Seminar 24th October 2012 2 p.m. Building 53, Room 4025A/B
Multi-Atlas Based Segmentation for Cardiac MR Images
Dr Wenjia Bai
Imperial College London
- Web page
- http://www1.imperial.ac.uk/medicine/people/w.bai/
- Submitter
- Luke Goater
Abstract: The evaluation of ventricular function is important for the diagnosis of cardiovascular diseases, which involves measurement of the left ventricular (LV) mass and LV cavity volume. Manual delineation of the myocardial contours is time-consuming and dependent on subjective experience. A multi-atlas-based method is proposed to automatically segment the cardiac MR images, by utilising the prior information from a set of atlases. Experimental results on cardiac MR images show that the method is able to provide accurate information for clinical diagnosis.
Bio: Wenjia is a post-doctorate research associate in the Myocardial Function section of the National Heart and Lung Institute within Imperial College, based at St Mary's and South Kensington campuses. He is currently working with Prof. Daniel Rueckert from Department of Computing and Prof. Nicholas Peters from St Mary's hospital, studying the mechanism of cardiac arrhythmia using cardiac MRI image analysis techniques. Wenjia did his D.Phil on medical imaging at Wolfson Medical Vision Laboratory, Department of Engineering, University of Oxford, under the supervision of Prof. Sir Michael Brady. His D.Phil thesis is on motion correction of respiratory PET/CT images. Wenjia is a member of Wolfson College, University of Oxford.