Computational Medical Imaging Research

Albarqouni Lab
Clinic for Diagnostic and Interventional Radiology, University Hospital Bonn
Prof. Dr. Shadi Albarqouni

The Computational Imaging Research (Albarqouni Lab.) is a research group located at the Clinic for Diagnostic and Interventional Radiology, Faculty of Medicine, University Hospital Bonn. We focus on developing and introducing Computational Medical Imaging algorithms into clinical practice. Our carefully designed algorithms mitigate the major challenges in medical imaging, e.g., i) the availability of a few annotated data, ii) low inter-/intra-observers agreement, iii) high-class imbalance, iv) inter-/intra-scanners variability and v) domain shift. Our developed algorithms not only save export labor and effort, but they are also fully automated, highly accurate, and cost-effective. This would have a positive impact on clinical services.

Furthermore, we focus our research on developing innovative deep Federated Learning algorithms that can distill and share knowledge among different medical institutes in a robust and privacy-preserved fashion. Research topics include, but are not limited to: i) handling distributed DL models with data heterogeneity including non-i.i.d, and domain shifts, ii) developing explainability and quality control tools, and iii) robustness to poisoning models. Recently, we became interested in developing affordable AI solutions suitable for poor-quality data generated by low infrastructure and point-of-care diagnosis.

Website

Towards Deep Federated Learning in Healthcare, Talk by Prof. Shadi Albarqouni, June 2021
Prof. Shadi Albarqouni
© Johann F. Saba / UKB

Methods

  • Machine Learning and Deep Learning with Medical Imaging
  • Federated Learning in Healthcare
  • Affordable AI and Healthcare