Back

COMBINe: Automated Detection and Classification of Neurons and Astrocytes in Tissue Cleared Mouse Brains

Cai, Y.; Zhang, X.; Li, C.; Ghashghaei, T.; Greenbaum, A.

2022-12-06 neuroscience
10.1101/2022.12.06.519291 bioRxiv
Show abstract

Tissue clearing renders entire organs transparent to enable combination with light sheet fluorescence microscopy and accelerate whole tissue imaging. Yet, challenges remain in analyzing the large resulting 3D datasets that consist of terabytes of images and information on millions of labeled cells. Previous work has established pipelines for automated analysis of tissue cleared mouse brains. However, they have focused on single color channels and/or detection of nuclear localized signals, in relatively low-resolution images. To address this gap, we present an automated workflow to map labeled neurons and astrocytes in the genetically distinct Mosaic Analysis with Double Markers (MADM) mouse forebrains. We named the workflow COMBINe (Cell detectiOn in Mouse BraIN) as it combines modules from multiple pipelines. With RetinaNet in its core, we quantitatively analyzed the regional and subregional effects of MADM-based deletion of the Epidermal growth factor receptor on neuronal and astrocyte populations in the mouse forebrain.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

1
eneuro
● 439 papers in training set
Top 0.1%
18.0%
Similar papers in this journal
2
eLife
● 5828 papers in training set
Top 8%
11.6%
Similar papers in this journal
3
Development
● 497 papers in training set
Top 0.9%
8.7%
Similar papers in this journal
4
Journal of Neuroscience Methods
○ 122 papers in training set
Top 0.2%
7.1%
Similar papers in this journal
5
Cell Reports Methods
○ 165 papers in training set
Top 0.1%
7.1%
Similar papers in this journal
50% of probability mass above
6
Cell Reports
○ 1498 papers in training set
Top 7%
5.3%
7
Frontiers in Neuroscience
○ 256 papers in training set
Top 1%
3.9%
8
Nature Communications
○ 5641 papers in training set
Top 38%
2.6%
9
Scientific Reports
○ 3612 papers in training set
Top 39%
2.6%
10
Communications Biology
○ 993 papers in training set
Top 9%
2.4%
11
PLOS Biology
● 486 papers in training set
Top 3%
2.3%
12
iScience
○ 1154 papers in training set
Top 14%
2.1%
13
Nature Methods
○ 385 papers in training set
Top 4%
1.7%
14
Biology Open
● 156 papers in training set
Top 2%
1.5%
15
Life Science Alliance
● 285 papers in training set
Top 4%
1.4%
16
Developmental Biology
○ 150 papers in training set
Top 1%
1.3%
17
Frontiers in Neuroanatomy
○ 15 papers in training set
Top 0.1%
1.1%
18
Cerebral Cortex
◐ 396 papers in training set
Top 4%
1.1%
19
Neuron
○ 337 papers in training set
Top 4%
1.1%
20
Frontiers in Cellular Neuroscience
○ 91 papers in training set
Top 2%
1.0%
21
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 42%
0.8%
22
Frontiers in Cell and Developmental Biology
○ 233 papers in training set
Top 5%
0.8%
23
Neurophotonics
● 42 papers in training set
Top 0.6%
0.8%
24
Imaging Neuroscience
● 282 papers in training set
Top 4%
0.8%
25
The Journal of Neuroscience
● 1025 papers in training set
Top 11%
0.6%
26
BMC Biology
○ 265 papers in training set
Top 7%
0.6%
27
NeuroImage
○ 903 papers in training set
Top 6%
0.6%

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.