Back

TractoFlow-ABS (Atlas-Based Segmentation)

Theaud, G.; Houde, J.-C.; Bore, A.; Rheault, F.; Morency, F.; Descoteaux, M.

2020-08-04 neuroscience
10.1101/2020.08.03.197384 bioRxiv
Show abstract

In Diffusion MRI (dMRI), pathological brains are a challenge for tractography processing, where most pipelines are not are not robust to white matter lesions. Intensity of white matter lesions on T1 images can have similar contrasts to gray matter tissue, which leads to misclassifications or "holes" in the white matter mask. These holes produce premature stop for tracking algorithms. To handle these issues, we developed TractoFlow-ABS (Atlas-Based Segmentation). TractoFlow-ABS uses the Freesurfer atlas to compute tissue masks instead of FSL fast in standard TractoFlow. TractoFlow-ABS is therefore a derived version of TractoFlow that is robust to white matter anomalies such as hyperintensities and lesions.

Matching journals

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

1
Neuroinformatics
○ 46 papers in training set
Top 0.1%
12.6%
Similar papers in this journal
2
NeuroImage
○ 903 papers in training set
Top 1%
11.9%
Similar papers in this journal
3
Frontiers in Neuroinformatics
○ 41 papers in training set
Top 0.1%
8.9%
Similar papers in this journal
4
Frontiers in Neuroscience
○ 256 papers in training set
Top 0.2%
6.7%
Similar papers in this journal
5
Human Brain Mapping
○ 329 papers in training set
Top 1%
5.5%
Similar papers in this journal
6
eneuro
● 439 papers in training set
Top 1%
5.2%
50% of probability mass above
7
Brain Structure and Function
○ 93 papers in training set
Top 0.2%
4.8%
8
PLOS ONE
● 5266 papers in training set
Top 30%
4.5%
9
Imaging Neuroscience
● 282 papers in training set
Top 2%
3.2%
10
Scientific Data
○ 209 papers in training set
Top 0.9%
2.8%
11
Scientific Reports
○ 3612 papers in training set
Top 42%
2.4%
12
Journal of Neuroscience Methods
○ 122 papers in training set
Top 0.8%
2.4%
13
Brain Informatics
○ 10 papers in training set
Top 0.1%
2.1%
14
Medical Image Analysis
○ 35 papers in training set
Top 0.4%
1.9%
15
PLOS Computational Biology
● 1863 papers in training set
Top 14%
1.7%
16
Network Neuroscience
● 126 papers in training set
Top 0.9%
1.7%
17
Frontiers in Neurology
○ 102 papers in training set
Top 2%
1.3%
18
Frontiers in Computational Neuroscience
○ 60 papers in training set
Top 0.9%
1.1%
19
Magnetic Resonance Imaging
○ 23 papers in training set
Top 0.4%
1.1%
20
Aperture Neuro
● 20 papers in training set
Top 0.4%
1.1%
21
Brain Connectivity
○ 25 papers in training set
Top 0.4%
0.9%
22
NeuroImage: Clinical
○ 144 papers in training set
Top 3%
0.6%
23
European Journal of Neuroscience
○ 189 papers in training set
Top 4%
0.6%
24
eLife
● 5828 papers in training set
Top 70%
0.6%
25
Frontiers in Psychiatry
○ 87 papers in training set
Top 3%
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.