The Cancer Drug Development Forum (CDDF) is pleased to present our live webinar series on “AI and Big Data in Cancer Drug Development.” This series is designed to explore the transformative impact of artificial intelligence and big data on oncology. Featuring leading experts, the webinars delve into the latest advancements and applications of AI in cancer drug discovery, development, and regulatory processes. Join us to uncover how these cutting-edge technologies are accelerating innovation, improving efficiency, and enhancing outcomes in oncology drug development.
You can learn more and rewatch the recording of the first two webinars here.
The third webinar in the series “Transformation of future clinical trials using AI-enhanced imaging biomarkers” took place on 18 September 2025 at 17:00 CEST. This webinar featured a lecture given by Prof. Joahnnes Haubold and was followed by a second presentation by Dr. Sasa Grbic (Siemens Healthineers). A panel discussion moderated by Prof. Rosa Giuliani (CDDF) and Prof. Ricky Sharma (Varian) followed thereafter.
WEBINAR OUTLINE
In the first presentation, Professor Johannes Haubold introduced the role of CT-based body composition metrics as emerging predictors of clinical outcomes in patients with solid tumors. Using lung cancer and renal cancer as illustrative examples, Professor Haubold will explain how these measurements are derived from routine imaging and discuss their growing clinical relevance. He will also review key studies that support the prognostic value of these metrics, highlighting their potential to inform patient management and therapeutic decision-making in oncology.
The second presentation will be delivered by Dr. Sasa Grbic, who will focus on how artificial intelligence solutions can enhance the analysis of chest CT scans to support the next generation of oncology clinical trials. Dr. Grbic will demonstrate how AI tools can detect and quantify a range of imaging biomarkers and comorbidities, including lung nodules, emphysema, coronary artery calcifications, vertebral height loss, bone mineral density, and airspace opacities. By automating these complex assessments, AI has the potential to improve consistency and reproducibility across study sites and timepoints, ultimately contributing to more reliable trial outcomes.
Following the presentations, a moderated panel discussion explored the broader implications of these technologies. The panel considered whether body composition data and AI-derived imaging biomarkers should be routinely incorporated into oncology clinical trial protocols. The discussion explored how these tools could improve data quality, enhance trial efficiency, and facilitate more effective stratification of trial participants. The panel also engaged with the audience’s questions and reflections on the presented topics.
Agenda: (CEST time zone)
17:00 – 17:05 Introduction – Prof. Rosa Giuliani (CDDF)
17:05 – 17:20 Lecture by Prof. Johannes Haubold (University of Essen)
17:20 – 17:35 Lecture by Dr Sasa Grbic (Siemens Healthineers)
17:35 – 18:00 Panel discussion – moderated by Prof. Rosa GIuliani (CDDF) and Prof. Ricky Sharma (Varian)
Prof. Johannes Haubold
Prof. Johannes Haubold is Senior Consultant in Diagnostic and Interventional Radiology and Neuroradiology at University Hospital Essen (Germany). He also heads the medical team at the Institute for Artificial Intelligence in Medicine, where he and his colleagues integrate AI solutions from research into everyday clinical practice. His research focuses on image-based biomarkers, automated segmentation, and generative AI for medical image processing.
Sasa Grbic
Sasa Grbic serves as Sr. Director within the Siemens Healthineers AI Technology Center. His team specializes in creating AI solutions using large data collections for novel healthcare applications in the space of oncology and MSK. His scientific contributions to medical imaging translated into multiple clinical products focused on improving the quality of care, specifically in the fields of diagnostic imaging, therapy planning and personalized medicine. He received his PhD degree in computer science from the Technical University in Munich.