Large-Scale Automatic Reconstruction of Neuronal Processes from Electron Microscopy Images

Autor: Seymour Knowles-Barley, Amelio Vazquez-Reina, Narayanan Kasthuri, Thouis R. Jones, Hanspeter Pfister, Mike Roberts, Jeff W. Lichtman, Eric L. Miller, Verena Kaynig
Jazyk: angličtina
Rok vydání: 2015
Předmět:
FOS: Computer and information sciences
Conditional random field
Computer science
Computer Vision and Pattern Recognition (cs.CV)
Computer Science - Computer Vision and Pattern Recognition
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Scale-space segmentation
Health Informatics
Sensitivity and Specificity
Bottleneck
Article
Pattern Recognition
Automated
Machine Learning
Imaging
Three-Dimensional
Image Interpretation
Computer-Assisted
Radiology
Nuclear Medicine and imaging
Segmentation
Computer vision
Scaling
Neurons
Radiological and Ultrasound Technology
business.industry
Brain
Reproducibility of Results
Image Enhancement
Computer Graphics and Computer-Aided Design
Random forest
Microscopy
Electron
Quantitative Biology - Neurons and Cognition
FOS: Biological sciences
Subtraction Technique
Neurons and Cognition (q-bio.NC)
Computer Vision and Pattern Recognition
Artificial intelligence
business
Classifier (UML)
Smoothing
Algorithms
Popis: Automated sample preparation and electron microscopy enables acquisition of very large image data sets. These technical advances are of special importance to the field of neuroanatomy, as 3D reconstructions of neuronal processes at the nm scale can provide new insight into the fine grained structure of the brain. Segmentation of large-scale electron microscopy data is the main bottleneck in the analysis of these data sets. In this paper we present a pipeline that provides state-of-the art reconstruction performance while scaling to data sets in the GB-TB range. First, we train a random forest classifier on interactive sparse user annotations. The classifier output is combined with an anisotropic smoothing prior in a Conditional Random Field framework to generate multiple segmentation hypotheses per image. These segmentations are then combined into geometrically consistent 3D objects by segmentation fusion. We provide qualitative and quantitative evaluation of the automatic segmentation and demonstrate large-scale 3D reconstructions of neuronal processes from a 27 , 000 μ m 3 volume of brain tissue over a cube of 30 μ m in each dimension corresponding to 1000 consecutive image sections. We also introduce Mojo, a proofreading tool including semi-automated correction of merge errors based on sparse user scribbles.
Databáze: OpenAIRE
Externí odkaz: