Do you want to contribute to top quality medical research?  

The Department of Molecular Medicine and Surgery (MMK) and the Cardiovascular Magnetic Resonance (CMR) Group is looking for a postdoctoral researcher to work with Dr. David Marlevi and co-workers on the use of machine learning and physics-informed analysis for improved hemodynamic risk prediction using four-dimensional flow magnetic resonance imaging (4D Flow MRI). Based in a clinically integrated, well-established larger network on cardiovascular imaging, and as part of a broad-reaching European research initiative, you will join a team expanding and evaluating dedicated data-driven imaging networks and processing algorithms for improved cardiovascular diagnosis, pushing 4D Flow MRI into previously inaccessible domains through a combination of experimental and clinical studies.

Your mission

Four-dimensional flow magnetic resonance imaging (4D Flow MRI) has emerged as a powerful imaging technique, providing unique full-field mapping of blood flow across various cardiovascular compartments. However, the required extensive acquisition limits effective spatiotemporal coverage, hindering assessment of narrow vasculatures or transient flow events. The incorporation of machine learning into medical image practice is, however, starting to fundamentally change what can be analysed and resolved. Specifically, our group has shown how the use of super-resolution networks and physics-informed image processing now allow for usage of 4D Flow MRI through previously inaccessible domains, opening for novel diagnostic paradigms.

The postdoctoral researcher will continue these efforts on quantitative 4D Flow MRI, targeting spatiotemporal super-resolution conversion using dedicated neural networks. This will include further enhancement of existing discriminatory networks (CNN), as well as extension into generative (GAN; Transformers; Difussion) or physics-informed (PINN) networks to improve resolution and image quality. Work may also couple into group efforts on dedicated acquisition sequences, improving scan efficiency and providing inline realization of developed networks. Making use of our translational team, work is also expected to include evaluation in existing patient-specific models, benchtop validation setups, as well as clinical patient cohorts, serving our overall goal of improving our understanding of hemodynamic risk through various cardiovascular compartments.

Your profile

We are looking for a highly motivated, creative, and independent researcher with a PhD and strong research background in scientific machine learning, with application for medical imaging purposes desired but nor required. Specific areas of relevance include, but are not limited to, discriminative and generative networks, super-resolution imaging, learned image acquisition or reconstruction, or computer vision. Solid and documented experience from scientific neural network implementations and programming including libraries such as TensorFlow or PyTorch, terminal scripting, and use/management of high-performance computers for network training and testing is essential. Previous experience from translation of neural networks into clinical studies, or basic knowledge of MR physics is also seen as an advantage. Scientific expertise and an ambitious, independent, and problem-solving attitude are highly valued. Excellent communication skills in both spoken and written English are a must, as is the ability to interact and work in a translational team of technical and clinical colleagues on an international level. Emphasis will also be placed on personal competence. The postdoctoral researcher will get the opportunity to co-write grants and articles, supervise students, and take part in career mentorship; all providing an excellent basis for a further career as a project leader in academic or relevant industry.

To be eligible for employment as a postdoctor a doctoral degree or a foreign degree deemed to be equivalent to a doctoral degree is required. This eligibility requirement must be fulfilled at the latest at the time of the employment decision. It is considered as an advantage if you have completed your doctoral degree within the last three years, if there are special reasons, your degree may have been completed earlier.

What do we offer?

As part of the Cardiovascular Magnetic Resonance Group, we offer a unique translational research environment with wide-ranging expertise spanning clinical science, biomedical engineering, and medical physics, all working together to improve cardiovascular disease diagnostics. With the position part of a recently funded broad-reaching European research initiative for advanced hemodynamic imaging (the MultiPRESS project: https://academic.oup.com/eurheartj/advance-article/doi/10.1093/eurheartj/ehad062/7046109?login=false), the candidate will also be directly involved in cutting-edge data-driven image science, collaborating with international networks to push learned and physics-driven imaging into novel application areas. Further, being deeply integrated with the clinical activities at the Karolinska University Hospital, direct access to state-of-the-art imaging equipment, diverse patient cohorts, and relevant computational resources provide excellent opportunities for ground-breaking research.

On a larger scale, Karolinska Institutet also offers a creative and inspiring environment with wide-ranging expertise and interests. Karolinska Institute is one of the world’s leading medical universities, and home of the Nobel Prize in Medicine or Physiology, attracting experts from disparate fields to enable next-generation care and novel insight into physiological mechanisms. Karolinska is also a state university, which entitles you to several benefits through our collective agreement.


Location: 

The position is located within the Department of Molecular Medicine and Surgery (MMK), Solna. The Department consists of 22 research groups, spanning preclinical and clinical work. The position is located within the Cardiovascular Magnetic Resonance Group lead by Prof. Marcus Carlsson and the research team lead by Dr. David Marlevi, jointly consisting of around 20 people and with direct extensions into the clinical facilities. The group is part of the unit of Clinical Physiology at the Karolinska University Hospital site in Solna, with close proximity to both clinical and academic partners along with an excellent variety of core facilities and research support.

Application

An employment application must contain the following documents in English or Swedish:

  • A complete resumé, including date of the thesis defence, title of the thesis, previous academic positions, academic title, current position, academic distinctions, and committee work
  • A complete list of publications
  • A summary of current work (no more than one page)

Welcome to apply at the latest June 16, 2023

The application is to be submitted through the Varbi recruitment system.

 

Want to make a difference? Join us and contribute to better health for all

Type of employment Temporary position
Contract type Full time
Salary Månadslön
Number of positions 1
Full-time equivalent 100%
City Stockholm
County Stockholms län
Country Sweden
Reference number STÖD 2-2026/2023
Contact
  • David Marlevi, Principal Investigator, david.marlevi@ki.se
Union representative
  • Virpi Töhönen, SACO, virpi.tohonen@ki.se
  • Taher Darreh-Shori, SACO, taher.darreh-shori@ki.se
  • Elisabeth Noren-Krog, OFR, elisabeth.noren-krog@ki.se
Published 16.Mar.2023
Last application date 25.Jun.2023 11:59 PM CEST

Return to job vacancies