Artificial neural networks for 3D cell shape recognition from confocal images
Greta Simionato, Konrad Hinkelmann, Revaz Chachanidze, Paola Ilaria Bianchi, Elisa Fermo, Richard van Wijk, Marc Leonetti, Christian Wagner, Lars Kaestner, Stephan Quint · arXiv (Cornell University) · 2020
We present a dual-stage neural network architecture for analyzing fine shape details from microscopy recordings in 3D. The system, tested on red blood cells, uses training data from both healthy donors and patients with a congenital blood disease. Characteristic shape features are revealed from the spherical harmonics spectrum of each cell and are automatically processed to create a reproducible and unbiased shape recognition and classification for diagnostic and theragnostic use.