Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.
AR Guidance for Radiological Interventions
This project focuses on enhancing the accuracy and efficiency of CT-guided medical interventions through the development of an Augmented Reality (AR) application for the Apple Vision Pro. By integrating advanced AR technologies with the Cube Navigation System (CNS), the project aims to improve needle placement precision, reducing procedural errors and intervention time. The development process will involve creating a sophisticated 3D environment and leveraging cutting-edge tracking and deep learning algorithms.
Keywords: Augmented Reality, Computer Vision, 3D Vision, Tool Pose Estimation, Artificial Intelligence, Machine Learning, Microsoft HoloLens2, Unity, Radiology, Biomedical Engineering, Data Science
Percutaneous CT-guided interventions are widely employed in the medical field, including pain therapies, biopsies, and ablations. Precise placement of the needle is crucial for the success of these procedures, as it helps prevent tissue damage, provides accurate diagnostic results, and leads to effective treatment outcomes. With the advent of navigation software and robotic assistance, needle placement has become safer and more efficient in recent years. One promising technique is the utilization of patient-mounted devices, such as Navigation Cubes, which are part of the Cube Navigation System (CNS). This method has been demonstrated to improve accuracy and reduce intervention time when compared to the traditional freehand method (FHM).
In this technique, the Access Cube is attached to the patient's skin over the target region. During a CT scan, the cube is automatically located by the software, which then references the planned trajectory of the puncture against the grid of the cube. This allows the software to determine the coordinates of the holes through which the needle must be guided.
Initial application experiences have shown that two main errors can occur:
- Users may use the wrong holes by misaligning rows or columns.
- During puncture, the cube may shift relative to the patient if the user applies pressure with their hand.
Percutaneous CT-guided interventions are widely employed in the medical field, including pain therapies, biopsies, and ablations. Precise placement of the needle is crucial for the success of these procedures, as it helps prevent tissue damage, provides accurate diagnostic results, and leads to effective treatment outcomes. With the advent of navigation software and robotic assistance, needle placement has become safer and more efficient in recent years. One promising technique is the utilization of patient-mounted devices, such as Navigation Cubes, which are part of the Cube Navigation System (CNS). This method has been demonstrated to improve accuracy and reduce intervention time when compared to the traditional freehand method (FHM). In this technique, the Access Cube is attached to the patient's skin over the target region. During a CT scan, the cube is automatically located by the software, which then references the planned trajectory of the puncture against the grid of the cube. This allows the software to determine the coordinates of the holes through which the needle must be guided.
Initial application experiences have shown that two main errors can occur: - Users may use the wrong holes by misaligning rows or columns. - During puncture, the cube may shift relative to the patient if the user applies pressure with their hand.
To eliminate these errors, you will develop an Augmented Reality (AR) app for the Apple Vision Pro will, which will include three key functions:
- AR Support: Display of the holes using AR elements. (Development with Unity Game Engine)
- Execution Control: Verification that the needle is inserted through the correct holes. (Development of deep learning methods with python)
- Cube Movement Detection: Warning the user if the cube moves during puncture. (Deployment of 3D tracking methods)
To eliminate these errors, you will develop an Augmented Reality (AR) app for the Apple Vision Pro will, which will include three key functions:
- AR Support: Display of the holes using AR elements. (Development with Unity Game Engine) - Execution Control: Verification that the needle is inserted through the correct holes. (Development of deep learning methods with python) - Cube Movement Detection: Warning the user if the cube moves during puncture. (Deployment of 3D tracking methods)
- Strong programming skills (python, MATLAB, C#, C, C++) - Experience with machine learning or statistics - Interest in AR/VR development - An independent way of working - The ability to take initiative and shape the direction of the project
We focus on human-centred product development and regard the link between research and education as the key to excellence in training. We see ourselves as a partner for industry and promote the continuous transfer of knowledge through cooperation, as well as the training and further education of students and graduates to strengthen the competitiveness of mechanical engineering industry.
We focus on human-centred product development and regard the link between research and education as the key to excellence in training. We see ourselves as a partner for industry and promote the continuous transfer of knowledge through cooperation, as well as the training and further education of students and graduates to strengthen the competitiveness of mechanical engineering industry.
Master Thesis
Please send your CV and transcript to Tobias Stauffer (tobiasta@ethz.ch)
Please send your CV and transcript to Tobias Stauffer (tobiasta@ethz.ch)
