Kaizen: Decomposing cellular images with VQ-VAE
Daniel Majoral, Marharyta Domnich
Kaizen improves cell segmentation in microscopy images by using a VQ-VAE to iteratively refine object hypotheses.
Author
University of TartuORCID 0000-0002-6037-4747Unclaimed ORCID profile · follow to get notified of new preprints
3 papers
Recent·Most cited
Daniel Majoral, Marharyta Domnich
Kaizen improves cell segmentation in microscopy images by using a VQ-VAE to iteratively refine object hypotheses.
Daniel Majoral, Ajmal Zemmar, Raúl Vicente
The paper develops a biophysical model to explain how Purkinje cells learn time intervals through intra-cellular calcium signaling and feedback loops, rather than synaptic weights.
Dmytro Fishman, Sten‐Oliver Salumaa, Daniel Majoral…·Leopold Parts
This paper demonstrates accurate nucleus segmentation from brightfield images using deep learning, showing that three CNN architectures can achieve this with U-Net performing best.