Back

NucleoNet and DropNet: Generalist deep learning models for instance segmentation of nuclei and lipid droplets from electron microscopy images

Bhardwaj, A.; Dell, C. W.; Mikolaj, M. R.; Spiers, H.; Harned, A.; Kuppusamy, B.; Liu, P.; Wei, D.; Sterneck, E.; Narayan, K.

2026-04-05 cell biology
10.64898/2026.04.02.713930 bioRxiv
Show abstract

Automating cellular organelle segmentation is key to increasing the throughput in electron microscopy (EM) and volume EM (vEM) workflows. Deep learning (DL) has accelerated this process, but model development has predominately centered on mitochondria, partly because of a scarcity of suitable training datasets for other features. Here, we crowdsourced the manual step of labeling nuclei and lipid droplets (LDs) from complex cellular EM images and trained Panoptic DeepLab (PDL) models on these large, heterogenous annotated datasets as well as on publicly available vEM datasets. NucleoNet and DropNet, the resulting instance segmentation models for nuclei and LDs, respectively, yield high-quality results on varied benchmarks. We applied these models to quantify differences between 2D and 3D in vitro cancer models versus in vivo tumors, highlighting a path toward robust quantitation in EM. NucleoNet and DropNet are publicly available on our napari plugin, empanada v1.2, for easy point-and-click segmentation of 2D and 3D cellular EM images.

Matching journals

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

1
Nature Methods
336 papers in training set
Top 0.1%
33.4%
2
Journal of Cell Biology
333 papers in training set
Top 0.4%
6.9%
3
Nature Communications
4913 papers in training set
Top 32%
4.9%
4
Journal of Structural Biology
58 papers in training set
Top 0.2%
4.9%
50% of probability mass above
5
Nature Cell Biology
99 papers in training set
Top 1.0%
4.4%
6
Nature
575 papers in training set
Top 6%
4.2%
7
eLife
5422 papers in training set
Top 25%
3.6%
8
Nature Biotechnology
147 papers in training set
Top 2%
3.6%
9
Science
429 papers in training set
Top 10%
3.1%
10
Proceedings of the National Academy of Sciences
2130 papers in training set
Top 27%
2.1%
11
Cell Systems
167 papers in training set
Top 6%
1.9%
12
Communications Biology
886 papers in training set
Top 7%
1.8%
13
Cell
370 papers in training set
Top 11%
1.7%
14
Cell Reports Methods
141 papers in training set
Top 3%
1.3%
15
Genome Biology
555 papers in training set
Top 5%
1.3%
16
PLOS ONE
4510 papers in training set
Top 60%
1.2%
17
Advanced Science
249 papers in training set
Top 15%
1.0%
18
Nature Machine Intelligence
61 papers in training set
Top 3%
0.9%
19
Scientific Reports
3102 papers in training set
Top 70%
0.9%
20
Patterns
70 papers in training set
Top 2%
0.9%
21
Nature Medicine
117 papers in training set
Top 4%
0.8%
22
Structure
175 papers in training set
Top 3%
0.8%
23
Cell Reports
1338 papers in training set
Top 33%
0.8%
24
Nature Genetics
240 papers in training set
Top 7%
0.8%
25
Science Advances
1098 papers in training set
Top 31%
0.7%
26
Journal of Cell Science
353 papers in training set
Top 3%
0.7%
27
Journal of Structural Biology: X
15 papers in training set
Top 0.2%
0.7%
28
iScience
1063 papers in training set
Top 37%
0.7%