Prostate MRI and Ultrasound Registration

Project type: IDP
Advisor: Nassir Navab
Supervision by: Amit Shah, Oliver Zettinig and Benjamin Frisch

We are looking for a master student to work on an interdisciplinary project, “Prostate MRI and Ultrasound Registration”

Abstract

In the clinical routine, prostate cancer diagnostic is done by systematic needle biopsies under TransRectal^? UltraSound^? (TRUS) image guidance. However, combining Magnetic Resonance Imaging (MRI) with TRUS has evolved the method of choice for this procedure. The previously acquired MRI needs to be registered with live TRUS and the combined image can be used for prostate biopsy guidance. The registration of MRI and Ultrasound is a challenging task and interesting research topic. TRUS/MRI registration methods reported in the literature use different transformations (rigid, affine and deformable), prostate models (spline, statistical shape model, probabilistic) and similarity metrics. The ideal registration method has to be able to recover the elastic deformation between MRI and TRUS due to patient positioning and force exerted by ultrasound probe. The algorithm needs to be fast enough and automatic so that it can be easily integrated into clinical workflow.

The objective of this IDP is to develop and implement advanced registration algorithms for Prostate MRI and US volumetric images. Your task would be to familiarize yourself with the challenges posed by MR and TRUS imaging, as well as state-of-the-art registration algorithms. You will then implement the algorithms in CAMPVis, the visualization framework developed at our chair, and iteratively evaluate the algorithms' performance with an extensive available dataset.

We require good knowledge of C++ and the ability to work independently, some experience with image processing is an advantage.

If you are interested please send your up-to-date CV to .

Fig. 1: Example MR and TRUS images, in which the prostate have to be segmented correspondingly.