Postdoc position in machine learning for cardiovascular imaging

Do you want to contribute to top quality medical research?

The Department of Molecular Medicine and Surgery (MMK) is looking for up a postdoctoral researchers to join Ass Prof. David Marlevi and his team on the use of machine learning for improved hemodynamic risk prediction using cardiovascular imaging in general, and four-dimensional flow magnetic resonance imaging (4D Flow MRI) in particular. 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 evaluating dedicated data-driven imaging networks and processing algorithms for improved cardiovascular diagnosis, pushing cardiovascular 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, acquisition, reconstruction and analysis still require complex analysis and clinical limitation in terms of manual data handling, spatiotemporal resolution limits, and so on still limit effective modality usage. The incorporation of machine learning and advanced MR-physics implementations 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 imaging, targeting data-driven data enhancements using dedicated neural networks and mathematical algorithms to streamline analysis and improve physiological insight. Work may include further enhancement of existing data-driven approaches into more advanced purpose-built setups (expanding into Diffusion, Transformer, or Foundation Model networks) as well as proposing novel utilities for higher-dimensional data analysis.

Making use of our translational team, work is expected to include evaluation in existing patient-specific models, benchtop validation setups, on dedicated and available MR-systems, 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 at least one highly motivated, creative, and independent researcher with a PhD and strong research background in scientific machine learning. Application for medical applications, medical imaging, or phase-contrast imaging are desired but nor required.

Specific areas of relevance include, but are not limited to 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 is seen as an advantage, as is experience from utilizing machine learning for clinical predictions or tasks.

In general, 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 postdoctoral researcher, a PhD or a foreign degree deemed to be equivalent to a Swedish PhD is required. This eligibility requirement must be fulfilled at the latest at the time of the employment decision. Completion of your doctoral degree within the last three years is considered an advantage. If there are special reasons, your degree may have been completed earlier.

What do we offer?

As part of the team of Ass. Prof. Marlevi and the wider group of Clinical Physiology, 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.

A creative and inspiring environment with wide-ranging expertise and interests. Karolinska Institutet is one of the world's leading medical universities. At Karolinska Institutet, we conduct successful medical research and hold the largest range of medical education in Sweden. At KI, you get to meet researchers working with a wide range of specialisms and methods, giving you ample opportunity to exchange knowledge and experience with the various scientific fields within medicine and health. It is the crossover collaborations, which have pushed KI to where it is today, at the forefront of global research. Several of the people you meet in healthcare are educated at KI. A close relationship with the health care providers is important for creating groundbreaking top quality education and research. Karolinska Institutet is also a state university, which entitles you to several benefits through our collective agreement.

Location: Solna

Choose to work at KI – Ten reasons why

Clinical Physiology – Marcus Carlsson's research group | Karolinska Institutet

Application

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

• PhD certificate
• 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)

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!