Enhancing clinical brain MRI scans with deep learning for improved deep brain stimulation
Lead Research Organisation:
University College London
Department Name: Medical Physics and Biomedical Eng
Abstract
1) Brief description of the context of the research including potential impact
Deep brain stimulation (DBS) is a surgical procedure used to treat several neurological conditions, such as Parkinson's disease and epilepsy. The procedure involves implanting electrodes in the brain in order to stimulate certain brain regions. To do this, surgeons first need to accurately locate the regions to be stimulated. Ultra-high field MRI produces high-quality brain scans which significantly ease this task. However, ultra-high field scanners are not widely available. Access to DBS could thus be improved if it was possible to obtain higher quality scans from standard MRI scanners.
2) Aims and Objectives
The aims of the project are:
- To develop an AI system for enhancing standard clinical MRI images, using data from the ultra-high field scanners
- To improve accuracy when locating brain regions for DBS using standard clinical MRI scans
3) Novelty of Research Methodology
The methodological novelty of this project lies in exploiting state-of-the-art deep learning approaches to enhance low-quality clinical MRI data from high-quality MRI data.
4) Alignment to EPSRC's strategies and research areas
The project aligns with EPSRC's "Healthcare technologies" theme, addressing in particular its Challenge three - "Discovering and accelerating the development of new interventions" - as it seeks to develop a novel method to improve outcomes of image-guided treatments.
5) Any companies or collaborators involved
The project is co-funded by Brain Research UK
Deep brain stimulation (DBS) is a surgical procedure used to treat several neurological conditions, such as Parkinson's disease and epilepsy. The procedure involves implanting electrodes in the brain in order to stimulate certain brain regions. To do this, surgeons first need to accurately locate the regions to be stimulated. Ultra-high field MRI produces high-quality brain scans which significantly ease this task. However, ultra-high field scanners are not widely available. Access to DBS could thus be improved if it was possible to obtain higher quality scans from standard MRI scanners.
2) Aims and Objectives
The aims of the project are:
- To develop an AI system for enhancing standard clinical MRI images, using data from the ultra-high field scanners
- To improve accuracy when locating brain regions for DBS using standard clinical MRI scans
3) Novelty of Research Methodology
The methodological novelty of this project lies in exploiting state-of-the-art deep learning approaches to enhance low-quality clinical MRI data from high-quality MRI data.
4) Alignment to EPSRC's strategies and research areas
The project aligns with EPSRC's "Healthcare technologies" theme, addressing in particular its Challenge three - "Discovering and accelerating the development of new interventions" - as it seeks to develop a novel method to improve outcomes of image-guided treatments.
5) Any companies or collaborators involved
The project is co-funded by Brain Research UK
People |
ORCID iD |
Hui Zhang (Primary Supervisor) | |
Cosimo Campo (Student) |
Studentship Projects
Project Reference | Relationship | Related To | Start | End | Student Name |
---|---|---|---|---|---|
EP/S021930/1 | 01/10/2019 | 31/03/2028 | |||
2897458 | Studentship | EP/S021930/1 | 01/12/2023 | 30/11/2027 | Cosimo Campo |