Learning Wavelet-Sparse FDK for 3D Cone-Beam CT Reconstruction

• URL: http://arxiv.org/abs/2505.13579v1
• Date: Mon, 19 May 2025 15:31:40 GMT
• Title: Learning Wavelet-Sparse FDK for 3D Cone-Beam CT Reconstruction
• Abstract summary: We introduce an enhanced FDK-based neural network that maintains the classical algorithm's interpretability.<n>We leverage wavelet transformations to create sparse representations of the cosine weights and filters.<n>This strategic sparsification reduces the parameter count by $93.75%$ without compromising performance.
• Score: 3.951261552751241
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Cone-Beam Computed Tomography (CBCT) is essential in medical imaging, and the Feldkamp-Davis-Kress (FDK) algorithm is a popular choice for reconstruction due to its efficiency. However, FDK is susceptible to noise and artifacts. While recent deep learning methods offer improved image quality, they often increase computational complexity and lack the interpretability of traditional methods. In this paper, we introduce an enhanced FDK-based neural network that maintains the classical algorithm's interpretability by selectively integrating trainable elements into the cosine weighting and filtering stages. Recognizing the challenge of a large parameter space inherent in 3D CBCT data, we leverage wavelet transformations to create sparse representations of the cosine weights and filters. This strategic sparsification reduces the parameter count by $93.75\%$ without compromising performance, accelerates convergence, and importantly, maintains the inference computational cost equivalent to the classical FDK algorithm. Our method not only ensures volumetric consistency and boosts robustness to noise, but is also designed for straightforward integration into existing CT reconstruction pipelines. This presents a pragmatic enhancement that can benefit clinical applications, particularly in environments with computational limitations.

Related papers

• CSGaussian: Progressive Rate-Distortion Compression and Segmentation for 3D Gaussian Splatting [57.73006852239138]
  We present the first unified framework for rate-distortion-optimized compression and segmentation of 3D Gaussian Splatting (3DGS)<n>Inspired by recent advances in rate-distortion-optimized 3DGS compression, this work integrates semantic learning into the compression pipeline to support decoder-side applications.<n>Our scheme features a lightweight implicit neural representation-based hyperprior, enabling efficient entropy coding of both color and semantic attributes.
  arXiv  Detail & Related papers  (2026-01-19T08:21:45Z)
• CAMP-HiVe: Cyclic Pair Merging based Efficient DNN Pruning with Hessian-Vector Approximation for Resource-Constrained Systems [3.343542849202802]
  We introduce CAMP-HiVe, a cyclic pair merging-based pruning with Hessian Vector approximation.<n>Our experimental results demonstrate that our proposed method achieves significant reductions in computational requirements.<n>It outperforms the existing state-of-the-art neural pruning methods.
  arXiv  Detail & Related papers  (2025-11-09T07:58:36Z)
• Fourier Optics and Deep Learning Methods for Fast 3D Reconstruction in Digital Holography [0.0]
  Computer-generated holography (CGH) is a promising user-defined waveforms with digital holograms.<n>Performance metrics are shown to be improved by using 2D median as well as to HoloNet deep learning CGH.
  arXiv  Detail & Related papers  (2025-08-08T21:14:36Z)
• Large-Scale Model Enabled Semantic Communication Based on Robust Knowledge Distillation [53.16213723669751]
  Large-scale models (LSMs) can be an effective framework for semantic representation and understanding.<n>However, their direct deployment is often hindered by high computational complexity and resource requirements.<n>This paper proposes a novel knowledge distillation based semantic communication framework.
  arXiv  Detail & Related papers  (2025-08-04T07:47:18Z)
• Skelite: Compact Neural Networks for Efficient Iterative Skeletonization [38.6452617345504]
  Skeletonization extracts thin representations from images that compactly encode their geometry and topology.<n>We propose a novel framework for training iterative skeletonization algorithms with a learnable component.<n>Our method demonstrates a 100 times speedup over topology-constrained algorithms.
  arXiv  Detail & Related papers  (2025-03-10T14:27:25Z)
• Accelerating Error Correction Code Transformers [56.75773430667148]
  We introduce a novel acceleration method for transformer-based decoders. We achieve a 90% compression ratio and reduce arithmetic operation energy consumption by at least 224 times on modern hardware.
  arXiv  Detail & Related papers  (2024-10-08T11:07:55Z)
• Advancing The Rate-Distortion-Computation Frontier For Neural Image Compression [6.167676495563641]
  Rate-distortion-computation study shows that neither floating-point operations (FLOPs) nor runtime are sufficient on their own to accurately rank neural compression methods. We identify a novel neural compression architecture that yields state-of-the-art RD performance with rate savings of 23.1% over BPG.
  arXiv  Detail & Related papers  (2023-09-26T19:47:31Z)
• PRISTA-Net: Deep Iterative Shrinkage Thresholding Network for Coded Diffraction Patterns Phase Retrieval [6.982256124089]
  Phase retrieval is a challenge nonlinear inverse problem in computational imaging and image processing. We have developed PRISTA-Net, a deep unfolding network based on the first-order iterative threshold threshold algorithm (ISTA) All parameters in the proposed PRISTA-Net framework, including the nonlinear transformation, threshold, and step size, are learned-to-end instead of being set.
  arXiv  Detail & Related papers  (2023-09-08T07:37:15Z)
• UNETR++: Delving into Efficient and Accurate 3D Medical Image Segmentation [93.88170217725805]
  We propose a 3D medical image segmentation approach, named UNETR++, that offers both high-quality segmentation masks as well as efficiency in terms of parameters, compute cost, and inference speed. The core of our design is the introduction of a novel efficient paired attention (EPA) block that efficiently learns spatial and channel-wise discriminative features. Our evaluations on five benchmarks, Synapse, BTCV, ACDC, BRaTs, and Decathlon-Lung, reveal the effectiveness of our contributions in terms of both efficiency and accuracy.
  arXiv  Detail & Related papers  (2022-12-08T18:59:57Z)
• NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstruction [79.13750275141139]
  This paper proposes a novel and fast self-supervised solution for sparse-view CBCT reconstruction. The desired attenuation coefficients are represented as a continuous function of 3D spatial coordinates, parameterized by a fully-connected deep neural network. A learning-based encoder entailing hash coding is adopted to help the network capture high-frequency details.
  arXiv  Detail & Related papers  (2022-09-29T04:06:00Z)
• Weakly-supervised Learning For Catheter Segmentation in 3D Frustum Ultrasound [74.22397862400177]
  We propose a novel Frustum ultrasound based catheter segmentation method. The proposed method achieved the state-of-the-art performance with an efficiency of 0.25 second per volume.
  arXiv  Detail & Related papers  (2020-10-19T13:56:22Z)
• A computationally efficient reconstruction algorithm for circular cone-beam computed tomography using shallow neural networks [0.0]
  We introduce the Neural Network Feldkamp-Davis-Kress (NN-FDK) algorithm. It adds a machine learning component to the FDK algorithm to improve its reconstruction accuracy while maintaining its computational efficiency. We show that the training time of an NN-FDK network is orders of magnitude lower than the considered deep neural networks, with only a slight reduction in reconstruction accuracy.
  arXiv  Detail & Related papers  (2020-10-01T14:10:23Z)
• Perceptron Synthesis Network: Rethinking the Action Scale Variances in Videos [48.57686258913474]
  Video action recognition has been partially addressed by the CNNs stacking of fixed-size 3D kernels. We propose to learn the optimal-scale kernels from the data. An textitaction perceptron synthesizer is proposed to generate the kernels from a bag of fixed-size kernels.
  arXiv  Detail & Related papers  (2020-07-22T14:22:29Z)

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.