Computationally Efficient 3D MRI Reconstruction with Adaptive MLP

• URL: http://arxiv.org/abs/2301.08868v2
• Date: Wed, 31 May 2023 15:34:02 GMT
• Title: Computationally Efficient 3D MRI Reconstruction with Adaptive MLP
• Authors: Eric Z. Chen, Chi Zhang, Xiao Chen, Yikang Liu, Terrence Chen, Shanhui Sun
• Abstract summary: Current methods are mainly based on convolutional neural networks (CNN) with small kernels, which are difficult to scale up to have sufficient fitting power for 3D MRI reconstruction. We propose Recon3DMLP, a hybrid of CNN modules with small kernels for low-frequency reconstruction and GPU (MLP) modules with large kernels to boost the high-frequency reconstruction.
• Score: 12.796051051794024
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Compared with 2D MRI, 3D MRI provides superior volumetric spatial resolution and signal-to-noise ratio. However, it is more challenging to reconstruct 3D MRI images. Current methods are mainly based on convolutional neural networks (CNN) with small kernels, which are difficult to scale up to have sufficient fitting power for 3D MRI reconstruction due to the large image size and GPU memory constraint. Furthermore, MRI reconstruction is a deconvolution problem, which demands long-distance information that is difficult to capture by CNNs with small convolution kernels. The multi-layer perceptron (MLP) can model such long-distance information, but it requires a fixed input size. In this paper, we proposed Recon3DMLP, a hybrid of CNN modules with small kernels for low-frequency reconstruction and adaptive MLP (dMLP) modules with large kernels to boost the high-frequency reconstruction, for 3D MRI reconstruction. We further utilized the circular shift operation based on MRI physics such that dMLP accepts arbitrary image size and can extract global information from the entire FOV. We also propose a GPU memory efficient data fidelity module that can reduce $>$50$\%$ memory. We compared Recon3DMLP with other CNN-based models on a high-resolution (HR) 3D MRI dataset. Recon3DMLP improves HR 3D reconstruction and outperforms several existing CNN-based models under similar GPU memory consumption, which demonstrates that Recon3DMLP is a practical solution for HR 3D MRI reconstruction.

Related papers

• fMRI-3D: A Comprehensive Dataset for Enhancing fMRI-based 3D Reconstruction [50.534007259536715]
  We present the fMRI-3D dataset, which includes data from 15 participants and showcases a total of 4768 3D objects. We propose MinD-3D, a novel framework designed to decode 3D visual information from fMRI signals.
  arXiv  Detail & Related papers  (2024-09-17T16:13:59Z)
• MinD-3D: Reconstruct High-quality 3D objects in Human Brain [50.534007259536715]
  Recon3DMind is an innovative task aimed at reconstructing 3D visuals from Functional Magnetic Resonance Imaging (fMRI) signals. We present the fMRI-Shape dataset, which includes data from 14 participants and features 360-degree videos of 3D objects. We propose MinD-3D, a novel and effective three-stage framework specifically designed to decode the brain's 3D visual information from fMRI signals.
  arXiv  Detail & Related papers  (2023-12-12T18:21:36Z)
• Video4MRI: An Empirical Study on Brain Magnetic Resonance Image Analytics with CNN-based Video Classification Frameworks [60.42012344842292]
  3D CNN-based models dominate the field of magnetic resonance image (MRI) analytics. In this paper, four datasets of Alzheimer's and Parkinson's disease recognition are utilized in experiments. In terms of efficiency, the video framework performs better than 3D-CNN models by 5% - 11% with 50% - 66% less trainable parameters.
  arXiv  Detail & Related papers  (2023-02-24T15:26:31Z)
• Attentive Symmetric Autoencoder for Brain MRI Segmentation [56.02577247523737]
  We propose a novel Attentive Symmetric Auto-encoder based on Vision Transformer (ViT) for 3D brain MRI segmentation tasks. In the pre-training stage, the proposed auto-encoder pays more attention to reconstruct the informative patches according to the gradient metrics. Experimental results show that our proposed attentive symmetric auto-encoder outperforms the state-of-the-art self-supervised learning methods and medical image segmentation models.
  arXiv  Detail & Related papers  (2022-09-19T09:43:19Z)
• GLEAM: Greedy Learning for Large-Scale Accelerated MRI Reconstruction [50.248694764703714]
  Unrolled neural networks have recently achieved state-of-the-art accelerated MRI reconstruction. These networks unroll iterative optimization algorithms by alternating between physics-based consistency and neural-network based regularization. We propose Greedy LEarning for Accelerated MRI reconstruction, an efficient training strategy for high-dimensional imaging settings.
  arXiv  Detail & Related papers  (2022-07-18T06:01:29Z)
• Highly Accurate FMRI ADHD Classification using time distributed multi modal 3D CNNs [0.0]
  This work proposes an algorithm for fMRI data analysis for the classification of ADHD disorders. By leveraging a 3D-GAN it would be possible to use deepfake data to enhance the accuracy of 3D CNN classification of brain disorders.
  arXiv  Detail & Related papers  (2022-05-24T11:39:11Z)
• Angular Super-Resolution in Diffusion MRI with a 3D Recurrent Convolutional Autoencoder [0.0]
  High resolution diffusion MRI (dMRI) data is often constrained by limited scanning time in clinical settings. We develop a 3D recurrent convolutional neural network capable of super-resolving dMRI volumes in the angular domain.
  arXiv  Detail & Related papers  (2022-03-29T14:08:30Z)
• 3-Dimensional Deep Learning with Spatial Erasing for Unsupervised Anomaly Segmentation in Brain MRI [55.97060983868787]
  We investigate whether using increased spatial context by using MRI volumes combined with spatial erasing leads to improved unsupervised anomaly segmentation performance. We compare 2D variational autoencoder (VAE) to their 3D counterpart, propose 3D input erasing, and systemically study the impact of the data set size on the performance. Our best performing 3D VAE with input erasing leads to an average DICE score of 31.40% compared to 25.76% for the 2D VAE.
  arXiv  Detail & Related papers  (2021-09-14T09:17:27Z)
• Memory-efficient Learning for High-Dimensional MRI Reconstruction [20.81538631727325]
  We show improved image reconstruction performance for in-vivo 3D MRI and 2D+time cardiac cine MRI using memory-efficient learning framework (MEL) MEL uses far less GPU memory while marginally increasing the training time, which enables new applications of DL to high-dimensional MRI.
  arXiv  Detail & Related papers  (2021-03-06T01:36:25Z)
• MRI Super-Resolution with GAN and 3D Multi-Level DenseNet: Smaller, Faster, and Better [16.65044022241517]
  High-resolution (HR) magnetic resonance imaging (MRI) provides detailed anatomical information critical for diagnosis in the clinical application. HR MRI typically comes at the cost of long scan time, small spatial coverage, and low signal-to-noise ratio (SNR) Recent studies showed that with a deep convolutional neural network (CNN), HR generic images could be recovered from low-resolution (LR) inputs via single image super-resolution (SISR) approaches.
  arXiv  Detail & Related papers  (2020-03-02T22:07:56Z)

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.