Cardiac MR and the UK Biobank
Ilkay Oksuz
Recorded during: The 2020 TechMed Event | more info
Date recording: 16 September 2020
Abstract
Cardiovascular disease is the major cause of mortality in the world. Recently, Cardiovascular Magnetic Resonance techniques have gained ground in diagnosis of cardiovascular disease and good quality of such MR images is a prerequisite for the success of subsequent image analysis pipelines. Quality assessment of medical images is therefore an essential activity and for large population studies such as the UK Biobank, manual identification of artefacts such as those caused by unanticipated motion is tedious and time-consuming. In this talk, recent work on detection of wrong cardiac planning and cardiac motion artefacts using deep learning techniques will be described. The details of deep learning architectures and machine learning methodologies will be given with a certain focus on synthetic k-space corruption and curriculum learning techniques. In the last part of the talk, the mechanisms to correct image artefacts will be discussed with their influence on segmentation.