Tweet
PhD position - University of Bath - Automatic segmentation of 3D ultrasound for spinal imaging in clinical settings - 2nd April deadline
Dear All,
The University of Bath is inviting applications for the following PhD project in the Department for Health commencing in October 2023.
The successful student will be part of the Centre for the Analysis of Motion, Entertainment Research and Applications (CAMERA) which performs world-leading multi-disciplinary research in Intelligent Visual and Interactive Technology. Funded by the EPSRC and the University of Bath, CAMERA exists to accelerate the impact of fundamental research being undertaken at the University in the Departments of Computer Science, Health and Psychology
3D ultrasound has the potential to obtain scans of spinal poses that are faster, cheaper, safer and more portable than current medical imaging methods, such as MRI or CT scans. Additionally, these scans can be performed in any spinal position, facilitating patient-specific biomechanical modelling that accurately matches how patients move. This technology could facilitate improved monitoring, diagnosis and design of rehabilitation programs for patients suffering from musculoskeletal spinal disorders, such as scoliosis and ankylosing spondylitis (AS).
Unfortunately, manually segmenting bone surfaces for all ultrasound images is incredibly time consuming and infeasible for clinical applications. Recent advances in machine learning has improved image segmentation for medical images such as ultrasound and MRI, although these algorithms are generally trained on large manually labelled datasets. We therefore propose development of an unsupervised/weakly supervised, generative machine learning model for ultrasound segmentation that harnesses 3D ultrasound location and temporal information.
The overall aim of this project is to enable imaging of the spine via ultrasound. This will be achieved through the following objectives:
a) Collection of 3D ultrasound and motion capture data in a clinical population of ankylosing spondylitis patients (already underway).
b) Implement and evaluate a generative machine learning model that uses computer vision approaches to automatically segment ultrasound images and create 3D spinal models.
c) Automate creation of highly patient-specific musculoskeletal models from the generative spine model that will accurately represent patient movements and joint loads for clinical settings.
Preferred start date – 2 October 2023
Please follow this link for more info and for applying online: https://www.findaphd.com/phds/projec...tings/?p154414
Informal enquiries are welcomed and should be directed to Dr Dario Cazzola (dc547@bath.ac.uk).
Application deadline 2nd April.
All the best.
Dario
The University of Bath is inviting applications for the following PhD project in the Department for Health commencing in October 2023.
The successful student will be part of the Centre for the Analysis of Motion, Entertainment Research and Applications (CAMERA) which performs world-leading multi-disciplinary research in Intelligent Visual and Interactive Technology. Funded by the EPSRC and the University of Bath, CAMERA exists to accelerate the impact of fundamental research being undertaken at the University in the Departments of Computer Science, Health and Psychology
3D ultrasound has the potential to obtain scans of spinal poses that are faster, cheaper, safer and more portable than current medical imaging methods, such as MRI or CT scans. Additionally, these scans can be performed in any spinal position, facilitating patient-specific biomechanical modelling that accurately matches how patients move. This technology could facilitate improved monitoring, diagnosis and design of rehabilitation programs for patients suffering from musculoskeletal spinal disorders, such as scoliosis and ankylosing spondylitis (AS).
Unfortunately, manually segmenting bone surfaces for all ultrasound images is incredibly time consuming and infeasible for clinical applications. Recent advances in machine learning has improved image segmentation for medical images such as ultrasound and MRI, although these algorithms are generally trained on large manually labelled datasets. We therefore propose development of an unsupervised/weakly supervised, generative machine learning model for ultrasound segmentation that harnesses 3D ultrasound location and temporal information.
The overall aim of this project is to enable imaging of the spine via ultrasound. This will be achieved through the following objectives:
a) Collection of 3D ultrasound and motion capture data in a clinical population of ankylosing spondylitis patients (already underway).
b) Implement and evaluate a generative machine learning model that uses computer vision approaches to automatically segment ultrasound images and create 3D spinal models.
c) Automate creation of highly patient-specific musculoskeletal models from the generative spine model that will accurately represent patient movements and joint loads for clinical settings.
Preferred start date – 2 October 2023
Please follow this link for more info and for applying online: https://www.findaphd.com/phds/projec...tings/?p154414
Informal enquiries are welcomed and should be directed to Dr Dario Cazzola (dc547@bath.ac.uk).
Application deadline 2nd April.
All the best.
Dario