Skelite: Compact Neural Networks for Efficient Iterative Skeletonization

• URL: http://arxiv.org/abs/2503.07369v1
• Date: Mon, 10 Mar 2025 14:27:25 GMT
• Title: Skelite: Compact Neural Networks for Efficient Iterative Skeletonization
• Authors: Luis D. Reyes Vargas, Martin J. Menten, Johannes C. Paetzold, Nassir Navab, Mohammad Farid Azampour,
• Abstract summary: 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.
• Score: 38.6452617345504
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Skeletonization extracts thin representations from images that compactly encode their geometry and topology. These representations have become an important topological prior for preserving connectivity in curvilinear structures, aiding medical tasks like vessel segmentation. Existing compatible skeletonization algorithms face significant trade-offs: morphology-based approaches are computationally efficient but prone to frequent breakages, while topology-preserving methods require substantial computational resources. We propose a novel framework for training iterative skeletonization algorithms with a learnable component. The framework leverages synthetic data, task-specific augmentation, and a model distillation strategy to learn compact neural networks that produce thin, connected skeletons with a fully differentiable iterative algorithm. Our method demonstrates a 100 times speedup over topology-constrained algorithms while maintaining high accuracy and generalizing effectively to new domains without fine-tuning. Benchmarking and downstream validation in 2D and 3D tasks demonstrate its computational efficiency and real-world applicability

Related papers

• A skeletonization algorithm for gradient-based optimization [13.2737105544687]
  The skeleton of a digital image is a compact representation of its topology, geometry, and scale. Most existing skeletonization algorithms are not differentiable, making it impossible to integrate them with gradient-based optimization. This work introduces the first three-dimensional skeletonization algorithm that is both compatible with gradient-based optimization and preserves an object's topology.
  arXiv  Detail & Related papers  (2023-09-05T18:40:14Z)
• A Generalization of Continuous Relaxation in Structured Pruning [0.3277163122167434]
  Trends indicate that deeper and larger neural networks with an increasing number of parameters achieve higher accuracy than smaller neural networks. We generalize structured pruning with algorithms for network augmentation, pruning, sub-network collapse and removal. The resulting CNN executes efficiently on GPU hardware without computationally expensive sparse matrix operations.
  arXiv  Detail & Related papers  (2023-08-28T14:19:13Z)
• Cascaded multitask U-Net using topological loss for vessel segmentation and centerline extraction [2.264332709661011]
  We propose to replace the soft-skeleton algorithm by a U-Net which computes the vascular skeleton directly from the segmentation. We build upon this network a cascaded U-Net trained with the clDice loss to embed topological constraints during the segmentation.
  arXiv  Detail & Related papers  (2023-07-21T14:12:28Z)
• Deep Efficient Continuous Manifold Learning for Time Series Modeling [11.876985348588477]
  A symmetric positive definite matrix is being studied in computer vision, signal processing, and medical image analysis. In this paper, we propose a framework to exploit a diffeomorphism mapping between Riemannian manifold and a Cholesky space. For dynamic modeling of time-series data, we devise a continuous manifold learning method by systematically integrating a manifold ordinary differential equation and a gated recurrent neural network.
  arXiv  Detail & Related papers  (2021-12-03T01:38:38Z)
• An End-To-End-Trainable Iterative Network Architecture for Accelerated Radial Multi-Coil 2D Cine MR Image Reconstruction [4.233498905999929]
  We propose a CNN-architecture for image reconstruction of accelerated 2D radial cine MRI with multiple receiver coils. We investigate the proposed training-strategy and compare our method to other well-known reconstruction techniques with learned and non-learned regularization methods.
  arXiv  Detail & Related papers  (2021-02-01T11:42:04Z)
• Spatio-Temporal Inception Graph Convolutional Networks for Skeleton-Based Action Recognition [126.51241919472356]
  We design a simple and highly modularized graph convolutional network architecture for skeleton-based action recognition. Our network is constructed by repeating a building block that aggregates multi-granularity information from both the spatial and temporal paths.
  arXiv  Detail & Related papers  (2020-11-26T14:43:04Z)
• Progressive Spatio-Temporal Graph Convolutional Network for Skeleton-Based Human Action Recognition [97.14064057840089]
  We propose a method to automatically find a compact and problem-specific network for graph convolutional networks in a progressive manner. Experimental results on two datasets for skeleton-based human action recognition indicate that the proposed method has competitive or even better classification performance.
  arXiv  Detail & Related papers  (2020-11-11T09:57:49Z)
• Temporal Attention-Augmented Graph Convolutional Network for Efficient Skeleton-Based Human Action Recognition [97.14064057840089]
  Graphal networks (GCNs) have been very successful in modeling non-Euclidean data structures. Most GCN-based action recognition methods use deep feed-forward networks with high computational complexity to process all skeletons in an action. We propose a temporal attention module (TAM) for increasing the efficiency in skeleton-based action recognition.
  arXiv  Detail & Related papers  (2020-10-23T08:01:55Z)
• Belief Propagation Reloaded: Learning BP-Layers for Labeling Problems [83.98774574197613]
  We take one of the simplest inference methods, a truncated max-product Belief propagation, and add what is necessary to make it a proper component of a deep learning model. This BP-Layer can be used as the final or an intermediate block in convolutional neural networks (CNNs) The model is applicable to a range of dense prediction problems, is well-trainable and provides parameter-efficient and robust solutions in stereo, optical flow and semantic segmentation.
  arXiv  Detail & Related papers  (2020-03-13T13:11:35Z)
• Large-Scale Gradient-Free Deep Learning with Recursive Local Representation Alignment [84.57874289554839]
  Training deep neural networks on large-scale datasets requires significant hardware resources. Backpropagation, the workhorse for training these networks, is an inherently sequential process that is difficult to parallelize. We propose a neuro-biologically-plausible alternative to backprop that can be used to train deep networks.
  arXiv  Detail & Related papers  (2020-02-10T16:20:02Z)

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.