This is not the latest version of this item. The latest version can be found here.
Self-supervised feature extraction for 3D axon segmentation
Name
2004.09629.pdf
Description
Accepted version
Size
1.77 MB
Format
Adobe PDF
Checksum (MD5)
8709721be9a9cae994a5f871186cb8e6
Author(s) • • • • •
Klinghoffer, T
Morales, P
Park, YG
Evans, N
Chung, K
Brattain, LJ
Date Issued
April 2020
Journal
IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Publisher
IEEE
Citation
Klinghoffer, T, Morales, P, Park, YG, Evans, N, Chung, K et al. 2020. "Self-supervised feature extraction for 3D axon segmentation." IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2020-June.
Version
Author's final manuscript
Abstract
© 2020 IEEE. Existing learning-based methods to automatically trace axons in 3D brain imagery often rely on manually annotated segmentation labels. Labeling is a labor-intensive process and is not scalable to whole-brain analysis, which is needed for improved understanding of brain function. We propose a self-supervised auxiliary task that utilizes the tube-like structure of axons to build a feature extractor from unlabeled data. The proposed auxiliary task constrains a 3D convolutional neural network (CNN) to predict the order of permuted slices in an input 3D volume. By solving this task, the 3D CNN is able to learn features without ground-truth labels that are useful for downstream segmentation with the 3D U-Net model. To the best of our knowledge, our model is the first to perform automated segmentation of axons imaged at subcellular resolution with the SHIELD technique. We demonstrate improved segmentation performance over the 3D U-Net model on both the SHIELD PVGPe dataset and the BigNeuron Project, single neuron Janelia dataset.
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
10.1109/CVPRW50498.2020.00497