Lineage Tracking and Asymmetric Inheritance Patterns of the Diatom Seminavis robusta [Training image mask generation source code]

This repository belongs to the observation experiments for tracking lineages of Seminavis robusta. The connected work reconstructed the lineages and obtained individuals' timing of division and motility. Cells were entrained for 5 days prior under white light with 25 µmol phot / s in a 12:12 hour rhythm. The images were recorded with a modified Leica microscope (DMIL) and 770 nm light source and a band pass filter. Entrainment continued for the time of recording.
The provided code automates the creation of training and test datasets for the training of U-Net. It generates the required directory structure at the location of the raw data and produces binary masks as PNG. The masks encode a coarse and fine label for the two object classes (cell aggregates and single cell).
Use: Specify the path to the raw data in main.py. Optionally, adjust the parameters of TrainingImageGenerator to suit your data; the default settings already yield satisfactory results for the example dataset. Run main.py.
License: This code is licensed under the European Union Public Licence v. 1.2. See the LICENSE file for details.