The Dutch screening programme offers a biennial mammographic examination to asymptomatic women from 50 to 75 years. Since the implementation of screening, the incidence of early stage invasive breast cancer has increased several-fold, without a substantial decline in advanced stage breast cancer incidence. This suggests overdiagnosis of early lesions. At the same time, some breast cancers are detected at an advanced stage, when cure is no longer an option. Consequently, overtreatment of women might occur for 'early' indolent cancer, whereas other cancers are treated 'too late', despite screening.

The IMAGINE study aims to optimise screening referral practice, by finding and internally validating image features, individual and in combination, of breast cancer that are predictive of the risk of recurrence. We hypothesize that image features determined by conventional and deep learning methods, on one or more screening mammograms, will allow for better risk assessment of a lesion identified at screening. This information will help the screening radiologist to optimise referral decisions, enabling timely detection of potentially lethal cancers, while in case of indolent disease referral might be prevented or delayed.

The IMAGINE study will be performed in collaboration with a consortium of national partners. The PhD student will work closely with the postdoc at Radboudumc (working on image features), but also with other partners of the project (in particular the National Cancer Institute/Antonie van Leeuwenhoek hospital (working on pathology subtypes) and University Medical Center Utrecht (working on prognostic models)).

Tasks and responsibilities

• Supporting data collection of diagnostic mammograms and pathology data;
• Collecting the tissue blocks from the labs and coordinating staining of histologic slides;
• Statistical data-analysis to develop the image feature-based prognostic models;
• Interacting with all members of the consortium to ensure multidisciplinary input in interpretation of the results;
• Writing scientific publications and preparing presentations for (inter)national conferences.

• A Master's degree in epidemiology, biomedical sciences, health sciences or medicine;
• Keen interest in and affinity with risk prediction modelling;
• A curious and creative mind combined with excellent analytical skills (experience in R is an advantage);
• Strong problem-solving skills and a capacity to produce results;
• Excellent English proficiency in oral and written communication;
• Ability to work both independently and as part of a team.

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

The Department for Health Evidence aims to improve healthcare and public health by developing, applying and teaching methods for prediction and evaluation research. We have three main tasks: research, education, and consultation. The focus of all three is on research methodology and data analysis, in the context of Radboudumc's research themes. The PhD student will be part of the research subgroup on Cancer Screening and Follow-up.

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 how you can do your part.