Back to Search
Start Over
DeepEM3D: approaching human-level performance on 3D anisotropic EM image segmentation
- Source :
- Bioinformatics. 33:2555-2562
- Publication Year :
- 2017
- Publisher :
- Oxford University Press (OUP), 2017.
-
Abstract
- Motivation Progress in 3D electron microscopy (EM) imaging has greatly facilitated neuroscience research in high-throughput data acquisition. Correspondingly, high-throughput automated image analysis methods are necessary to work on par with the speed of data being produced. One such example is the need for automated EM image segmentation for neurite reconstruction. However, the efficiency and reliability of current methods are still lagging far behind human performance. Results Here, we propose DeepEM3D, a deep learning method for segmenting 3D anisotropic brain electron microscopy images. In this method, the deep learning model can efficiently build feature representation and incorporate sufficient multi-scale contextual information. We propose employing a combination of novel boundary map generation methods with optimized model ensembles to address the inherent challenges of segmenting anisotropic images. We evaluated our method by participating in the 3D segmentation of neurites in EM images (SNEMI3D) challenge. Our submission is ranked #1 on the current leaderboard as of Oct 15, 2016. More importantly, our result was very close to human-level performance in terms of the challenge evaluation metric: namely, a Rand error of 0.06015 versus the human value of 0.05998. Availability and Implementation The code is available at https://github.com/divelab/deepem3d/ Supplementary information Supplementary data are available at Bioinformatics online.
- Subjects :
- 0301 basic medicine
Statistics and Probability
Computer science
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Scale-space segmentation
Image processing
Biochemistry
03 medical and health sciences
Imaging, Three-Dimensional
0302 clinical medicine
Image Processing, Computer-Assisted
Neurites
Animals
Humans
Computer vision
Molecular Biology
business.industry
Deep learning
Neurosciences
Reproducibility of Results
Image segmentation
Original Papers
Computer Science Applications
Microscopy, Electron
Computational Mathematics
030104 developmental biology
Computational Theory and Mathematics
Feature (computer vision)
Metric (mathematics)
Artificial intelligence
business
Algorithms
Software
030217 neurology & neurosurgery
Subjects
Details
- ISSN :
- 13674811 and 13674803
- Volume :
- 33
- Database :
- OpenAIRE
- Journal :
- Bioinformatics
- Accession number :
- edsair.doi.dedup.....69ed5c9ecd1dda4d62ba50c55054ab49