Back

Vasculature segmentation in 3D hierarchical phase-contrast tomography images of human kidneys

Jain, Y.; Walsh, C. L.; Yagis, E.; Aslani, S.; Nandanwar, S.; Zhou, Y.; Ha, J.; Gustilo, K. S.; Brunet, J.; Rahmani, S.; Tafforeau, P.; Bellier, A.; Weber, G. M.; Lee, P. D.; Borner, K.

2024-08-26 bioinformatics
10.1101/2024.08.25.609595 bioRxiv
Show abstract

Efficient algorithms are needed to segment vasculature in new three-dimensional (3D) medical imaging datasets at scale for a wide range of research and clinical applications. Manual segmentation of vessels in images is time-consuming and expensive. Computational approaches are more scalable but have limitations in accuracy. We organized a global machine learning competition, engaging 1,401 participants, to help develop new deep learning methods for 3D blood vessel segmentation. This paper presents a detailed analysis of the top-performing solutions using manually curated 3D Hierarchical Phase-Contrast Tomography datasets of the human kidney, focusing on the segmentation accuracy and morphological analysis, thereby establishing a benchmark for future studies in blood vessel segmentation within phase-contrast tomography imaging.

Published in Nature Communications (predicted rank #2) · training set

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

1
Scientific Reports
○ 3612 papers in training set
Top 2%
13.1%
Similar papers in this journal
Nature Communications · published here
○ 5641 papers in training set
Top 20%
8.0%
Similar papers in this journal
3
Medical Image Analysis
○ 35 papers in training set
Top 0.1%
6.8%
Similar papers in this journal
4
Scientific Data
○ 209 papers in training set
Top 0.4%
6.4%
Similar papers in this journal
5
PLOS Computational Biology
● 1863 papers in training set
Top 6%
6.4%
Similar papers in this journal
6
Communications Biology
○ 993 papers in training set
Top 1%
5.6%
7
Bioinformatics
◐ 1204 papers in training set
Top 4%
5.6%
50% of probability mass above
8
GigaScience
◐ 212 papers in training set
Top 0.8%
4.1%
9
Nature Methods
○ 385 papers in training set
Top 3%
3.3%
10
Computers in Biology and Medicine
○ 128 papers in training set
Top 2%
2.4%
11
Nature Machine Intelligence
○ 70 papers in training set
Top 1%
1.8%
12
Frontiers in Bioinformatics
○ 49 papers in training set
Top 0.4%
1.8%
13
Advanced Science
○ 286 papers in training set
Top 4%
1.8%
14
Small Methods
○ 29 papers in training set
Top 0.4%
1.4%
15
Annals of Biomedical Engineering
○ 37 papers in training set
Top 0.7%
1.4%
16
Biology Methods and Protocols
◐ 61 papers in training set
Top 1%
1.4%
17
PLOS ONE
● 5266 papers in training set
Top 50%
1.4%
18
Advanced Intelligent Systems
○ 11 papers in training set
Top 0.2%
1.1%
19
iScience
○ 1154 papers in training set
Top 25%
1.1%
20
BMC Bioinformatics
○ 457 papers in training set
Top 5%
1.1%
21
Journal of Pathology Informatics
○ 15 papers in training set
Top 0.2%
1.1%
22
Frontiers in Bioengineering and Biotechnology
○ 98 papers in training set
Top 2%
1.1%
23
Briefings in Bioinformatics
◐ 354 papers in training set
Top 6%
1.0%
24
Communications Medicine
○ 113 papers in training set
Top 4%
0.9%
25
Frontiers in Medicine
○ 120 papers in training set
Top 5%
0.6%
26
Journal of the American Medical Informatics Association
◐ 71 papers in training set
Top 2%
0.6%
27
Patterns
○ 78 papers in training set
Top 3%
0.6%
28
npj Systems Biology and Applications
○ 125 papers in training set
Top 2%
0.6%
29
Cytometry Part A
○ 33 papers in training set
Top 0.4%
0.6%
30
PLOS Digital Health
● 106 papers in training set
Top 5%
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.