nucleAIzer : A Parameter-free Deep Learning Framework for Nucleus Segmentation Using Image Style Transfer

Show full item record



Permalink

http://hdl.handle.net/10138/316205

Citation

Hollandi , R , Szkalisity , A , Toth , T , Tasnadi , E , Molnar , C , Mathe , B , Grexa , I , Molnar , J , Balind , A , Gorbe , M , Kovacs , M , Migh , E , Goodman , A , Balassa , T , Koos , K , Wang , W , Caicedo , J C , Bara , N , Kovacs , F , Paavolainen , L , Danka , T , Kriston , A , Carpenter , A E , Smith , K & Horvath , P 2020 , ' nucleAIzer : A Parameter-free Deep Learning Framework for Nucleus Segmentation Using Image Style Transfer ' , Cell Systems , vol. 10 , no. 5 , pp. 453-+ . https://doi.org/10.1016/j.cels.2020.04.003

Title: nucleAIzer : A Parameter-free Deep Learning Framework for Nucleus Segmentation Using Image Style Transfer
Author: Hollandi, Reka; Szkalisity, Abel; Toth, Timea; Tasnadi, Ervin; Molnar, Csaba; Mathe, Botond; Grexa, Istvan; Molnar, Jozsef; Balind, Arpad; Gorbe, Mate; Kovacs, Maria; Migh, Ede; Goodman, Allen; Balassa, Tamas; Koos, Krisztian; Wang, Wenyu; Caicedo, Juan Carlos; Bara, Norbert; Kovacs, Ferenc; Paavolainen, Lassi; Danka, Tivadar; Kriston, Andras; Carpenter, Anne Elizabeth; Smith, Kevin; Horvath, Peter
Contributor: University of Helsinki, Institute for Molecular Medicine Finland
University of Helsinki, Institute for Molecular Medicine Finland
University of Helsinki, Institute for Molecular Medicine Finland
Date: 2020-05-20
Language: eng
Number of pages: 12
Belongs to series: Cell Systems
ISSN: 2405-4712
URI: http://hdl.handle.net/10138/316205
Abstract: Single-cell segmentation is typically a crucial task of image-based cellular analysis. We present nucleAIzer, a deep-learning approach aiming toward a truly general method for localizing 2D cell 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 that during training nucleAIzer automatically adapts its nucleus-style model to unseen and unlabeled data using image style transfer to automatically generate augmented training samples. This allows the model to recognize nuclei in new and different experiments efficiently without requiring expert annotations, making deep learning for nucleus segmentation fairly simple and labor free for most biological light microscopy experiments. It can also be used online, integrated into CellProfiler and freely downloaded at www.nucleaizer.org. A record of this paper's transparent peer review process is included in the Supplemental Information.
Subject: 1182 Biochemistry, cell and molecular biology
Rights:


Files in this item

Total number of downloads: Loading...

Files Size Format View
PIIS2405471220301174.pdf 1.370Mb PDF View/Open

This item appears in the following Collection(s)

Show full item record