KD-MRI: A knowledge distillation framework for image reconstruction and image restoration in MRI workflow

• URL: http://arxiv.org/abs/2004.05319v1
• Date: Sat, 11 Apr 2020 06:21:28 GMT
• Title: KD-MRI: A knowledge distillation framework for image reconstruction and image restoration in MRI workflow
• Authors: Balamurali Murugesan, Sricharan Vijayarangan, Kaushik Sarveswaran, Keerthi Ram and Mohanasankar Sivaprakasam
• Abstract summary: We propose a knowledge distillation (KD) framework for the image to image problems in the MRI workflow. We conduct experiments using Cardiac, Brain, and Knee MRI datasets for 4x, 5x and 8x accelerations. For the Knee dataset, the student network achieves $65%$ parameter reduction, 2x faster CPU running time, and 1.5x faster GPU running time compared to the teacher.
• Score: 1.2599533416395765
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep learning networks are being developed in every stage of the MRI workflow and have provided state-of-the-art results. However, this has come at the cost of increased computation requirement and storage. Hence, replacing the networks with compact models at various stages in the MRI workflow can significantly reduce the required storage space and provide considerable speedup. In computer vision, knowledge distillation is a commonly used method for model compression. In our work, we propose a knowledge distillation (KD) framework for the image to image problems in the MRI workflow in order to develop compact, low-parameter models without a significant drop in performance. We propose a combination of the attention-based feature distillation method and imitation loss and demonstrate its effectiveness on the popular MRI reconstruction architecture, DC-CNN. We conduct extensive experiments using Cardiac, Brain, and Knee MRI datasets for 4x, 5x and 8x accelerations. We observed that the student network trained with the assistance of the teacher using our proposed KD framework provided significant improvement over the student network trained without assistance across all the datasets and acceleration factors. Specifically, for the Knee dataset, the student network achieves $65\%$ parameter reduction, 2x faster CPU running time, and 1.5x faster GPU running time compared to the teacher. Furthermore, we compare our attention-based feature distillation method with other feature distillation methods. We also conduct an ablative study to understand the significance of attention-based distillation and imitation loss. We also extend our KD framework for MRI super-resolution and show encouraging results.

Related papers

• Attention Incorporated Network for Sharing Low-rank, Image and K-space Information during MR Image Reconstruction to Achieve Single Breath-hold Cardiac Cine Imaging [9.531827741901662]
  We propose to embed information from multiple domains, including low-rank, image, and k-space, in a novel deep learning network for MRI reconstruction. A-LIKNet adopts a parallel-branch structure, enabling independent learning in the k-space and image domain.
  arXiv  Detail & Related papers  (2024-07-03T11:54:43Z)
• NeuroPictor: Refining fMRI-to-Image Reconstruction via Multi-individual Pretraining and Multi-level Modulation [55.51412454263856]
  This paper proposes to directly modulate the generation process of diffusion models using fMRI signals. By training with about 67,000 fMRI-image pairs from various individuals, our model enjoys superior fMRI-to-image decoding capacity.
  arXiv  Detail & Related papers  (2024-03-27T02:42:52Z)
• fMRI-PTE: A Large-scale fMRI Pretrained Transformer Encoder for Multi-Subject Brain Activity Decoding [54.17776744076334]
  We propose fMRI-PTE, an innovative auto-encoder approach for fMRI pre-training. Our approach involves transforming fMRI signals into unified 2D representations, ensuring consistency in dimensions and preserving brain activity patterns. Our contributions encompass introducing fMRI-PTE, innovative data transformation, efficient training, a novel learning strategy, and the universal applicability of our approach.
  arXiv  Detail & Related papers  (2023-11-01T07:24:22Z)
• CMRxRecon: An open cardiac MRI dataset for the competition of accelerated image reconstruction [62.61209705638161]
  There has been growing interest in deep learning-based CMR imaging algorithms. Deep learning methods require large training datasets. This dataset includes multi-contrast, multi-view, multi-slice and multi-coil CMR imaging data from 300 subjects.
  arXiv  Detail & Related papers  (2023-09-19T15:14:42Z)
• Attention Hybrid Variational Net for Accelerated MRI Reconstruction [7.046523233290946]
  The application of compressed sensing (CS)-enabled data reconstruction for accelerating magnetic resonance imaging (MRI) remains a challenging problem. This is due to the fact that the information lost in k-space from the acceleration mask makes it difficult to reconstruct an image similar to the quality of a fully sampled image. We propose a deep learning-based attention hybrid variational network that performs learning in both the k-space and image domain.
  arXiv  Detail & Related papers  (2023-06-21T16:19:07Z)
• Iterative Data Refinement for Self-Supervised MR Image Reconstruction [18.02961646651716]
  We propose a data refinement framework for self-supervised MR image reconstruction. We first analyze the reason of the performance gap between self-supervised and supervised methods. Then, we design an effective self-supervised training data refinement method to reduce this data bias.
  arXiv  Detail & Related papers  (2022-11-24T06:57:16Z)
• 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)
• Edge-Enhanced Dual Discriminator Generative Adversarial Network for Fast MRI with Parallel Imaging Using Multi-view Information [10.616409735438756]
  We introduce a novel parallel imaging coupled dual discriminator generative adversarial network (PIDD-GAN) for fast multi-channel MRI reconstruction. One discriminator is used for holistic image reconstruction, whereas the other one is responsible for enhancing edge information. Results show that our PIDD-GAN provides high-quality reconstructed MR images, with well-preserved edge information.
  arXiv  Detail & Related papers  (2021-12-10T10:49:26Z)
• Adaptive Gradient Balancing for UndersampledMRI Reconstruction and Image-to-Image Translation [60.663499381212425]
  We enhance the image quality by using a Wasserstein Generative Adversarial Network combined with a novel Adaptive Gradient Balancing technique. In MRI, our method minimizes artifacts, while maintaining a high-quality reconstruction that produces sharper images than other techniques.
  arXiv  Detail & Related papers  (2021-04-05T13:05:22Z)
• Multifold Acceleration of Diffusion MRI via Slice-Interleaved Diffusion Encoding (SIDE) [50.65891535040752]
  We propose a diffusion encoding scheme, called Slice-Interleaved Diffusion. SIDE, that interleaves each diffusion-weighted (DW) image volume with slices encoded with different diffusion gradients. We also present a method based on deep learning for effective reconstruction of DW images from the highly slice-undersampled data.
  arXiv  Detail & Related papers  (2020-02-25T14:48:17Z)
• Deep Residual Dense U-Net for Resolution Enhancement in Accelerated MRI Acquisition [19.422926534305837]
  We propose a deep-learning approach, aiming at reconstructing high-quality images from accelerated MRI acquisition. Specifically, we use Convolutional Neural Network (CNN) to learn the differences between the aliased images and the original images. Considering the peculiarity of the down-sampled k-space data, we introduce a new term to the loss function in learning, which effectively employs the given k-space data.
  arXiv  Detail & Related papers  (2020-01-13T19:01:17Z)

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.