Project Aim: To detect Covid-19 infection on chest tomography.
Starting with ISTKA call for Covid-19 research, we have developed a deep learning system to detect Covid-19 in CT scans. Our deep learning ensemble is able to detect Covid-19 infection with 90% accuracy, from both healthy images as well as other lung infections. Separating Covid-19 from healthy lungs is a relatively easy problem, while the main challenge is distinguishing Covid-19 from other infections. The system is now deployed and being used at İstanbul University Cerrahpaşa Schol of Medicine Hospital, with 95% reported accuracy.
Video demo of the 2D system showing Covid scores per each segment of the CT scan.
TRT news about the project.
Project Team: This is a joint work with Sabanci University, Istanbul University Cerrahpaşa School of Medicine and TÜBİTAK UME.
- AI system development: Sara Atito A. Ahmed, Mehmet Can Yavuz, M. Umut Şen, B. Yanıkoğlu
- Data and medical expertise provided by İU-Cerrahpaşa Faculty of Medicine (project lead: Dr. Fatih Gülşen)
Project Support: TÜBİTAK 1001-KAGM (120E165)