Machines that learn to segment images: a crucial technology for connectomics.

By Viren Jain, H. Sebastian Seung, Srinivas C. Turaga. 2010

170 citations recorded by the source corpus.

Subfields: Aging, Biophysics, Cognitive Neuroscience

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aging

1. Anindya Pain
2. Shaifaly Sharma
3. Debi Prasanna Kanungo
4. Moritz Helmstaedter

In Biophysics

1. Johannes E. Schindelin
2. Pavel Tomancak
3. Albert Cardona
4. Moritz Helmstaedter
5. Stephan Saalfeld
6. Anindya Pain
7. Shaifaly Sharma
8. Debi Prasanna Kanungo

In Cognitive Neuroscience

1. J. Urgen Schmidhuber
2. Anindya Pain
3. Shaifaly Sharma
4. Debi Prasanna Kanungo
5. Moritz Helmstaedter
6. Joachim M. Buhmann
7. H. Sebastian Seung
8. Adeel Razi

Citations in the corpus

• Artificial Neural Network (ANN) and Regression Tree (CART) applications for the indirect estimation of unsaturated soil shear strength parameters (2014, methodology): “The in-situ tests include a field vane shear test, a standard penetration test, a cone penetration test, and piezocone and pressure meter readings (Jain et al., 2010).”
• DeepEM3D: approaching human‐level performance on 3D anisotropic EM image segmentation (2017, background): “A breakthrough for automatic dense EM reconstruction is in urgent need, and better machine learning algorithms are considered the most likely approach toward this goal (Jain et al., 2010; Helmstaedter et al., 2013).”
• TrakEM2 Software for Neural Circuit Reconstruction (2012, methodology): “Automated methods for neuronal reconstruction are currently the focus of intensive research in Computer Vision (for review see [9]).”
• Machine Learning for Predicting Epileptic Seizures Using EEG Signals: A Review (2020, background): “In connectomics, to understand the mapping of the connectivity of neural networks in the brain, deep networks are used to understand the connectivity of neural units from 3D electron microscopic images [82].”
• Quantitative neuroanatomy for connectomics in Drosophila (2015, background): “They are therefore sensitive to noise (Jain et al., 2010), particularly in anisotropic EM data where the smallest neurites may be thinner than the thickness of individual serial sections (Veeraraghavan et al., 2010; Helmstaedter, 2013).”
• Crowdsourcing the creation of image segmentation algorithms for connectomics (2015, methodology): “This study employed semiautomated methods, using advances in machine learning to automate most of the reconstruction (Jain et al., 2010b).”
• High-precision automated reconstruction of neurons with flood-filling networks (2017, methodology): “The use of computers those decisions began in earnest after improved volume electron microscopy (EM) methods 5 started yielding datasets for which complete analysis by human annotation would have been prohibitively laborious 6 , and the process soon came to rely heavily on machine learning (ML).”
• Cellular-resolution connectomics: challenges of dense neural circuit reconstruction (2013, background): “Improvements in algorithms have saturated at the level of voxel classification (‘voxel classifiers’ 27,28,32,37–39 ), and the current focus is on segmentation-based classifiers (‘super-voxel classifiers’ 31,34,40 ).”