TY  - JOUR
AU  - Hollandi, Réka
AU  - Szkalisity, Ábel
AU  - Tóth, Tímea
AU  - Tasnádi, Ervin Áron
AU  - Molnár, Csaba
AU  - Mathe, Botond
AU  - Grexa, István
AU  - Molnár, József
AU  - Bálind, Árpád
AU  - Gorbe, Mate
AU  - Kovács, Mária
AU  - Migh, Ede
AU  - Goodman, Allen
AU  - Balassa, Tamás
AU  - Koós, Krisztián
AU  - Wang, Wenyu
AU  - Caicedo, Juan Carlos
AU  - Bara, Norbert
AU  - Kovács, Ferenc
AU  - Paavolainen, Lassi
AU  - Danka, Tivadar
AU  - Kriston, András
AU  - Carpenter, Anne Elizabeth
AU  - Smith, Kevin
AU  - Horváth, Péter
TI  - nucleAIzer: A Parameter-free Deep Learning Framework for Nucleus Segmentation Using Image Style Transfer
JF  - CELL SYSTEMS
J2  - CELL SYST
VL  - 10
PY  - 2020
IS  - 5
SP  - 453
EP  - 458
PG  - 6
SN  - 2405-4712
DO  - 10.1016/j.cels.2020.04.003
UR  - https://m2.mtmt.hu/api/publication/31334623
ID  - 31334623
AB  - 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.
LA  - English
DB  - MTMT
ER  -