A Densely Interconnected Network for Deep Learning Accelerated MRI

• URL: http://arxiv.org/abs/2207.02073v2
• Date: Mon, 22 May 2023 11:54:09 GMT
• Title: A Densely Interconnected Network for Deep Learning Accelerated MRI
• Abstract summary: A cascading deep learning reconstruction framework (baseline model) was modified by applying three architectural modifications. The proposed densely interconnected residual cascading network (DIRCN) achieved a SSIM improvement of 8% and 11% for four- and eight-fold acceleration.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Objective: To improve accelerated MRI reconstruction through a densely connected cascading deep learning reconstruction framework. Materials and Methods: A cascading deep learning reconstruction framework (baseline model) was modified by applying three architectural modifications: Input-level dense connections between cascade inputs and outputs, an improved deep learning sub-network, and long-range skip-connections between subsequent deep learning networks. An ablation study was performed, where five model configurations were trained on the NYU fastMRI neuro dataset with an end-to-end scheme conjunct on four- and eight-fold acceleration. The trained models were evaluated by comparing their respective structural similarity index measure (SSIM), normalized mean square error (NMSE) and peak signal to noise ratio (PSNR). Results: The proposed densely interconnected residual cascading network (DIRCN), utilizing all three suggested modifications, achieved a SSIM improvement of 8% and 11% for four- and eight-fold acceleration, respectively. For eight-fold acceleration, the model achieved a 23% decrease in the NMSE when compared to the baseline model. In an ablation study, the individual architectural modifications all contributed to this improvement, by reducing the SSIM and NMSE with approximately 3% and 5% for four-fold acceleration, respectively. Conclusion: The proposed architectural modifications allow for simple adjustments on an already existing cascading framework to further improve the resulting reconstructions.

Related papers

• State of Health Estimation using Convolutional and Bidirectional LSTM Neural Networks tuned by Bayesian Optimization [0.8602553195689513]
  A novel framework is proposed for the SOH estimation, which employs a hybrid deep learning architecture of a concatenation of a Convolution Neural Network (CNN) and a Bidirectional Long Short-Term Memory (BiLSTM) Neural Network (NN)<n>The model with the intermediate FC layers demonstrated the highest predictive accuracy.
  arXiv  Detail & Related papers  (2026-08-31T11:08:33Z)
• On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability [57.03393882933515]
  We describe the architecture and ablations of Qwen3.8-Flash-Next, a sparse mixture-of-experts model with 125B parameters, 6B activated per token, and 51B parameters of n-gram embedding tables held off the accelerator.<n>On fourteen pre-training benchmarks the model leads the 397B-A17B predecessor on eight and trails it on the rest by at most 2.6 points, at 1/3 the activated parameters, 1/3 the training tokens, and roughly 1/9 the training FLOPs.
  arXiv  Detail & Related papers  (2026-08-31T06:35:07Z)
• Similarity-Guided Curriculum Fine-Tuning of LLMs for Neural Architecture Synthesis [48.83701310501069]
  We introduce a MinHash-based similarity scheduling framework that constructs a progressive curriculum over neural architecture code for neural architecture search (NAS)<n>We evaluate the framework on OlympicCoder-7B within the LEMUR benchmark on CIFAR-10 image classification.<n>We report a cross-dataset transfer observation on SVHN, where direct base-model generation without curriculum yields 27% peak SR at substantially lower accuracy (60.5%) than the CIFAR-10 equivalent.
  arXiv  Detail & Related papers  (2026-07-13T14:14:30Z)
• GradAttn: Replacing Fixed Residual Connections with Task-Modulated Attention Pathways [2.105564340986074]
  GradAttn is a CNN-transformer framework that replaces fixed residual connections with attention-controlled gradient flow.<n>For representational analysis, we evaluated three GradAttn variants across eight diverse datasets.<n>Results demonstrate that GradAttn outperforms ResNet-18 on five of eight datasets.
  arXiv  Detail & Related papers  (2026-03-23T14:45:07Z)
• Unrolled Reconstruction with Integrated Super-Resolution for Accelerated 3D LGE MRI [0.07026564887314535]
  We propose a hybrid unrolled reconstruction framework in which an Enhanced Deep Super-Resolution (EDSR) network replaces the operator within each iteration of the optimization loop.<n>Across acceleration factors, the proposed method consistently improves PSNR and SSIM over standard unrolled reconstruction.<n>These results demonstrate that integrating super-resolution priors directly within model-based reconstruction provides measurable gains in accelerated 3D LGE MRI.
  arXiv  Detail & Related papers  (2026-03-18T21:48:48Z)
• Deep Learning Architectures for Code-Modulated Visual Evoked Potentials Detection [0.40822165794627957]
  Non-invasive brain interfaces (BCIs) based on Code-Modulated Visual Evoked Potentials (C-VEPs) require highly robust decoding methods to address temporal variability and session-dependent noise in EEG signals.<n>This study proposes and evaluates several deep learning architectures, including convolutional neural networks (CNNs) for 63-bit m-sequence reconstruction and classification, and Siamese networks for similarity-based decoding, alongside canonical correlation analysis (CCA) baselines.<n>The proposed deep models significantly outperformed traditional approaches, with distance-based decoding using Earth Mover's Distance (EMD) and constrained showing greater robustness
  arXiv  Detail & Related papers  (2025-11-26T22:02:22Z)
• An Efficient GNNs-to-KANs Distillation via Self-Attention Dynamic Sampling with Potential for Consumer Electronics Edge Deployment [12.385364522094612]
  This paper introduces an innovative framework for knowledge distillation from Graph Networks to Kolmogorov-Arnold Networks (KANs)<n>Through the incorporation of learnable frequency bases and phase-shift mechanisms, FR-KAN significantly improves its nonlinear fitting capability while effectively reducing computational complexity.<n>Experiments conducted on six real-world datasets demonstrate that SA-DSD achieves performance improvements of 3.05%-3.62% over three GNN teacher models and 15.61% over the FR-KAN+ model.
  arXiv  Detail & Related papers  (2025-08-30T16:53:42Z)
• Is Architectural Complexity Overrated? Competitive and Interpretable Knowledge Graph Completion with RelatE [6.959701672059059]
  RelatE is an interpretable and modular method that efficiently integrates dual representations for entities and relations.<n>It achieves competitive or superior performance on standard benchmarks.<n>Perturbation studies demonstrate improved robustness, with MRR reduced by up to 61% relative to TransE and by up to 19% compared to RotatE.
  arXiv  Detail & Related papers  (2025-05-25T04:36:52Z)
• 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. A novel method for converting the complex-valued convolutional layers and activations into spiking neural networks (SNNs) is developed. 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)
• DRACO: Differentiable Reconstruction for Arbitrary CBCT Orbits [3.331348121758607]
  This paper introduces a novel method for reconstructing cone beam computed tomography (CBCT) images for arbitrary orbits. The proposed method employs a shift-variant FBP algorithm optimized for arbitrary trajectories through a deep learning approach. The proposed method is a significant advancement in interventional medical imaging, particularly for robotic C-arm CT systems.
  arXiv  Detail & Related papers  (2024-10-18T22:59:36Z)
• DiTMoS: Delving into Diverse Tiny-Model Selection on Microcontrollers [34.282971510732736]
  We introduce DiTMoS, a novel DNN training and inference framework with a selector-classifiers architecture. A composition of weak models can exhibit high diversity and the union of them can significantly boost the accuracy upper bound. We deploy DiTMoS on the Neucleo STM32F767ZI board and evaluate it based on three time-series datasets for human activity recognition, keywords spotting, and emotion recognition.
  arXiv  Detail & Related papers  (2024-03-14T02:11:38Z)
• Reparameterization through Spatial Gradient Scaling [69.27487006953852]
  Reparameterization aims to improve the generalization of deep neural networks by transforming convolutional layers into equivalent multi-branched structures during training. We present a novel spatial gradient scaling method to redistribute learning focus among weights in convolutional networks.
  arXiv  Detail & Related papers  (2023-03-05T17:57:33Z)
• 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)
• SmoothNets: Optimizing CNN architecture design for differentially private deep learning [69.10072367807095]
  DPSGD requires clipping and noising of per-sample gradients. This introduces a reduction in model utility compared to non-private training. We distilled a new model architecture termed SmoothNet, which is characterised by increased robustness to the challenges of DP-SGD training.
  arXiv  Detail & Related papers  (2022-05-09T07:51:54Z)
• 4-bit Conformer with Native Quantization Aware Training for Speech Recognition [13.997832593421577]
  We propose to develop 4-bit ASR models with native quantization aware training, which leverages native integer operations to effectively optimize both training and inference. We conducted two experiments on state-of-the-art Conformer-based ASR models to evaluate our proposed quantization technique. For the first time investigated and revealed the viability of 4-bit quantization on a practical ASR system that is trained with large-scale datasets.
  arXiv  Detail & Related papers  (2022-03-29T23:57:15Z)
• PR-RRN: Pairwise-Regularized Residual-Recursive Networks for Non-rigid Structure-from-Motion [58.75694870260649]
  PR-RRN is a novel neural-network based method for Non-rigid Structure-from-Motion. We propose two new pairwise regularizations to further regularize the reconstruction. Our approach achieves state-of-the-art performance on CMU MOCAP and PASCAL3D+ dataset.
  arXiv  Detail & Related papers  (2021-08-17T08:39:02Z)
• Consistency and Monotonicity Regularization for Neural Knowledge Tracing [50.92661409499299]
  Knowledge Tracing (KT) tracking a human's knowledge acquisition is a central component in online learning and AI in Education. We propose three types of novel data augmentation, coined replacement, insertion, and deletion, along with corresponding regularization losses. Extensive experiments on various KT benchmarks show that our regularization scheme consistently improves the model performances.
  arXiv  Detail & Related papers  (2021-05-03T02:36:29Z)
• Three-Dimensional Embedded Attentive RNN (3D-EAR) Segmentor for Left Ventricle Delineation from Myocardial Velocity Mapping [1.8653386811342048]
  We propose a novel fully automated framework incorporating a 3D-UNet backbone architecture with Embedded multichannel Attention mechanism and LSTM based Recurrent neural networks (RNN) for the MVM-CMR datasets. By comparing the baseline model of 3D-UNet and ablation studies with and without embedded attentive LSTM modules and various loss functions, we can demonstrate that the proposed model has outperformed the state-of-the-art baseline models with significant improvement.
  arXiv  Detail & Related papers  (2021-04-26T11:04:43Z)
• FPCR-Net: Feature Pyramidal Correlation and Residual Reconstruction for Optical Flow Estimation [72.41370576242116]
  We propose a semi-supervised Feature Pyramidal Correlation and Residual Reconstruction Network (FPCR-Net) for optical flow estimation from frame pairs. It consists of two main modules: pyramid correlation mapping and residual reconstruction. Experiment results show that the proposed scheme achieves the state-of-the-art performance, with improvement by 0.80, 1.15 and 0.10 in terms of average end-point error (AEE) against competing baseline methods.
  arXiv  Detail & Related papers  (2020-01-17T07:13:51Z)

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.