Radiotherapy is a primary treatment modality for patients with non-small cell lung cancer (NSCLC). However, managing treatment-related toxicity remains a significant challenge. Current clinical workflows are limited by the use of static treatment plans that do not account for daily anatomical variations or the evolving biological state of the tumor. Online adaptive radiotherapy (ART) addresses these limitations by allowing for plan adjustment while the patient is on the treatment table, utilizing daily in-room cone-beam CT (CBCT) imaging.
As a PhD candidate, you will focus on the development and clinical validation of novel online adaptive workflows. Your research will integrate artificial intelligence for image enhancement, the evaluation of novel radiotherapy schedules, and the use of liquid biopsies for biological monitoring. The objective is to transition toward highly individualized treatment strategies that improve both tumor control and patient safety.
You will utilize Deep Learning systems, which enhance CBCT image quality, aiming for a level of accuracy sufficient for direct treatment adaptations. Based on these scans, we will create a "direct-to-LINAC" workflow. This bypasses traditional pre-treatment planning CTs, potentially improving treatment accuracy and efficiency. You will be responsible for analyzing data from clinical trials investigating a novel radiation protocol, "Primer Shot." This involves a single high-dose fraction followed by a three-week break designed to facilitate tumor reoxygenation. Finally, to complement anatomical adaptation, you will investigate biological markers of treatment response. This involves training and validating a liquid biopsy hypoxia signature. By analyzing protein and DNA/RNA panels in blood and correlating them with validated tissue signatures, you will assess the feasibility of non-invasively monitoring tumor oxygenation and response over a multi-week treatment course.
Test and validate AI models for CBCT image enhancement to support online adaptive adaptations.
Design in-silico studies to evaluate the accuracy and robustness of CBCT-based plan adaptations.
Clinically validate CBCT-guided online adaptations in a prospective trial for direct-to-treat radiotherapy.
Analyze clinical data from the "Primer Shot" trials, including tumor response and toxicity outcomes.
Train a liquid biopsy hypoxia signature and correlate this with clinical outcomes.
Collaborate within a multidisciplinary team of medical physicists, radiation oncologists, and AI researchers at the Netherlands Cancer Institute (NKI).
Present research findings at international conferences and publish in peer-reviewed medical physics and oncology journals.
You will be based at the Department of Radiation Oncology of the Netherlands Cancer Institute (NKI), embedded in an experienced, highly interdisciplinary team of medical physicists, physician-scientists, AI researchers and radiation technologists (RTTs).
At the Netherlands Cancer Institute, we have a shared goal: providing the best care for every patient and every type of cancer. Quite a lot, but not impossible. Here, science and health care join forces towards innovation. We keep finding new ways to help people facing cancer on a global scale. Here we save lives, gain time and quality.
In the Department of Radiation Oncology, we are internationally recognized for image-guided and adaptive radiotherapy, including advanced CBCT- and MR-linac-based treatments, and for close collaboration between clinic, physics and data science.