Super Resolution Ultrasound

Thesis by:
Advisor: Nassir Navab
Supervision by:Diana Mateus , Tassilo Klein
Due date:

Overview

Ultrasound imaging systems are more accessible, mobile and inexpensive compared to other imaging techniques. Furthermore, its real-time image formation, low cost as well as non-invasive nature make it very attractive. However, due to the inherent process of ultrasound, generated images are view-dependent and subject to noise. In particular, the dominant noise, referred to as speckle, decreases the resolution of ultrasound image. Therefore, it is difficult to directly use common image processing methods in ultrasound imagery. By recording a sequence of ultrasound images, however, an enhanced image can be generated. This is of particular interest in the domain of transcranial ultrasound (ultrasound images of the brain through the temporal lobe), where the quality of the images is bad due to the transmission through the skull bone.

There are several ways to get involved in the project: -For Bachelor/IDP/SDP implementation and evaluation of several super-resolution approaches. -For Master Thesis, we want to improve standard methods for super-resolution, using ultrasound specific image formation.

At the initial stage, prototyping can be done in Matlab. In order to improve the performance of the method for practical application, the final approach to be ported to C++ later on. Afterwards, the method is to be integrated into an already existing 3D ultrasound framework. The work is concluded with experiments in the NARVIS lab.

The project involves interacting with people from different disciplines.

If you are interested please send a brief CV to mateus@cs.tum.edu or kleint@in.tum.de.

Tasks

• Development (prototype algorithms) will be written in Matlab.
• Improvement of current techniques for ultrasound.
• Implementation of the final method in C++.
• Validation of method on synthetic test data and real patient data.

Requirements

• Strong knowledge of MATLAB and C++ (mandatory).
• Good Math skills.
• Interest in medical applications and multidisciplinary work.
• Organizational skills.

References

• Dai, Wang & Liu, "A Fast and Robust Super Resolution Method for Intima Reconstruction in Medical Ultrasound", Int. Conf. Bioinf & Biomed Eng. 2009
• Wang Bo et al., "Ultrasound Speckle Reduction via Super Resolution and Nonlinear Diffusion," ACCV 2009, vol. 5996, pp. 130-139
• Seitz & Baker, "Filter Flow", ICCV 2009.
• Hirsch, Sra, Scholkopf & Harmeling, "Efficient Filter Flow for Space-Variant Multiframe Blind Deconvolution", CVPR 2010.
• Glasner, Bagon & Irani, Super-resolution from a Single Image, ICCV 2009. Project webpage
• Farsiu, Robinson, Elad & Milanfar, "Advances and challenges in superresolution". Int Journal Imag Syst Technol vol 14, No. 2, pp. 47-57, Aug 2004.