|
Teaching
Senior Research Scientists
|
- Interventional image registration
- Disocclusion in medical images
- Shape-based detection in medical images
- Segmentation in medical treatment planning
|
|
- Computer-assisted surgery
- Medical imaging and segmentation
- Multimodal image registration
- 3D reconstruction
|
|
- Deformable surface modeling and tracking
- 3D reconstruction (multi-camera, stereo)
- Real-time object detection and tracking
- Object detection and localization in 3D data
|
|
- Computer Aided Surgery and Diagnosis.
- Cardiac, Intracardiac, and Intravascular Imaging.
- Signal Processing for Medical Applications.
- Medical Image Analysis and Perception.
|
Joint CAMP / Helmholtz Senior Research Group
|
- Machine Learning for Medical Applications
- 3D shape acquisition, modeling and registration
- Computer Vision
|
|
- Medical Imaging Modalities
- Computer-Assisted Interventions
- Tomographic Reconstruction Methods
|
|
- Cardiac imaging and image analysis
- Medical image registration and segmentation
- Computer aided diagnosis
- Computer assisted cardiac surgery
|
|
- Machine Learning for Medical Applications
- Medical Imaging Modalities
- Computer aided diagnosis
- Histology Imaging
|
Senior Affiliate Lecturers / Research Scientists
|
- Lecturer: conebeam CT and US Imaging
- Research: Advanced Ultrasound Imaging
|
|
- Lecturer: Entrepreneurship in Medical Imaging
- Research: Freehand SPECT in surgery
|
|
- Lecturer: Medical Imaging
- Research: Tomographic reconstruction
|
|
- Lecturer: Ultrasound Imaging
- Scientific Advisor: BMC Master of TUM in Singapore
|
|
Selected Video
News
 | 30 January 2012, MI 00.12.019? QUANTITATIVE EVALUTATION OF 4D MYOCARDIAL STRAIN MEASURES VIA OPTICAL FLOW WITH A FINITE ELEMENT MODEL FITTED TO SONOMICROMETRY Dynamic cardiac metrics, including strains and displacements, can provide a quantitative approach to evaluate cardiac function. However, in current clinical diagnosis, strain measures in 2D are used despite the fact that cardiac motions are complex changes in 4D. Recent advances in 4D ultrasound enable the capability to capture such complex motion in real time. In our previous work, a 4D optical flow based motion tracking algorithm was developed to extract full 4D dynamic cardiac metrics from such 4D ultrasound data. In order to quantitatively evaluate this method, coronary artery occlusion experiments at various locations were performed on five canine hearts with 4D ultrasound and sonomicrometry data acquired during the occlusion. Optical flow displacement was then mapped onto a finite element field fitted model. Corresponding 4D ultrasound data from these experiments were then analyzed. Estimated principal strains were directly compared to those recorded by sonomicrometry showing strong agreement. This was the first validation study of optical flow based strain estimation for 4D cardiac ultrasound including a direct comparison with sonomicrometry on in vivo data. |
 | 27 January 2012, MI 03.13.010 Modeling Brain Circuitry over a Wide Range of Scales Electron microscopes (EM) can now provide the nanometer resolution that is needed to image synapses, and therefore connections, while Light Microscopes (LM) see at the micrometer resolution required to model the 3D structure of the dendritic network. Since both the arborescence and the connections are integral parts of the brain's wiring diagram, combining these two modalities is critically important. In this talk, I will therefore present our approach to building the dendritic arborescence and to tracking migrating neurons from LM images, as well as to segmenting intra-neuronal structures from EM images. I will also argue that the techniques that are in wide usage in the Computer Vision and Machine Learning community are just as applicable in this context. |
 | 26 January 2012, MI 01.13.010 Multi-People Tracking through Global Optimization Given three or four synchronized videos taken at eye level and from different angles, we show that we can effectively detect and track people, even when the only available data comes from the binary output of a simple blob detector and the number of present individuals is a priori unknown. We start from occupancy probability estimates in a top view and rely on a generative model to yield probability images to be compared with the actual input images. We then refine the estimates so that the probability images match the binary input images as well as possible. Finally, having performed this computation independently at each time step, we compute trajectories over tive by solving a convex constrained flow problem, which allows us accurately follow individuals across thousands of frames. Our algorithm yields metrically accurate trajectories for each one of them, in spite of very significant occlusions. In short, we combine a mathematically well-founded generative model that works in each frame individually with a simple approach to global optimization. This yields excellent performance using very simple models that could be further improved. |
 | 16 January 2012, MI 02.08.020? Invited Talk by Bharat Rao, Ph.D., Siemens Healthcare, Inc., Malvern, PA, USA Dr. Bharat Rao, Senior Director and Head of the Knowledge Solutions (KS) group Health Analytics & Business Intelligence business unit in Siemens Healthcare, will give an invited talk on mining medical images to automatically detect potentially abnormal structures, automated decision-support & inference from EMR’s and personalized medicine for therapy selection. |
 | 22 December 2011, MI 03.13.010 Invited Talk by Prof. Franjo Pernuš, PhD, University of Ljubljana In an invited talk at the CAMP lecture, Prof. Franjo Pernuš, PhD, University of Ljubljana, will present an overview of existing methods, three novel methods for registering 3D CT or MR images to 2D X-ray images, and quantitative registration results. |
 | 20 December 2011, MI 02.09.023 Contributions to Medical Image Registration: Theoretical Insights and New Methodologies As part of his PhD defense, Darko Zikic will give a talk on Tuesday, December 20, 2011 at 17:00, in Room 02.09.023 (FMI-Building, Garching, Boltzmannstr. 3). |
Recent Publications
Address
Proud of our Alumni
|