Job description

We invite applications for a doctoral student position on tomographic image reconstruction using deep dictionary learning with the Mathematical Imaging Group at the Department of Mathematics.

The position is part of a larger medical imaging project where the overall goal is to develop theory and algorithms for image reconstruction applicable to various x-ray based medical imaging modalities with under-sampled and/or highly noisy data. Overall clinical goals are to significantly reduce the total dose of x-rays and/or acquisition time while maintaining a clinically useful image quality, alternatively to significantly improve image quality given a fixed total dose/acquisition time.

The position includes development of theory and algorithms that combine methods from machine learning with sparse signal processing for joint dictionary design and image reconstruction for clinical 3D axial/helical CT and spectral CT. A key element is to design dictionaries using techniques from machine learning that not only yield sparse representation, but also contain discriminative information.

The research includes both theoretical development as well as implementation of numerical algorithms. The large-scale nature of the problems requires algorithms that not only convergence fast but also have small memory footprint. Algorithms will be implemented as software components integrated with TensorFlow and ODL (http://github.com/odlgroup/odl), the latter is a Python-based software framework for numerical functional analysis that is used by the group.

The research will be pursued in close collaboration with Philips Research Laboratories in Hamburg and the Neuroimaging clinic at the Karolinska University Hospital in Solna. The candidate is therefore expected to spend significant time at these locations.

There is a possibility to teach at 20% if the candidate wishes to do so.

Qualifications

Applicants must hold, or be about to receive, a MSc degree in (applied) mathematics, mathematical statistics, computational physics/engineering, medical technology, computer science, electrical engineering, computer engineering, information and communication technologies, , or a related area. Furthermore, the applicant must have:

• Strong academic credentials, written and spoken English proficiency, communication and team-work skills.
• Interest in several of the following: design, analysis, verification, implementation, or empirical evaluation of tomographic image reconstruction methods.
• Background in several of the following: mathematics, mathematical statistics, machine learning, signal/image processing, programming languages (preferably python/C++), software engineering, and optimization.
• Preparation and readiness to contribute to our research agenda and to work in an internationally oriented group.

Trade union representatives

You will find contact information to trade union representatives at KTH:s webbpage.

Application

Log into KTH's recruitment system in order to apply to this position. You are the main responsible to ensure that your application is complete according to the ad.

Your complete application must be received at KTH no later than the last day of application, midnight CET/CEST (Central European Time/Central European Summer Time).

Early applications are strongly recommended. An application, written in English, at least in 10pt font, should include:

• Cover letter: One-page summary of your application.
• Cirricum vitae: A document on all your relevant academic, professional, and other achievements, experience, and knowledge. Maximum four (4) pages.
• Transcripts and degrees: Official documents from your previously attended University-level institutions, with certified translations in English (unless provided so by the issuing institution).
• Recommendation letters: Please include detailed contact information for at least two (2) references and attach recommendation letters to your application.
• Statement of purpose: Please discuss: your motivation and research interests, your preparation (studies, technical knowledge, research, experience, etc.) towards a PhD in our group, and your future goals. Maximum two (2) pages.
• Representative publications/technical reports: Up to two (2) documents, up to twelve (12) pages each. For longer documents (e.g., theses), please provide an abstract and a web link to the full text.

Others

The employment is time limited following the regulations for Ph.D. employment in the Higher Education Ordinance (5 years when 80% PhD studies and 20% department service including teaching).

We firmly decline all contact with staffing and recruitment agencies and job ad salespersons.

Disclaimer: In case of discrepancy between the Swedish original and the English translation of the job announcement, the Swedish version takes precedence.