Standardized Data and Modeling for AI-based CoVID-19 Diagnosis Support on CT Scans (SDMCT)
Description
Hospitals and research institutes are highly investigating applications of AI in medical imaging. However, developed models and datasets are barely mergeable, and the research results are not reproducible on different datasets due to different CT scanners used. Radiologists told us that “unifying data is crucial for CoVID-19 diagnosis because of data scarcity and time limitations”.
The project SDMCT targets this by developing a standardized preprocessing to use diversely collected data to build a unified model: We train a neural network that produces “standard” CTs by forgetting the information of the specific CT scanner used. The project thus targets a main problem posed by radiologists in the context of CoVID-19 with a long-term impact on the applications of AI in industry and hospitals.
Key data
Projectlead
Mohammadreza Amirian
Project team
Prof. Dr. Frank-Peter Schilling, Dr. Ricardo Chavarriaga, Dr. Javier Montoya, Dr. Ahmet Selman Bozkir
Project status
completed, 05/2020 - 10/2020
Institute/Centre
Institute of Computer Science (InIT)
Funding partner
ZHAW digital / Digital Futures Fund
Project budget
19'700 CHF
