Back

PointTree: Automatic and accurate reconstruction of long-range axonal projections of single-neuron

Cai, L.; Fan, T.; Qu, X.; Zhang, Y.; Gou, X.; Ding, Q.; Feng, W.; Cao, T.; Lv, X.; Liu, X.; Huang, Q.; Quan, T.; Zeng, S.

2024-09-23 neuroscience
10.1101/2024.09.23.614432 bioRxiv
Show abstract

Single-neuron axonal projections reveal the route map of neuron output and provide a key cue for understanding how information flows across the brain. Reconstruction of single-neuron axonal projections requires intensive manual operations in tens of terabytes of brain imaging data, and is highly time-consuming and labor-intensive. The main issue lies in the need for precise reconstruction algorithms to avoid reconstruction errors, yet current methods struggle with densely distributed axons, focusing mainly on skeleton extraction. To overcome this, we introduce a point assignment-based method that uses cylindrical point sets to accurately represent axons and a minimal information flow tree model to suppress the snowball effect of reconstruction errors. Our method successfully reconstructs single-neuron axonal projections across hundreds of GBs (Gigabytes) images with an average of 80% F1-score, while current methods only provide less than 40% F1-score reconstructions from a few hundred MBs (Megabytes) images. This huge improvement is helpful for high-throughput mapping of neuron projections.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

1
PLOS Computational Biology
● 1863 papers in training set
Top 2%
13.2%
Similar papers in this journal
2
Scientific Reports
○ 3612 papers in training set
Top 4%
10.0%
Similar papers in this journal
3
Nature Communications
○ 5641 papers in training set
Top 18%
9.9%
Similar papers in this journal
4
Frontiers in Computational Neuroscience
○ 60 papers in training set
Top 0.1%
8.1%
Similar papers in this journal
5
Communications Biology
○ 993 papers in training set
Top 1%
5.7%
Similar papers in this journal
6
Science Bulletin
○ 21 papers in training set
Top 0.1%
4.5%
50% of probability mass above
7
IEEE Transactions on Medical Imaging
● 21 papers in training set
Top 0.1%
4.5%
8
eLife
● 5828 papers in training set
Top 34%
3.3%
9
Neural Networks
○ 35 papers in training set
Top 0.2%
2.5%
10
NeuroImage
○ 903 papers in training set
Top 4%
2.0%
11
Advanced Science
○ 286 papers in training set
Top 4%
1.8%
12
PLOS ONE
● 5266 papers in training set
Top 45%
1.8%
13
iScience
○ 1154 papers in training set
Top 16%
1.8%
14
Advanced Intelligent Systems
○ 11 papers in training set
Top 0.1%
1.5%
15
Optics Express
● 26 papers in training set
Top 0.2%
1.4%
16
Bioinformatics
◐ 1204 papers in training set
Top 7%
1.4%
17
IEEE Journal of Biomedical and Health Informatics
● 37 papers in training set
Top 0.8%
1.2%
18
Scientific Data
○ 209 papers in training set
Top 2%
1.2%
19
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 37%
1.1%
20
Medical Image Analysis
○ 35 papers in training set
Top 0.6%
1.0%
21
Journal of Neural Engineering
○ 221 papers in training set
Top 2%
0.9%
22
Computers in Biology and Medicine
○ 128 papers in training set
Top 4%
0.9%
23
Frontiers in Neuroinformatics
○ 41 papers in training set
Top 0.6%
0.9%
24
Nature Computational Science
○ 55 papers in training set
Top 2%
0.9%
25
Small Methods
○ 29 papers in training set
Top 0.7%
0.9%
26
Biomedical Optics Express
● 95 papers in training set
Top 1%
0.6%
27
Science Advances
● 1243 papers in training set
Top 32%
0.6%
28
Briefings in Bioinformatics
◐ 354 papers in training set
Top 7%
0.6%
29
Science China Life Sciences
○ 29 papers in training set
Top 0.7%
0.6%
30
Optics Letters
● 13 papers in training set
Top 0.2%
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.