barrier to innovation.
This project will investigate how generative artificial intelligence can be used to improve the assessment of mitral valve diseases in particular mitral regurgitation. The doctoral candidate will develop novel methods analysing different echocardiography data modalities such as b-mode or colorflow and investigate how generating synthetic echocardiographic images can support automated image analysis tasks, such as valve segmentation and the assessment of mitral valve regurgitation. Attention will be given to understanding how patient-specific information can be incorporated into generative models to improve accuracy, consistency and clinical relevance.
Working at the interface of artificial intelligence, medical imaging and cardiovascular medicine, the candidate will evaluate how generated synthetic data can improve the performance and robustness of machine-learning models when compared with training approaches utilising real world data alone. The project will make use of both proprietary clinical datasets and publicly available resources, including the CAMUS echocardiography dataset. Ultimately, the developed methods will be integrated into clinical software and evaluated as part of a prospective study of automated mitral valve assessment.
The project provides a unique opportunity to contribute to the next generation of AI-enabled cardiac imaging technologies within a leading industrial research environment, while benefiting from close collaboration with academic and clinical partners across Europe.
Planned Secondments
- Oslo University Hospital, Norway (3 months): retrospective analysis of mitral valve regurgitation and validation of automated assessment methods.
- IDIBAPS, Spain (2 months): design and implementation of a prospective clinical study for automated mitral valve assessment.
- King's College London, United Kingdom (2 months): investigation of how mechanistic cardiovascular models can complement machine-learning approaches.
Where to apply
Website: https://www.cdtnet.eu/apply-now
Requirements
Research Field: Computer science » Informatics
Education Level: Master Degree or equivalent
Specific Requirements
Desirable Project-Specific Qualifications and Skills
We are looking for highly motivated and solution-oriented applicants with a strong machine learning background. The ideal candidate will have:
- Master’s degree (equivalent to a minimum of 120 ECTS credits) preferably in machine learning, computer science, statistics, applied mathematics/electrical engineering. Other degrees can also be considered given that the candidate has formal competence in machine learning and/or image analysis/computer vision. Foreign completed degrees (M.Sc.-level) must correspond to a minimum of four years in the Norwegian educational system
- A solid background in modern deep learning, machine learning, mathematics, linear algebra, and/or statistics is also required
- Solid knowledge and documented experience with programming in Python and relevant machine learning frameworks (e.g., PyTorch, TensorFlow)
- Fluent oral and written communication skills in English
- Experience with medical image analysis and echocardiography is a plus
- MSCA Mobility Rule: You must not have lived or worked in Norway for more than 12 months in the 3 years before recruitment.
- MSCA Eligibility Rule: You must not already hold a doctoral degree and must be eligible to enrol in the PhD programme at the University of Oslo.
Languages: English
Level: Excellent
Additional Information
Website for additional job details: https://www.cdtnet.eu/
Work Location(s)
Number of offers available: 1
Company/Institute: GE HealthCare
Country: Norway
City: Oslo
Street: Forskningsparken
Contact
City: Oslo
Website: https://www.gehealthcare.com/en-gb
E-Mail: Sarina.Thomas@gehealthcare.com, CDTnet@kcl.ac.uk
