:13Z)

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.