Marker-controlled watershed with deep edge emphasis and optimized H-minima transform for automatic segmentation of densely cultivated 3D cell nuclei.

Tuomas Kaseva Bahareh Omidali Eero Hippeläinen Teemu MäkeläUlla WilppuAlexey SofievArto Merivaara Marjo Yliperttula Sauli Savolainen Eero Salli

Published in: BMC bioinformatics (2022)

The use of edge emphasizing U-Nets and optimized H-minima transform can improve the marker-controlled watershed transform for segmentation of densely cultivated 3D cell nuclei. A novel dataset of twelve spheroids was introduced to the public.

Keyphrases

deep learning
single cell
cell therapy
convolutional neural network
healthcare
stem cells
emergency department