Standardized Data and Modeling for AI-based CoVID-19 Diagnosis Support on CT Scans (SDMCT)
Auf einen Blick
- Projektleiter/in : Mohammadreza Amirian
- Projektteam : Dr. Ahmet Selman Bozkir, Dr. Ricardo Chavarriaga, Dr. Javier Montoya, Dr. Frank-Peter Schilling
- Projektvolumen : CHF 19'700
- Projektstatus : abgeschlossen
- Drittmittelgeber : Interne Förderung (ZHAW digital / Digital Futures Fund)
- Kontaktperson : Mohammadreza Amirian
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”. 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.
Amirian, Mohammadreza; Montoya, Javier; Gruss, Jonathan; Stebler, Yves D.; Bozkir, Ahmet Selman; Calandri, Marco; Schwenker, Friedhelm; Stadelmann, Thilo,
PrepNet : a convolutional auto-encoder to homogenize CT scans for cross-dataset medical image analysis [Paper].
Proceedings of CISP-BMEI’21.
14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI), Shanghai, China, 23-25 October 2021.
ZHAW Zürcher Hochschule für Angewandte Wissenschaften.
Verfügbar unter: https://doi.org/10.21256/zhaw-23318