Motivation
Helium radiography and computed tomography are experimental imaging techniques capable of providing high-resolution, low-dose images for various applications in ion beam therapy, including treatment planning, patient positioning verification, and motion management. Owing to their fundamental properties, helium ions exhibit low scattering and can produce metal artifact–free images. Recently, the concept of simultaneous helium imaging during carbon ion radiotherapy (CIRT) has been proposed, offering new possibilities for real-time adaptive CIRT.
However, this approach presents significant challenges due to the presence of high energy fragments generated in helium and especially in mixed carbon-helium beams. These fragments are detected by the imaging system and degrade image quality, limiting the benefits of helium-based imaging. Because these fragments can have energies comparable to primary ions but follow unpredictable trajectories, standard filtering techniques are often ineffective. In this context, deep learning (DL) approaches offer a promising solution. DL-based methods have already demonstrated success in various radiotherapy imaging applications, such as synthetic CT generation from MRI and CBCT, which are crucial for adaptive radiotherapy workflows. The application of DL techniques could enable effective filtration of high energy fragments, allowing only primary helium ions to be used for image reconstruction.
This project lies at the intersection of data science, particle physics, and life sciences, offering advancements that could benefit all three domains.
Requirements
We are looking for excellent graduates holding master’s degrees in computer science, mathematics, engineering, physics or related quantitative sciences (e.g., bioinformatics, medical informatics, robotics).
As an international research school, we require our doctoral researchers to be fluent in English (German is optional). If you are neither a native German nor a native English speaker, we therefore ask for a proof of language skills in form of a certificate (IELTS, TOEFL or CAE) or a certified statement that the studies in your previous university degree were taught in English.

Application Procedure
1. Create a PDF document for your application containing all relevant information and documents outlined using our application tool (see below). Details on essential documents and further requirements are directly indicated in the appropriate sections of the application tool. Find the available projects in the tool and listed: https://www.hidss4health.de/assets/hidss4health/Dokumente/HIDSS4Health_Project_Abstracts_2025.pdf

2. Submit your application document at the DKFZ job portal: https://jobs.dkfz.de/en/jobs/167858/doctoral-researchers-up-to-6-fully-funded-positions-in-data-science-health

3. (optional): Ask two independent referees to submit reference letters to this email address: references@hidss4health.de, or (if you already have them) send the letters yourself.

This project is a collaboration between the Karlsruhe Institute of Technology (KIT) and the German Cancer Research Center (DKFZ) in Heidelberg. It is funded by the Helmholtz Information and Data Science School for Health (HIDSS4Health).