Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Few-shot hypercolumn-based mitochondria segmentation in cardiac and outer hair cells in focused ion beam-scanning electron microscopy (FIB-SEM) data

Dietlmeier, Julia orcid logoORCID: 0000-0001-9980-0910, McGuinness, Kevin orcid logoORCID: 0000-0003-1336-6477, Rugonyi, Sandra, Wilson, Teresa, Nuttall, Alfred and O'Connor, Noel E. orcid logoORCID: 0000-0002-4033-9135 (2020) Few-shot hypercolumn-based mitochondria segmentation in cardiac and outer hair cells in focused ion beam-scanning electron microscopy (FIB-SEM) data. Pattern Recognition Letters, 128 (1). pp. 521-528. ISSN 0167-8655

Abstract
We present a novel AI-based approach to the few-shot automated segmentation of mitochondria in large-scale electron microscopy images. Our framework leverages convolutional features from a pre-trained deep multilayer convolutional neural network, such as VGG-16. We then train a binary gradient boosting classifier on the resulting high-dimensional feature hypercolumns. We extract VGG-16 features from the first four convolutional blocks and apply bilinear upsampling to resize the obtained maps to the input image size. This procedure yields a 2688-dimensional feature hypercolumn for each pixel in a 224 x 224 input image. We then apply L1-regularized logistic regression for supervised active feature selection to reduce dependencies among the features, to reduce overfitting, as well as to speed-up gradient boosting-based training. During inference we block process 1728 x 2022 large microscopy images. Our experiments show that in such a formulation of transfer learning our processing pipeline is able to achieve high-accuracy results on very challenging datasets containing a large number of irregularly shaped mitochondria in cardiac and outer hair cells. Our proposed few-shot training approach gives competitive performance with the state-of-the-art using far less training data.
Metadata
Item Type:Article (Published)
Refereed:Yes
Subjects:Computer Science > Algorithms
Computer Science > Artificial intelligence
Computer Science > Image processing
Computer Science > Machine learning
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Electronic Engineering
Research Initiatives and Centres > INSIGHT Centre for Data Analytics
Publisher:Elsevier
Official URL:http://dx.doi.org/10.1016/j.patrec.2019.10.031
Copyright Information:© 2019
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
ID Code:23950
Deposited On:11 Dec 2019 09:31 by Julia Dietlmeier . Last Modified 29 Oct 2021 03:30
Documents

Full text available as:

[thumbnail of Julia_PRL_paper_Camera_ready_version.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
2MB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record