Qaiser Mahmood defends his doctoral thesis: Unsupervised Segmentation of Head Tissues from Multi-Modal Magnetic Resonance Images: With Application to EEG Source Localization and Stroke Detection

Lic. Eng. Qaiser Mahmood, will defend his doctoral thesis, entitled ” Unsupervised Segmentation of Head Tissues from Multi-Modal Magnetic Resonance Images: With Application to EEG Source Localization and Stroke Detection”, on April 1st, 2016, at 10:00 in room EA, Chalmers University of Technology, Hörsalsvägen 11, Göteborg.

The faculty opponent will be Professor Ali R Khan, Department of Medical Biophysics and Department of Medical Imaging at Western University, Ontario, Canada.

Qaiser Mahmood was admitted for postgraduate studies at Chalmers in 2010. The PhD thesis consists of an introduction and appended papers of which four are published journal papers, and two are published conference contributions. The thesis is based on the following papers:

Paper A

Qaiser Mahmood, Artur Chodorowski, Andrew Mehnert, Mikael Persson, “A Novel Bayesian Approach to Adaptive Mean Shift Segmentation of Brain Images”, Proceedings of IEEE International

Conference on Computer Based Medical Systems (CBMS), pp. 1-6, Rome, Italy, 20th-22nd June, 2012.

Paper B

Qaiser Mahmood, Artur Chodorowski, Mikael Persson, “Automated MRI Brain Tissue Segmentation

based on Mean Shift and Fuzzy C-Means using a Priori Tissue Probability Maps”, Innovation and Research in BioMedical Engineering (IRBM), pp.185-196, 2015.

Paper C

Yazdan Shirvany, Antonio R. Porras, Koushyar Kowkabzadeh, Qaiser Mahmood, Hoi-Shun Lui, Mikael Persson, “Investigation of Brain Tissue Segmentation Error and its Effect on EEG Source Localization”, Proceedings of International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 1522-1525, San Diego, USA, 22nd Aug.-1st Sep., 2012.

Paper D

Yazdan Shirvany, Qaiser Mahmood, Fredrik Edelvik, Stefan Jakobsson, Anders Hedström, Mikael Persson, “Particle Swarm Optimization Applied to EEG Source Localization of Somatosensory Evoked Potentials”, IEEE Transactions on Neural Systems and Rehabilitation Engineering, pp. 11- 20, 2013.

Paper E

Qaiser Mahmood, Artur Chodorowski, Andrew Mehnert, Johanna Gellermann, Mikael Persson, “Unsupervised Segmentation of Head Tissues from Multi-modal MR Images for EEG Source Localization”, Journal of Digital Imaging (JDI), pp. 1-16, 2014, DOI:10.1007/s10278-014-9752-6.

Paper F

Qaiser Mahmood, Shaochuan Li, Andreas Fhager, Stefan Candefjord, Artur Chodorowski, Andrew Mehnert, Mikael Persson, “A Comparative Study of Automated Segmentation Methods for Use in a Microwave Tomography System for Imaging Intracerebral Hemorrhage in Stroke Patients”, Journal of Electromagnetic Analysis and Applications (JEMAA), Online, May 2015.

The overall goal of the thesis was to develop an efficient method for segmentation of head tissues in magnetic resonance images to be used in applications such as EEG source localization and stroke detection.

Qaiser is the principal author of all but two of the included contributions of the thesis. He has performed most of the work and written most of these papers with advice and ideas from his co-authors and his co-supervisors. In paper C the main contributors are the three first authors, and Qaiser’s contribution was more limited. In paper D the first author implemented the source localization part and Qaiser implemented the head model segmentation part. The two first authors took main responsibility in writing the paper with advice and ideas from the co-authors.

The work has been performed in the Centre MedTech West at Sahlgrenska University Hospital and at the Department of Signals and Systems at Chalmers University of Technology. The daily supervision has been given by Co-supervisors have been Associate Professor Andrew Mehnert, Chalmers (currently at the University of Western Australia), Dr. Artur Chodorowski and Associate Professor Andreas Fhager, Chalmers.

Qaiser has during the years developed a thorough understanding on the segmentation aspects of the medical images, in particular images of the human head. It has been a pleasure for me to see his development to a researcher.

The project has been founded in part by Chalmers University of Technology and in part by the Higher Education Commission (HEC) of Pakistan.

If you would like to receive a copy of the thesis, please send an email to qaiserm@chalmers.se