DeepMICROIA – Deep learning for TOMCAT imaging


  • Ender Konukogklu (ETH Zürich)
  • Anne Bonnin (PSI)

Project presentation

April 20th 2018

Project presentation
May 13th 2019


Improving state-of-the-art in micro-CT image analysis for studying tissue microstructure and disease related alterations in the heart

Improve segmentation and quantification models

User interaction in CNN based approaches

Improve robustness to artifacts


Data curation

Development and benchmarking of advanced segmentation approaches

Developing interaction methods in CNN-based segmentation

Quantification of tissue composition in the heart

Scientific publications and tools dissemination


Micron-scale CT images are essential in studying tissue microstructure and alterations. Image analysis plays an important role for quantitative analysis. Better automatic / semi-automatic tools would allow high throughput and more accurate analysis.