Development of conventional and AI-based methods for mammographic image analysis to optimize breast cancer screening.

In this project, we will develop new artificial intelligence-based and conventional image analysis methods, leveraging recent advances in deep learning and in AI-based automated interpretation of medical images, to optimize the breast cancer screening image interpretation process. Automated AI-based systems can now interpret mammography images with similar performance to that of screening breast radiologists. However, more work is needed before they can have a real and optimal impact on large, regional and national screening programs, like the Dutch National Breast Cancer Screening Programme.

Developing and combining new methods to analyze the images, both in search of lesions but also for interpretation of the tissue patterns present, and their impact on human interpretation, will allow for having a real and impactful influence on the performance of breast cancer screening. This, in turn, will allow for an increase in the early detection of cancer, while reducing the rate of false alarms. As a result, we envision that screening will become more effective and efficient.

The AXTI (Advanced X-ray Tomographic Imaging) laboratory of the Department of Radiology and Nuclear Medicine at Radboudumc works closely with breast screening radiologists and industry to develop new, and improve existing, methods and processes in screening and clinical breast imaging. Our direct connection with the Dutch Expert Centre for Screening (LRCB) ensures and maximizes the relevance and applicability of our developments.

In addition, in this project we will work together with experts in human visual perception, AI-based interpretation of images, AI-based and conventional image analysis methods, and breast cancer screening. We will also work closely with industrial partners that are involved in every aspect of breast cancer image interpretation in screening, including AI, image analysis, and image display and workflow companies.

Tasks will consist of development of novel AI and conventional image analysis methods to optimize the incorporation of AI into breast cancer screening, as well as presenting and writing papers on the study results.

• You should be a creative and enthusiastic researcher with a MSc degree in artificial intelligence, physics, mathematics, medical physics, biomedical engineering, or similar.
• Experience or interest in radiology and/or medical imaging and affinity with biomedical research.
• Experience in programming in Python (and preferably other languages, like C++).
• Excellent communication skills in English, both written and spoken.

Fixed-term contract: 4 years.

Upon commencement of employment we require a certificate of conduct (Verklaring Omtrent het Gedrag, VOG) and there will be, depending on the type of job, a screening based on the provided cv. Radboud university medical center's HR Department will apply for this certificate on your behalf.

Read more about the Radboudumc employment conditions and what our International Office can do for you when moving to the Netherlands.

Radboudumc

Department of Radiology, Nuclear Medicine and Anatomy
The Department of Radiology, Nuclear Medicine and Anatomy is one of the most active research departments of the Radboudumc. More than 100 researchers are continuously striving to optimize healthcare. Close cooperation between preclinical researchers, radiologists and cardiologists gives a fantastic opportunity to implement new imaging techniques in clinical practice, and you will be working directly in this field.

Advanced X-ray Tomographic Imaging laboratory
The AXTI laboratory is focused on the development, optimization, and clinical evaluation of new x-ray based imaging methods. The lab focuses on the use of medical physics approaches to improve image acquisition methods and processing algorithms, and to evaluate the clinical performance of new technology in new clinical applications. The group counts with wide-ranging expertise in image processing, reconstruction, and analysis, as well as observer studies, screening, radiation dosimetry, along with the design and performance of patient trials.

Research Institutes
At the moment there are more than 1,300 PhD candidates at our medical hospital. This number includes PhD candidates on our pay roll as well as external candidates (those employed somewhere else but researching on our premises).

• Radboud Institute for Health Sciences: ± 700
• Radboud Institute for Molecular Life Sciences: ± 400
• Donders Center for Medical Neurosciences: ± 200

Read what it is like to do a PhD at the Radboud University Medical Center.

Radboudumc
Radboudumc strives to be a leading developer of sustainable, innovative and affordable healthcare to improve the health and wellbeing of people and society in the Netherlands and beyond. This is the core of our mission: To have a significant impact on healthcare. To get a better picture of what this entails, check out our strategy.

Read more about what it means to work at Radboudumc and what our people have to say about it.