A reusable pipeline for large-scale fiber segmentation on unidirectional fiber beds using fully convolutional neural networks

• URL: http://arxiv.org/abs/2101.04823v2
• Date: Fri, 15 Jan 2021 00:33:14 GMT
• Title: A reusable pipeline for large-scale fiber segmentation on unidirectional fiber beds using fully convolutional neural networks
• Authors: Alexandre Fioravante de Siqueira and Daniela Mayumi Ushizima and St\'efan van der Walt
• Abstract summary: We present an open computational pipeline to detect fibers in ex-situ X-ray computed tomography fiber beds. To separate the fibers in these samples, we tested four different architectures of fully convolutional neural networks. When comparing our neural network approach to a semi-supervised one, we obtained Dice and Matthews coefficients greater than $92.28 pm 9.65%$, reaching up to $98.42 pm 0.03 %$.
• Score: 68.8204255655161
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Fiber-reinforced ceramic-matrix composites are advanced materials resistant to high temperatures, with application to aerospace engineering. Their analysis depends on the detection of embedded fibers, with semi-supervised techniques usually employed to separate fibers within the fiber beds. Here we present an open computational pipeline to detect fibers in ex-situ X-ray computed tomography fiber beds. To separate the fibers in these samples, we tested four different architectures of fully convolutional neural networks. When comparing our neural network approach to a semi-supervised one, we obtained Dice and Matthews coefficients greater than $92.28 \pm 9.65\%$, reaching up to $98.42 \pm 0.03 \%$, showing that the network results are close to the human-supervised ones in these fiber beds, in some cases separating fibers that human-curated algorithms could not find. The software we generated in this project is open source, released under a permissive license, and can be freely adapted and re-used in other domains. All data and instructions on how to download and use it are also available.

Related papers

• Ensemble learning of the atrial fiber orientation with physics-informed neural networks [0.0]
  We propose Fibernet, a method for the automatic identification of the anisotropic conduction -- and thus fibers -- in the atria from local electrical recordings. We use an ensemble of neural networks to produce multiple samples, all fitting the observed data, and compute posterior statistics. Our approach can estimate the fiber orientation and conduction velocities in under 7 minutes with quantified uncertainty.
  arXiv  Detail & Related papers  (2024-10-30T18:45:19Z)
• FRC-TOuNN: Topology Optimization of Continuous Fiber Reinforced Composites using Neural Network [4.355018965813992]
  We propose a mesh-independent representation based on a neural network (NN) to capture the matrix topology and fiber distribution. The implicit NN-based representation enables geometric and material queries at a higher resolution than a mesh discretization. We show that the optimized continuous fiber reinforced composites can be directly fabricated at high resolution using additive manufacturing.
  arXiv  Detail & Related papers  (2022-05-07T23:10:34Z)
• Deep fiber clustering: Anatomically informed fiber clustering with self-supervised deep learning for fast and effective tractography parcellation [22.754116315299182]
  We propose a novel deep learning framework for white matter fiber clustering, Deep Fiber Clustering (DFC) DFC solves the unsupervised clustering problem as a self-supervised learning task with a domain-specific pretext task to predict pairwise fiber distances. Experimental results demonstrate superior performance of DFC in terms of cluster compactness, generalization ability, anatomical coherence, and computational efficiency.
  arXiv  Detail & Related papers  (2022-05-02T02:41:02Z)
• End-to-End Sensitivity-Based Filter Pruning [49.61707925611295]
  We present a sensitivity-based filter pruning algorithm (SbF-Pruner) to learn the importance scores of filters of each layer end-to-end. Our method learns the scores from the filter weights, enabling it to account for the correlations between the filters of each layer.
  arXiv  Detail & Related papers  (2022-04-15T10:21:05Z)
• On the Neural Tangent Kernel Analysis of Randomly Pruned Neural Networks [91.3755431537592]
  We study how random pruning of the weights affects a neural network's neural kernel (NTK) In particular, this work establishes an equivalence of the NTKs between a fully-connected neural network and its randomly pruned version.
  arXiv  Detail & Related papers  (2022-03-27T15:22:19Z)
• Scalable Lipschitz Residual Networks with Convex Potential Flows [120.27516256281359]
  We show that using convex potentials in a residual network gradient flow provides a built-in $1$-Lipschitz transformation. A comprehensive set of experiments on CIFAR-10 demonstrates the scalability of our architecture and the benefit of our approach for $ell$ provable defenses.
  arXiv  Detail & Related papers  (2021-10-25T07:12:53Z)
• Deep Fiber Clustering: Anatomically Informed Unsupervised Deep Learning for Fast and Effective White Matter Parcellation [21.835894924330752]
  We propose a novel WMFC framework based on unsupervised deep learning. We use a convolutional neural network to learn embeddings of input fibers, using pairwise fiber distances as pseudo annotations. Results demonstrate superior performance and efficiency of the proposed approach.
  arXiv  Detail & Related papers  (2021-07-11T01:36:57Z)
• Characterization and stability measurement of deployed multicore fibers for quantum applications [50.591267188664666]
  We characterize for the first time, in terms of phase stability, multiple strands of a 4-core multicore fiber installed underground in the city of L'Aquila. We investigate the possibility of using such an infrastructure to implement quantum-enhanced schemes, such as high-dimensional quantum key distribution, quantum-based environmental sensors.
  arXiv  Detail & Related papers  (2021-03-11T18:24:59Z)
• FabricNet: A Fiber Recognition Architecture Using Ensemble ConvNets [0.0]
  We propose FabricNet, a pioneering approach for the image-based textile fiber recognition system. The FabricNet can recognize a large scale of fibers by only utilizing a surface image of fabric. The experiment is conducted on recognizing 50 different types of textile fibers.
  arXiv  Detail & Related papers  (2021-01-14T12:11:23Z)
• Fitting the Search Space of Weight-sharing NAS with Graph Convolutional Networks [100.14670789581811]
  We train a graph convolutional network to fit the performance of sampled sub-networks. With this strategy, we achieve a higher rank correlation coefficient in the selected set of candidates.
  arXiv  Detail & Related papers  (2020-04-17T19:12:39Z)

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.