Postdoctoral Research Fellow Dr. Abouzar Eslami Chair for Computer Aided Medical Procedures & Augmented Reality Fakultät für Informatik Technische Universität München Boltzmannstr. 3 85748 Garching b. München room: MI 03.13.056 Email: phone: +49 89 289-19405 fax: +49 89 289-17059 Groups: Registration/Visualization, Segmentation, Reconstruction, Medical Imaging, Machine Learning for Medical Applications

Overview

• 01/2011-present: Postdoctoral Research Fellow of CAMP, TUM.
• 10/2005-11/2010: PhD at EE Department of Sharif University of Technology
• 8/2006-1/2010: Research Assistant and Software Developer of Research Center of Science and Technology in Medicine.
• 9/2004-9/2007: Teacher Assistant and Instructor of Electrical Engineering Department of Sharif University of Technology.

• PhD Dissertation Topic: Joint Segmentation and Motion Estimation of Cardiac Cine MR Image sequence

Research Interests

• Cardiac imaging and image analysis.
• Medical image registration and segmentation.
• Computer aided diagnosis.
• Computer assisted cardiac surgery.

Active research projects

Shape Guided Segmentation of Cardiac Boundaries Prior shape information has been shown to be invaluable for segmenting cardiac boundaries. We develop new methods of exploiting such prior information to guide the segmentation by using techniques of machine learning or formulating the segmentation problem to fit our requirements in segmentation of 4D cardiac data.

Coupled Curves Segmentation The term of coupled curves refers to two or more boundaries bounded biomechanically or anatomically. Some examples are luminal and outer borders of the vessel in intravascular ultrasound images, the myocardial borders of heart in different cardiac modalities like Echocardiography and MRI, retinal layers in optical coherent tomography of eye etc. Coupling these boundaries and taking into account their interdependency efficiently assists segmentation of weaker boundaries by the guide of stronger ones. This project is an extension to our recently developed segmentation approaches by modifying the formulation to segment coupled curves. The primary deliverable is segmentation of double boundaries and can be followed to the secondary deliverable, i.e. segmentation of multiple boundaries depending on the performance of the researcher. Platform of the project is visual programing with mevislab. Preferred coding language is C++ Nevertheless matlab coding can be used for development. There are plenty of applications to the segmentation of coupled curves in medical image processing and the project has significant contribution with high impact to the community.

Student projects

Running

• Coupled Curves Segmentation (DA/BA/MA or IDP/SEP)
• Shape guided segmentation of cardiac boundarieson (DA/BA/MA or IDP/SEP)

Teaching

• WS 2011/12: Lecture: Computer Aided Medical Procedure (CAMP)
• WS 2011/12: Master seminar:Advances in Spatio-Temporal Medical Image Processing: Theory and Applications

Reviewing & Conference Activity

• Journal of IEEE Transactions on Medical Imaging.
• Journal of Elsevier Medical Image Analysis.
• Journal of Elsevier Computers in Biology and Medicine.
• Journal of Elsevier Pattern Recognition Letters
• Conferences & Workshops: MICCAI, ISBI

Publications

2011
	A. Eslami, M. Yigitsoy, N. Navab Manifold learning for shape guided segmentation of Cardiac boundaries: Application to 3D+t Cardiac MR 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC'11), Boston, MA, August 30 - September 3, 2011. (bib)

Other Publications

• A Multiscale Phase Field Method for Joint Segmentation-Rigid Registration - Application to Motion Estimation of Human Knee Joint. A. Eslami, F. Esfandiarpour, A. Shakourirad, F. Farahmand. Journal of Biomedical Engineering-Applications Basis Communications, Accepted 2011
• Joint Denoising, Edge Detection and Motion Estimation of Cardiac MR Image Sequence by Phase Field Method. A. Eslami, M. Jahed, T. Preusser. Journal of Computers in Biology and Medicine, Vol. 40, Issue 1, Jan. 2010, pp. 22-28
• Fuzzy Motion Interpolation for Mesh Based Motion Estimation. A. Eslami, N. Sadati. IEEE Symposium on Computational Intelligence in Image and Signal Processing (CIISP 2007).
• A New Method For Colorizing Of Multichannel MR Images Based On Real Color Of Human Brain M. H. Kadbi , E. Fatemizadeh, A. Eslami. European signal processing Conference (EUSIPCO 2007).
• Radial Multiscale Cyst Segmentation in Ultrasound Images of Kidney. A. Eslami, S. Kasaei, M. Jahed. IEEE Symposium on Signal Processing and Information Technology (ISSPIT 2004).

Patents

• Patent No. IR38703972: GeomStudioSurface^? a CPU-GPU software implemented for geometric deformation investigation of 3D surfaces