Back

Convolutional neural networks for automated CMR image segmentation in rats with myocardial infarcts

Gondova, A.; Zurek, M.; Karlsson, J.; Hultin, L.; Noeske, T.; Watson, E.

2020-12-02 bioengineering
10.1101/2020.12.01.405969 bioRxiv
Show abstract

In translational cardiovascular research, delineation of left ventricle (LV) in magnetic resonance images is a crucial step in assessing hearts function. Performed manually, this task is time-consuming and prone to inter- and intra-reader variability. Here we report first AI-based tool for segmentation of rat cardiovascular MRI. The method is an ensemble of fully convolutional networks and can quantify clinically relevant measures: end-diastolic volume (EDV), end-systolic volume (ESV), and ejection fraction (EF) automatically. Overall, our method reaches Dice score of 0.93 on the independent test set. The mean absolute difference of segmented volumes between automated and manual segmentation is 22.5L for EDV, 13.6L for ESV, and for EF 2.9%. Our work demonstrates the value of AI in development of tools that will significantly reduce time spent on repetitive work and result in increased efficiency of reporting data to project teams.

Matching journals

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

1
Computers in Biology and Medicine
○ 128 papers in training set
Top 0.1%
11.6%
Similar papers in this journal
2
Computer Methods and Programs in Biomedicine
○ 28 papers in training set
Top 0.1%
9.5%
Similar papers in this journal
3
Frontiers in Cardiovascular Medicine
○ 53 papers in training set
Top 0.2%
9.5%
Similar papers in this journal
4
PLOS ONE
● 5266 papers in training set
Top 22%
7.1%
Similar papers in this journal
5
IEEE Transactions on Medical Imaging
● 21 papers in training set
Top 0.1%
6.6%
Similar papers in this journal
6
Magnetic Resonance in Medicine
○ 85 papers in training set
Top 0.2%
6.6%
50% of probability mass above
7
Scientific Reports
○ 3612 papers in training set
Top 11%
6.6%
8
PLOS Computational Biology
● 1863 papers in training set
Top 8%
4.2%
9
IEEE Access
● 35 papers in training set
Top 0.3%
4.0%
10
Medical Physics
○ 14 papers in training set
Top 0.2%
2.6%
11
Journal of Medical Imaging
● 11 papers in training set
Top 0.2%
2.4%
12
Annals of Biomedical Engineering
○ 37 papers in training set
Top 0.4%
2.0%
13
npj Digital Medicine
○ 118 papers in training set
Top 2%
1.9%
14
Bioengineering
○ 29 papers in training set
Top 0.4%
1.7%
15
Medical Image Analysis
○ 35 papers in training set
Top 0.4%
1.7%
16
IEEE Transactions on Biomedical Engineering
● 40 papers in training set
Top 0.7%
1.3%
17
Biomedical Signal Processing and Control
○ 22 papers in training set
Top 0.4%
1.3%
18
Photoacoustics
○ 12 papers in training set
Top 0.2%
1.3%
19
Ultrasound in Medicine & Biology
○ 10 papers in training set
Top 0.3%
1.1%
20
Frontiers in Neuroscience
○ 256 papers in training set
Top 5%
1.0%
21
Biomedical Optics Express
● 95 papers in training set
Top 1%
0.8%
22
European Radiology
○ 15 papers in training set
Top 0.6%
0.8%
23
Magnetic Resonance Imaging
○ 23 papers in training set
Top 0.5%
0.8%
24
Frontiers in Physiology
○ 106 papers in training set
Top 3%
0.8%
25
Brain Structure and Function
○ 93 papers in training set
Top 2%
0.8%
26
Nature Communications
○ 5641 papers in training set
Top 57%
0.8%
27
International Journal for Numerical Methods in Biomedical Engineering
○ 14 papers in training set
Top 0.3%
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.