Journal article
ANMAF: an automated neuronal morphology analysis framework using convolutional neural networks
Scientific reports, Vol.11(1), pp.8179-8179
04/14/2021
DOI: 10.1038/s41598-021-87471-w
PMCID: PMC8046969
PMID: 33854113
Abstract
Measurement of neuronal size is challenging due to their complex histology. Current practice includes manual or pseudo-manual measurement of somatic areas, which is labor-intensive and prone to human biases and intra-/inter-observer variances. We developed a novel high-throughput neuronal morphology analysis framework (ANMAF), using convolutional neural networks (CNN) to automatically contour the somatic area of fluorescent neurons in acute brain slices. Our results demonstrate considerable agreements between human annotators and ANMAF on detection, segmentation, and the area of somatic regions in neurons expressing a genetically encoded fluorophore. However, in contrast to humans, who exhibited significant variability in repeated measurements, ANMAF produced consistent neuronal contours. ANMAF was generalizable across different imaging protocols and trainable even with a small number of humanly labeled neurons. Our framework can facilitate more rigorous and quantitative studies of neuronal morphology by enabling the segmentation of many fluorescent neurons in thick brain slices in a standardized manner.
Details
- Title: Subtitle
- ANMAF: an automated neuronal morphology analysis framework using convolutional neural networks
- Creators
- Ling Tong - Iowa City, 52242 Iowa United StatesRachel Langton - Iowa City, 52242 Iowa United StatesJoseph Glykys - Iowa City, 52242 Iowa United StatesStephen Baek - Iowa City, 52242 Iowa United States
- Resource Type
- Journal article
- Publication Details
- Scientific reports, Vol.11(1), pp.8179-8179
- DOI
- 10.1038/s41598-021-87471-w
- PMID
- 33854113
- PMCID
- PMC8046969
- NLM abbreviation
- Sci Rep
- eISSN
- 2045-2322
- Publisher
- Nature Publishing Group UK; London
- Grant note
- 1R01NS115800 / ;
- Language
- English
- Date published
- 04/14/2021
- Academic Unit
- Neurology; Electrical and Computer Engineering; Stead Family Department of Pediatrics; Iowa Neuroscience Institute; Industrial and Systems Engineering; Radiation Oncology; Business Analytics; Neurology (Pediatrics)
- Record Identifier
- 9984065771502771
Metrics
29 Record Views