Deep models for brain EM image segmentation: novel insights and improved performance - PubMed (original) (raw)
Deep models for brain EM image segmentation: novel insights and improved performance
Ahmed Fakhry et al. Bioinformatics. 2016.
Abstract
Motivation: Accurate segmentation of brain electron microscopy (EM) images is a critical step in dense circuit reconstruction. Although deep neural networks (DNNs) have been widely used in a number of applications in computer vision, most of these models that proved to be effective on image classification tasks cannot be applied directly to EM image segmentation, due to the different objectives of these tasks. As a result, it is desirable to develop an optimized architecture that uses the full power of DNNs and tailored specifically for EM image segmentation.
Results: In this work, we proposed a novel design of DNNs for this task. We trained a pixel classifier that operates on raw pixel intensities with no preprocessing to generate probability values for each pixel being a membrane or not. Although the use of neural networks in image segmentation is not completely new, we developed novel insights and model architectures that allow us to achieve superior performance on EM image segmentation tasks. Our submission based on these insights to the 2D EM Image Segmentation Challenge achieved the best performance consistently across all the three evaluation metrics. This challenge is still ongoing and the results in this paper are as of June 5, 2015.
Availability and implementation: https://github.com/ahmed-fakhry/dive
Contact: : sji@eecs.wsu.edu.
© The Author 2016. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.
Similar articles
- DeepEM3D: approaching human-level performance on 3D anisotropic EM image segmentation.
Zeng T, Wu B, Ji S. Zeng T, et al. Bioinformatics. 2017 Aug 15;33(16):2555-2562. doi: 10.1093/bioinformatics/btx188. Bioinformatics. 2017. PMID: 28379412 Free PMC article. - Residual Deconvolutional Networks for Brain Electron Microscopy Image Segmentation.
Fakhry A, Zeng T, Ji S. Fakhry A, et al. IEEE Trans Med Imaging. 2017 Feb;36(2):447-456. doi: 10.1109/TMI.2016.2613019. Epub 2016 Sep 23. IEEE Trans Med Imaging. 2017. PMID: 28113967 - Deep Learning Segmentation of Optical Microscopy Images Improves 3-D Neuron Reconstruction.
Li R, Zeng T, Peng H, Ji S. Li R, et al. IEEE Trans Med Imaging. 2017 Jul;36(7):1533-1541. doi: 10.1109/TMI.2017.2679713. Epub 2017 Mar 8. IEEE Trans Med Imaging. 2017. PMID: 28287966 - Brain tumor segmentation with Deep Neural Networks.
Havaei M, Davy A, Warde-Farley D, Biard A, Courville A, Bengio Y, Pal C, Jodoin PM, Larochelle H. Havaei M, et al. Med Image Anal. 2017 Jan;35:18-31. doi: 10.1016/j.media.2016.05.004. Epub 2016 May 19. Med Image Anal. 2017. PMID: 27310171 - Quick guide on radiology image pre-processing for deep learning applications in prostate cancer research.
Masoudi S, Harmon SA, Mehralivand S, Walker SM, Raviprakash H, Bagci U, Choyke PL, Turkbey B. Masoudi S, et al. J Med Imaging (Bellingham). 2021 Jan;8(1):010901. doi: 10.1117/1.JMI.8.1.010901. Epub 2021 Jan 6. J Med Imaging (Bellingham). 2021. PMID: 33426151 Free PMC article. Review.
Cited by
- Deep learning-based label-free imaging of lymphatics and aqueous veins in the eye using optical coherence tomography.
Gong P, Tang X, Chen J, You H, Wang Y, Yu PK, Yu DY, Cense B. Gong P, et al. Sci Rep. 2024 Mar 13;14(1):6126. doi: 10.1038/s41598-024-56273-1. Sci Rep. 2024. PMID: 38480842 Free PMC article. - PS-Net: human perception-guided segmentation network for EM cell membrane.
Shi R, Bi K, Du K, Ma L, Fang F, Duan L, Jiang T, Huang T. Shi R, et al. Bioinformatics. 2023 Aug 1;39(8):btad464. doi: 10.1093/bioinformatics/btad464. Bioinformatics. 2023. PMID: 37505461 Free PMC article. - Frontal Cortex Segmentation of Brain PET Imaging Using Deep Neural Networks.
Zhan Q, Liu Y, Liu Y, Hu W. Zhan Q, et al. Front Neurosci. 2021 Dec 8;15:796172. doi: 10.3389/fnins.2021.796172. eCollection 2021. Front Neurosci. 2021. PMID: 34955739 Free PMC article. - CleftNet: Augmented Deep Learning for Synaptic Cleft Detection From Brain Electron Microscopy.
Liu Y, Ji S. Liu Y, et al. IEEE Trans Med Imaging. 2021 Dec;40(12):3507-3518. doi: 10.1109/TMI.2021.3089547. Epub 2021 Nov 30. IEEE Trans Med Imaging. 2021. PMID: 34129494 Free PMC article. - Where Do We Stand in Regularization for Life Science Studies?
Tozzo V, Azencott CA, Fiorini S, Fava E, Trucco A, Barla A. Tozzo V, et al. J Comput Biol. 2022 Mar;29(3):213-232. doi: 10.1089/cmb.2019.0371. Epub 2021 Apr 29. J Comput Biol. 2022. PMID: 33926217 Free PMC article.
MeSH terms
LinkOut - more resources
Full Text Sources
Other Literature Sources
Research Materials