Morphological Neuron Classification Using Machine Learning
Classification and quantitative characterization of neuronal morphologies from histological neuronal reconstruction are challenging since still unclear how to delineate a neuronal cell class and which would be the best features to define them. The morphological neuron characterization represents pri...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Book |
| Published: |
Frontiers Media S.A.,
2016-11-01T00:00:00Z.
|
| Subjects: | |
| Online Access: | Connect to this object online. |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Classification and quantitative characterization of neuronal morphologies from histological neuronal reconstruction are challenging since still unclear how to delineate a neuronal cell class and which would be the best features to define them. The morphological neuron characterization represents primary sources to address anatomical comparisons, morphometric analysis of cells or brain modeling. The objective of this paper are i), to develop and integrate a pipeline that goes from morphological features extraction to classification and ii), to assess and compare the accuracy of machine learning algorithms to classify neuron morphologies. The algorithms were trained on 430 digitally reconstructed neurons subjectively classified into layers and/or m-types using young and/or adult development state population of the somatosensory cortex in rats. For supervised algorithms, Linear Discriminant Analysis provided better classification results by comparison with others. For unsupervised, algorithms providing slightly better results are the affinity propagation and the Ward algorithms. |
|---|---|
| Item Description: | 1662-5129 10.3389/fnana.2016.00102 |