Speaker
Description
Zoltán Perkó is an internationally recognized researcher of computational physics and deep learning in radiation applications. He is a Senior Applied Scientist at Radformation Inc. and an associate professor at Delft University of Technology. His research focuses on cancer treatment planning (AI solutions, robust optimization, adaptive radiotherapy) and data driven physics based modeling of large scale systems (uncertainty quantification, model reduction) for real-life impact.
Summary
Treatment planning is crucial to providing effective particle and radiation therapy treatments and involves several computationally expensive steps, from dose calculation, through optimizing competing dosimetric objectives while respecting organ constraints and ensuring final plan deliverability, to robustness evaluation and secondary checks. The move towards online and real-time adaptive treatments puts stringent time constraints on all these processes, which are often challenging for traditional methods. AI approaches have the potential to not only overcome these computational barriers, but to also allow more automation, better decision making, higher plan consistency, and ultimately higher quality and better outcomes.
In this talk I will present the state-of-the-art of AI methodologies applied to treatment planning, including methods for dose calculation, dose prediction, machine parameter optimization, knowledge based approaches and large language model powered agentic workflows aimed at enabling wide-scale application of online adaptive workflows and future real-time adaptation or direct biology and outcome based planning.