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
"Uncertainty estimation in medical image analysis"
Time and place: June 11, 2024 11:15 AM, Kristen Nygaards sal (5370), Ole-Johan Dahls hus / Zoom
Main research findings
Cardiac ultrasound, or echocardiography, is the primary method used to evaluate heart health, yielding essential diagnostic and prognostic information. However, performing these evaluations can be time-consuming and labor-intensive for cardiologists. To address this, fully automatic algorithms based on deep learning are being developed. In this thesis, we introduced a new method for delineating heart cycles directly in spectral Doppler images. This innovation eliminates the need to record ECG simultaneously, which means clinicians don't need to attach ECG pads, saving valuable time.
Additionally, our research tackles the issue of poor image quality in patients who are difficult to scan. Specifically, it addresses the problem of reverberational clutter that can obscure important cardiac structures in the images. The effectiveness of this method is demonstrated using in-vivo data.
Adjudication committee
- Associate Professor Nicolas Duchateau, Université Lyon 1, France
- Associate Professor Elisabeth Wetzer, The Arctic University of Norway
- Associate Professor Sven Peter Näsholm, Department of Informatics, University of Oslo, Norway
Supervisors
- Professor Anne Solberg, Department of Informatics, University of Oslo, Norway
- Chief Engineer Erik Steen, GE Wingmed Ultrasound, Norway
Chair of defence:
Contact information at Department: Mozhdeh Sheibani Harat