Fluorescence Microscopy Imaging Analysis

This website is no longer maintained. It is kept for historical purposes only.

In collaboration with the Ben-Gurion University in the Negev's Bio-Chemistry labs we are developing novel methods for analyzing flourescence microscopy images using machine learning methods.

We tackle issues where human annotation is very costly or highly subjective, such as:

  • Detection: Looking for existance of biological structures or events
  • Segmentation: Marking the image in regions where a biological structure appears
  • Evolution: Tracking of structures through a microscopy imaging film, or cellular evolution stages


Localization and Tracking in 4D Fluorescence Microscopy Imagery, Abousamra, Shahira, Adar Shai, Elia Natalie, and Shilkrot Roy , Workshop on Computer Vision for Microscopy Imaging (CVMI) at CVPR, 07/2018, Salt Lake, Utah, (2018)
Automating Lifecycle-Phase Identification in Microscopy Images of Zebrafish Embryos, Abousamra, Shahira, Aydin Ali Selman, and Shilkrot Roy , Center of Excellence in Wireless and Information Technology (CEWIT'17), (2017)
CNN Based Yeast Cell Segmentation in Multi-Modal Fluorescent Microscopy Data, Aydin, Ali Selman, Dubey Abhinandan, Dovrat Daniel, Aharoni Amir, and Shilkrot Roy , CVPR-CVMI, 07/2017, Hawaii, (2017)