The PhD defence will be partially digital, in Kristen Nygaards sal (5370), Ole-Johan Dahls hus and streamed directly using Zoom. The host of the session will moderate the technicalities while the chair of the defence will moderate the disputation.
Ex auditorio questions: the chair of the defence will invite the attending audience at Kristen Nygaards sal to ask ex auditorio questions.
Trial lecture
"Federated learning for medical applications”.
Time and place: February 17, 2023 10:15 AM, Kristen Nygaards sal (5370), Ole-Johan Dahls hus/ZOOM
Main research findings
-
Computer science techniques in medical image analysis have remarkably progressed over the last decades. The progress is due to increased image resolution, reduced hardware price, and high technology readiness level. Consequently, these advances have meant that the volume of data analyzed from these images has also increased, impacting the software engineering side on how to efficiently and accurately process medical images. Deep learning is one of the top choices for analyzing medical images. Although deep learning techniques have had the highest accuracy in image classification competitions, the classification process is a black box and requires expensive high-end computers. Therefore, manual analysis remains the state-of-the-art in medical image analysis, specifically microcirculation analysis. The main goal of this Ph.D. was to develop a system that can automatically analyze microcirculation images and allow real-time bedside analysis of the microcirculation system. The developed system shortens and automates the analysis of microcirculation images while exceeding the accuracy of a trained medical expert. In addition, the developed system can be deployed bed-side at hospitals and provide results in real-time, thus providing a substantial improvement over previous systems requiring a lab session and a subsequent 20-minute manual analysis.
Adjudication committee:
- Professor Arlindo Oliveira, Instituto Superior Técnico / INESC ID, Portugal
- Senior Researcher Sonia Ben Mokhtar, Centre national de la recherche scientifique (CNRS), France
- Professor Dag Sjøberg, University of Oslo, Department of informatics Norway
Supervisors
- Professor Paulo Ferreira, Department of Informatics, UIO, Norway
-
Professor Eric Bartley Jul, Department of Informatics, UIO, Norway
-
Associate Professor Trung Tuyen Truong, Department of Mathematics, UiO, Norway
Chair of defence:
Associate Professor Ragnhild Kobro Runde
Contact information at Department: Mozhdeh Sheibani Harat