A deep learning framework for nucleus segmentation using image style transfer

By Réka Hollandi, Ábel Szkalisity, Tímea Tóth, Ervin A. Tasnádi, Csaba Molnar, Botond Máthé, István Grexa, József Molnár, Á. Bálind, Mate Gorbe and 14 more. 2019

48 citations recorded by the source corpus.

Single cell segmentation is typically one of the first and most crucial tasks of image-based cellular analysis. We present a deep learning approach aiming towards a truly general method for localizing nuclei across a diverse range of assays and light microscopy modalities. We outperform the 739 methods submitted to the 2018 Data Science Bowl on images representing a variety of realistic conditions, some of which were not represented in the training data. The key to our approach is to adapt our model to unseen and unlabeled data using image style transfer to generate augmented training samples. This allows the model to recognize nuclei in new and different experiments without requiring expert annotations.

Subfields: Artificial Intelligence, Biophysics, Media Technology, Medical Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. William Graf
2. Erick Moen
3. Markus W. Covert
4. Takamasa Kudo
5. David Van Valen
6. D. Bannon

Citations in the corpus

• Nucleus segmentation across imaging experiments: The 2018 Data Science Bowl (2019, neutral): “Any methods, additional references, Nature Research reporting summaries, source data, statements of code and data availability and associated accession codes are available at https://doi.org/10.1038/ s41592-019-0612-7.”
• Deep learning for cellular image analysis (2019, methodology): “NaTurE METhoDs | www.nature.com/naturemethods have been successful when adapted to cellular data 92–94 .”