English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Conference Paper

Leveraging Self-supervised Denoising for Image Segmentation.

MPS-Authors
/cone/persons/resource/persons219548

Prakash,  Mangal
Max Planck Institute for Molecular Cell Biology and Genetics, Max Planck Society;

/cone/persons/resource/persons247501

Lalit,  Manan
Max Planck Institute for Molecular Cell Biology and Genetics, Max Planck Society;

/cone/persons/resource/persons219742

Tomancak,  Pavel
Max Planck Institute for Molecular Cell Biology and Genetics, Max Planck Society;

/cone/persons/resource/persons219280

Jug,  Florian
Max Planck Institute for Molecular Cell Biology and Genetics, Max Planck Society;

/cone/persons/resource/persons219351

Krull,  Alexander
Max Planck Institute for Molecular Cell Biology and Genetics, Max Planck Society;

External Resource
No external resources are shared
Fulltext (restricted access)
There are currently no full texts shared for your IP range.
Fulltext (public)
There are no public fulltexts stored in PuRe
Supplementary Material (public)
There is no public supplementary material available
Citation

Prakash, M., Buchholz, T.-O., Lalit, M., Tomancak, P., Jug, F., & Krull, A. (2020). Leveraging Self-supervised Denoising for Image Segmentation. In IEEE ISBI 2020: International Conference on Biomedical Imaging: April 2-7, 2020, Iowa City, Iowa, USA: symposium proceeding (pp. 428-432). Piscataway, N.J.: IEEE.


Cite as: https://hdl.handle.net/21.11116/0000-0008-A215-9
Abstract
Deep learning (DL) has arguably emerged as the method of choice for the detection and segmentation of biological structures in microscopy images. However, DL typically needs copious amounts of annotated training data that is for biomedical projects typically not available and excessively expensive to generate. Additionally, tasks become harder in the presence of noise, requiring even more high-quality training data. Hence, we propose to use denoising networks to improve the performance of other DL-based image segmentation methods. More specifically, we present ideas on how state-of-the-art self-supervised CARE networks can improve cell/nuclei segmentation in microscopy data. Using two state-of-the-art baseline methods, U-Net and StarDist, we show that our ideas consistently improve the quality of resulting segmentations, especially when only limited training data for noisy micrographs are available.