DaUltrasound

Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

THIS WEBPAGE IS DEPRECATED - please visit our new website

Projects in Ultrasound Imaging

Advisor: Nassir Navab
Supervision by: Christian Wachinger, Athanasios Karamalis
In cooperation with: Chirurgische Klinik und Poliklinik, Klinikum rechts der Isar

Abstract

A variety of student projects in the area of ultrasound imaging. The projects touch different areas of computer science and engineering. The students will have access to our ultrasound system to gather hands-on experience with ultrasound image acquisition. A detailled description of the projects can be found below.

Please contact Christian Wachinger or Athanasios Karamalis for further information or direclty come to our offices.

ARvis.png

1.Filtering Ultrasound Images

Ultrasound images are crippled by speckle noise. In order to reduce the noise and to make follow-up processing steps like segmentation or registration easier a variety of techniques are available. In the scope of this project we would like to investigate further the characteristics of several filtering techniques. Here, the singal processing toolbox of Matlab includes many algorithms for processing the data and allows therfore for a fast analysis of several approaches. Next to the processing of intensity ultrasound images, we will also investigate the filtering of raw image signals, which can be direclty accessed on our ultrasound system. Lastly, various noise models could be analyzed to see which noise distribution best matches the reality.

Requirements:

  • Knowledge in programming, optionally experience in Matlab
  • Kwonledge in image processing
  • Interested in applying signal processing methods to real data
  • Interested in ultrasound imaging

Courtesy of Y. Schechner

2. Texture Analysis and Learning

Ultrasound images are generally considered to be gradient-like images, meaning that mainly the boundary between the organs is visualized. Frequently, not much intention is paid to the interior region of the organs, which is dominated by speckle noise. A common strategy, like in project 1, is to reduce the speckle noise by filtering operations. In this project we would like to investigate the possibility for learning the texture of organs. This is motivated by the fact that speckle is not any arbitrary kind of noise, but is the result of micro-inhomogeneities in the tissue. Since there is a physical reason behind the appearance of speckle, the extraction of a characteristic texture for each organ seems feasible.

The student will first have to read into different methods of texture analysis and synthesis, which are closely related to machine learning techniques. In a second step, a few methods will be tested on real ultrasound images which we will acquire with our ultrasound system at the hospital rechts der Isar.

Requirements:

  • Knowledge in programming, optionally experience in Matlab
  • Kwonledge in image processing
  • Interested in applying machine learning and statistical methods to real data
  • Interested in ultrasound imaging


Courtesy of Yanxi Liu (CMU)

3. Ultrasound Simulation

The simulation of medical ultrasound has numerous applications, including ultrasound transducer and system development and image simulation for registration and training applications. Various simulation methods have been proposed, however, they require considerable computation time that can even be in the range of hours. Therefore, the focus of this project is to investigate alternative approaches for simulating ultrasound wave behaviour in different media in an adequate processing time. For this purpose a literature survey will be conducted that will point out the state-of-the-art and which will introduce the student to the topic. The simulation will mostly likely be implemented based on the Finite-Difference Time-Domain (FDTD) method or the Finite-Element Method (FEM), depending on the model chosen after the literature survey. Furthermore, the student will be strongly encouraged to implement the method on the GPU, taking advantage of its parallel processing architecture, hence reducing dramatically the overall processing time.

Requirements:

  • Knowledge in programming, optionally experience in Matlab
  • Knowledge in numerical methods for solving PDEs optional, but beneficial
  • Knowledge in GPU programming (GLSL, CUDA) optional, but beneficial
  • Interested in learning ultrasound imaging and physics
WesterveltSequence.gif

4. Ultrasound Speckle Tracking

Speckle refers to the small scale reflectors in ultrasound images, commonly also referred to as speckle noise. Speckle tracking refers to the technique of tracking the motion or deformation of a given speckle region between consecutive ultrasound image frames. Applications of this technique include sensorless 3D freehand ultrasound, meaning the ultrasound tracking is not implemented via sensors like electromagnetic or optical tracking, but by using the information from the speckle change between consecutive frames. Another application is the evaluation of motion, like in echocardiography, by tracking the speckle pattern. This project will focus on the application of speckle tracking for extracting the deformation field betweenconsecutive image frames. That is, the extraction of the deformation between images that show the same anatomic, but at a different time. Initially, a literature survey will be conducted, in order to identify the state-of-the-art and to smoothly introduce the student to the topic. One promising method will be selected and implement, whereas, possible improvements to the method will be introduced during the course of this project.

Requirements:

  • Knowledge in programming, optionally experience in Matlab
  • Knowledge in image processing
  • Interested in ultrasound imaging



.

ProjectForm
Title: Ultrasound Imaging
Abstract: A variety of student projects in the area of ultrasound imaging. The projects touch different areas of computer science and engineering.
Student:  
Director: Nassir Navab
Supervisor: Christian Wachinger, Athanasios Karamalis
Type: DA/MA/BA
Area: Registration / Visualization, Medical Imaging
Status: finished
Start:  
Finish:  
Thesis (optional):  
Picture:  


Edit | Attach | Refresh | Diffs | More | Revision r1.16 - 12 Nov 2010 - 22:06 - ChristianWachinger