Embedding-based Instance Segmentation in Microscopy

Manan Lalit, Pavel Tomancak, Florian Jug
Proceedings of the Fourth Conference on Medical Imaging with Deep Learning, PMLR 143:399-415, 2021.

Abstract

Automatic detection and segmentation of objects in 2D and 3D microscopy data is important for countless biomedical applications. In the natural image domain, spatial embedding-based instance segmentation methods are known to yield high-quality results, but their utility for segmenting microscopy data is currently little researched. Here we introduce EmbedSeg, an embedding-based instance segmentation method which outperforms existing state-of-the-art baselines on 2D as well as 3D microscopy datasets. Additionally, we show that EmbedSeg has a GPU memory footprint small enough to train even on laptop GPUs, making it accessible to virtually everyone. Finally, we introduce four new 3D microscopy datasets, which we make publicly available alongside ground truth training labels. Our open-source implementation is available at https://github.com/juglab/EmbedSeg.

Cite this Paper

BibTeX
@InProceedings{pmlr-v143-lalit21a, title = {Embedding-based Instance Segmentation in Microscopy}, author = {Lalit, Manan and Tomancak, Pavel and Jug, Florian}, booktitle = {Proceedings of the Fourth Conference on Medical Imaging with Deep Learning}, pages = {399--415}, year = {2021}, editor = {Heinrich, Mattias and Dou, Qi and de Bruijne, Marleen and Lellmann, Jan and Schläfer, Alexander and Ernst, Floris}, volume = {143}, series = {Proceedings of Machine Learning Research}, month = {07--09 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v143/lalit21a/lalit21a.pdf}, url = {https://proceedings.mlr.press/v143/lalit21a.html}, abstract = {Automatic detection and segmentation of objects in 2D and 3D microscopy data is important for countless biomedical applications. In the natural image domain, spatial embedding-based instance segmentation methods are known to yield high-quality results, but their utility for segmenting microscopy data is currently little researched. Here we introduce EmbedSeg, an embedding-based instance segmentation method which outperforms existing state-of-the-art baselines on 2D as well as 3D microscopy datasets. Additionally, we show that EmbedSeg has a GPU memory footprint small enough to train even on laptop GPUs, making it accessible to virtually everyone. Finally, we introduce four new 3D microscopy datasets, which we make publicly available alongside ground truth training labels. Our open-source implementation is available at https://github.com/juglab/EmbedSeg.} }
Endnote
%0 Conference Paper %T Embedding-based Instance Segmentation in Microscopy %A Manan Lalit %A Pavel Tomancak %A Florian Jug %B Proceedings of the Fourth Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2021 %E Mattias Heinrich %E Qi Dou %E Marleen de Bruijne %E Jan Lellmann %E Alexander Schläfer %E Floris Ernst %F pmlr-v143-lalit21a %I PMLR %P 399--415 %U https://proceedings.mlr.press/v143/lalit21a.html %V 143 %X Automatic detection and segmentation of objects in 2D and 3D microscopy data is important for countless biomedical applications. In the natural image domain, spatial embedding-based instance segmentation methods are known to yield high-quality results, but their utility for segmenting microscopy data is currently little researched. Here we introduce EmbedSeg, an embedding-based instance segmentation method which outperforms existing state-of-the-art baselines on 2D as well as 3D microscopy datasets. Additionally, we show that EmbedSeg has a GPU memory footprint small enough to train even on laptop GPUs, making it accessible to virtually everyone. Finally, we introduce four new 3D microscopy datasets, which we make publicly available alongside ground truth training labels. Our open-source implementation is available at https://github.com/juglab/EmbedSeg.
APA
Lalit, M., Tomancak, P. & Jug, F.. (2021). Embedding-based Instance Segmentation in Microscopy. Proceedings of the Fourth Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 143:399-415 Available from https://proceedings.mlr.press/v143/lalit21a.html.

Related Material