Back

ReSCU-Nets: recurrent U-Nets for segmentation of multidimensional microscopy data

Hawkins, R.; Balaghi, N.; Rothenberg, K. E.; Ly, M.; Fernandez-Gonzalez, R.

2024-12-03 bioinformatics
10.1101/2024.11.28.625889 bioRxiv
Show abstract

Segmenting multi-dimensional microscopy data requires high accuracy across many images (e.g. timepoints or Z slices) and is thus a labour-intensive part of biological image processing pipelines. We present ReSCU-Nets, recurrent convolutional neural networks that use the segmentation results from the previous frame as a prompt to segment the current frame. We demonstrate that ReSCU-Nets outperform state-of-the-art image segmentation models in different segmentation tasks on time-lapse microscopy sequences.

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

1
Nature Methods
○ 385 papers in training set
Top 0.3%
22.4%
Similar papers in this journal
2
Nature Machine Intelligence
○ 70 papers in training set
Top 0.1%
15.4%
Similar papers in this journal
3
Nature Communications
○ 5641 papers in training set
Top 17%
10.8%
Similar papers in this journal
4
Bioinformatics
◐ 1204 papers in training set
Top 3%
6.9%
Similar papers in this journal
50% of probability mass above
5
Scientific Reports
○ 3612 papers in training set
Top 9%
6.9%
Similar papers in this journal
6
Advanced Intelligent Systems
○ 11 papers in training set
Top 0.1%
4.1%
7
Nature Biotechnology
○ 172 papers in training set
Top 1%
3.3%
8
Communications Biology
○ 993 papers in training set
Top 6%
3.2%
9
Small Methods
○ 29 papers in training set
Top 0.2%
2.2%
10
Cell Reports Methods
○ 165 papers in training set
Top 2%
1.5%
11
New Phytologist
○ 346 papers in training set
Top 4%
1.1%
12
iScience
○ 1154 papers in training set
Top 25%
1.1%
13
Briefings in Bioinformatics
◐ 354 papers in training set
Top 5%
1.1%
14
Patterns
○ 78 papers in training set
Top 2%
1.1%
15
eLife
● 5828 papers in training set
Top 63%
1.0%
16
PLOS Computational Biology
● 1863 papers in training set
Top 19%
0.9%
17
BMC Bioinformatics
○ 457 papers in training set
Top 5%
0.9%
18
Nature Biomedical Engineering
○ 47 papers in training set
Top 2%
0.9%
19
PLOS ONE
● 5266 papers in training set
Top 58%
0.9%
20
Advanced Science
○ 286 papers in training set
Top 10%
0.6%
21
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 43%
0.6%
22
Nano Letters
● 71 papers in training set
Top 1%
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.