Radiotherapy (RT) is a key treatment modality for cancer, but side-effects can have significant negative impact
on patients’ quality-of-life. Intensity-Modulated Proton Therapy (IMPT) is a new type of RT, better preserving normal tissues surrounding the tumor than traditional photon therapy, due to the finite range of protons. However, IMPT’s
advantage also comes at the cost of increased sensitivity to uncertainties in patient alignment, daily variations in patient anatomy or progressive changes, which can never be completely eliminated. To account for uncertainties in IMPT, the current clinical practice is robust treatment planning, where possible errors are directly incorporated in the optimization to make treatments robust. However, while sufficient robustness in IMPT treatments is crucially
important, robust planning has several limitations, as it only includes a few (typically 7) specific errors scenarios, it disregards the probability of different errors happening, and most importantly it does not give the detailed, statistically meaningful measures that clinicians would need. This prevents exploiting the full tissue-sparing potential of IMPT, and could even nullify its advantage compared to conventional RT.
To provide a solution, the PROSPER project will develop techniques for computationally feasible probabilistic optimization. PROSPER (PRObabiliStic Proton thERapy planning) is a collaborative project between Erasmus Medical Center, Holland Proton Therapy Center and our industrial collaborator, in which 2 PhDs will work on both the fundamental numerical research necessary to include uncertainties in treatment planning in a statistically meaningful manner and the clinical testing of such methods compared to robust optimization. The goal of this PhD (embedded at TU Delft) is the methodological development, where both classic numerical approaches such as Polynomial Chaos Expansion (PCE) and state-of-the-art deep learning methods will be investigated to allow probabilistic plan optimization. We will develop different optimization methods, evaluate their computational feasibility and performance, and use this novel computational framework to make probabilistic multi-criteria optimization feasible and balancing trade-off between tumor coverage probability vs. organ overdose probability possible. This will ultimately lead to plans that have a better control on errors, hence can maintain treatment effectiveness without excessively being robust, minimizing side effects.
To qualify for this position you must have:
- An MSc degree (or equivalent) in applied physics, applied mathematics, medical physics, biomedical engineering, computer science or a strongly related field.
- Solid background in applied mathematics and computational physics, especially in probability theory, numerical analysis, statistics and algorithm development.
- Demonstrated experience in programming in at least one current language (e.g., Python, Matlab, C/C++).
- A proven record and interest in further developing modelling, programming and analytical skills.
- Strong affinity and enthusiasm for state-of-the-art numerical modelling, statistics and deep learning methods, and their medical applications.
- Demonstrated ability to be results oriented, applying creativity and out-of-the-box thinking to produce innovative concepts and solutions.
- Demonstrated proficiency in expressing yourself verbally and in writing in English, proven affinity for scientific writing.
- The ability to work in a team and take initiative.
- Affinity for teaching and guiding students.
To be a strong candidate for this position, it is nice – but not necessary – if you have:
- Background in medical physics or radiotherapy.
- Prior experience in numerical modelling/artificial intelligence/machine learning/data science.
- Demonstrated experience with convolutional neural networks, generative adversarial networks and/or transformer architectures.
- Proven familiarity with modern deep learning libraries (PyTorch, TensorFlow, PyMC3).
All candidates will receive consideration regardless of gender, race, religion, sexual orientation, disability status, and all other characteristics protected by law. We encourage all qualified candidates to apply, and we especially welcome applications from historically underrepresented minorities in the STEM field.
Salary and benefits are in accordance with the Collective Labour Agreement for Dutch Universities. The TU Delft offers a customisable compensation package, a discount on health insurance and sport memberships, and a monthly work costs contribution. Flexible work schedules can be arranged.
For international applicants we offer the Coming to Delft Service and Partner Career Advice to assist you with your relocation. An International Children’s Centre offers childcare and there is an international primary school.
Doctoral candidates will be offered a 4-year period of employment in principle, but in the form of 2 employment contracts. An initial 1,5 year contract with an official go/no go progress assessment within 15 months. Followed by an additional contract for the remaining 2,5 years assuming everything goes well and performance requirements are met.
Salary and benefits are in accordance with the Collective Labour Agreement for Dutch Universities. As a PhD candidate you will be enrolled in the TU Delft Graduate School. The TU Delft Graduate School provides an inspiring research environment with an excellent team of supervisors, academic staff and a mentor. The Doctoral Education Programme is aimed at developing your transferable, discipline-related and research skills.
The TU Delft offers a customisable compensation package, discounts on health insurance and sport memberships, and a monthly work costs contribution. Flexible work schedules can be arranged. For international applicants we offer the Coming to Delft Service and Partner Career Advice to assist you with your relocation.
Delft University of Technology is built on strong foundations. As creators of the world-famous Dutch waterworks and pioneers in biotech, TU Delft is a top international university combining science, engineering and design. It delivers world class results in education, research and innovation to address challenges in the areas of energy, climate, mobility, health and digital society. For generations, our engineers have proven to be entrepreneurial problem-solvers, both in business and in a social context. At TU Delft we embrace diversity and aim to be as inclusive as possible (see our Code of Conduct). Together, we imagine, invent and create solutions using technology to have a positive impact on a global scale. Challenge. Change. Impact!
Faculty of Applied Sciences / Department of Radiation Science and Technology
The Faculty of Applied Sciences is the largest faculty of TU Delft, with around 550 scientists, a support staff of 250 and 1,800 students. The faculty conducts fundamental, application-oriented research and offers scientific education at the bachelor, master and doctoral levels. The faculty is active in the fields of Life and Health Science & Technology, Nanoscience, Chemical Engineering, Radiation Science & Technology, and Applied Physics.
The position is in the Department of Radiation Science and Technology (RST, www.tudelft.nl/rst). Radiation ties the RST department together. The focus of our research is on energy and health. However various our interests, whether they be materials, sensors and instrumentation, energy and sustainable production or health, all our research is somehow related to radiation. Close collaboration with the Reactor Institute Delft and the newly built Holland Proton Therapy Center (HollandPTC) guarantees access to the reactor and the irradiation facilities, as well as to a clinical proton beam.
For information about this vacancy, you can contact:
Dr. Zoltan Perko, Associate Professor.
Include PROSPER in the subject line
To apply for this PhD position, pleas submit your application on the online platform. You will need to include:
• Motivation letter (1 page, A4 size, font size 12, PDF format), highlighting past achievements that demonstrate your relevant competence and specific interest and enthusiasm for this project.
- Your CV (PDF format), including contact details of two references who we can contact if needed to attest to your academic attitude, skills and work ethic.
- A summary of your M.Sc. thesis (1 page, A4, size 12, PDF format).
- A list of courses and grades taken for your B. Sc. and M. Sc. (or similar education).
• If applicable, a paper that you have written in which you demonstrate your writing skills (PDF format).
Applications which do no follow the format specifications, are incomplete or are not sent in via the application platform will not be considered. Emailed applications will not be considered. Screening applicants will start after 2022.08.15.