PhD position on Robust, Generalizable AI for Medical Imaging

Artificial intelligence is increasingly being used in medical applications, supporting doctors and other medical professionals in their work, facilitating the analysis of medical images and other data, for more rapid, comprehensive and accurate diagnosis, guidance of surgeries and more. Today, deep learning methods are achieving excellent results on many medical imaging problems, resulting in highly accurate segmentation, recognition, classification, anomaly detection. However, they do not always generalize, meaning they fail when faced with a dataset from a different source (e.g. a different brand of scanner). More generally, they face challenges with so-called Out-of-Distribution (OOD) data or display overly optimistic results on data similar to the training dataset, indicating possible shortcuts and overfitting. This is particularly critical in applications like medical imaging, where data distribution drift may occur due to different imaging protocols, minor change in images obtained from the same modality but different machines, various artifacts. Anomalies and unseen pathologies may further confound the validity and reliability of results.

Your task would be to investigate and improve the robustness and generalizability of AI for medical imaging applications. This may involve the effective detection of out of distribution data or outliers, as well as the development of reliable, generalizable visual analysis solutions for various medical image classification, segmentation, and anomaly detection problems, also in collaboration with medical experts and hospitals.

Requirements:

• We are looking for enthusiastic, highly motivated and curiosity-driven researchers (D/F/M).
• You have, or will shortly, acquire a M.Sc. degree in the field of data science, computer science, electrical engineering, applied mathematics, biomedical engineering, or a closely related study program.
• You have a creative mindset and excellent analytical and communication skills.
• You have a good team spirit and like to work in an interdisciplinary and internationally oriented environment.
• You are proficient in English.

Salary Benefits:

• As a PhD candidate at UT, you will be appointed to a full-time position for four years, with a qualifier in the first year, within a very stimulating and exciting scientific environment;
• The University offers a dynamic ecosystem with enthusiastic colleagues;
• Your salary and associated conditions are in accordance with the collective labour agreement for Dutch universities (CAO-NU);
• You will receive a gross monthly salary ranging from € 2.770,- (first year) to € 3.539,- (fourth year);
• There are excellent benefits including a holiday allowance of 8% of the gross annual salary, an end-of-year bonus of 8.3%, and a solid pension scheme;
• The flexibility to work (partially) from home;
• A minimum of 232 leave hours in case of full-time employment based on a formal workweek of 38 hours. A full-time employment in practice means 40 hours a week, therefore resulting in 96 extra leave hours on an annual basis.
• Free access to sports facilities on campus
• A family-friendly institution that offers parental leave (both paid and unpaid);
• You will have a training programme as part of the Twente Graduate School where you and your supervisors will determine a plan for a suitable education and supervision;
• We encourage a high degree of responsibility and independence, while collaborating with close colleagues, researchers and other staff.

40 hours per week

Drienerlolaan 5