Project: Clinical decision support for predicting cachexia in cancer patients using hybrid PET/CT imaging

Acronym	PETictCAC (Reference Number: ERAPERMED2021-324)
Project Topic	Cancer associated cachexia (CAC) is characterized by systemic inflammation, which disrupts energy homeostasis. Treatment of CAC focuses mainly on the compensation of weight loss. However, total parenteral nutrition fails to provide sustained clinical benefits. Therefore, novel approaches to diagnose and prognosticate CAC are required for improved patient management. As such, whole-body PET (WB-PET) imaging enables the observation and quantification of molecular processes in multiple organs across the entire human body. However, WB-PET image information is typically not explored to its full potential in clinical routine. This proposal seeks to establish and validate a high-throughput computational framework that exploits artificial intelligence (AI) to support an automated analysis of metabolic interactions between organs based on WB-PET imaging. Our hypothesis is that energy homeostasis is disturbed before weight loss becomes apparent in cancer patients. Specifically, we aim to assess the clinical value of AI-driven clinical decision support (CDS) built on multi-organ analysis in lung cancer (LC) patients for early diagnosis of CAC. 18F-labelled glucose (FDG) WB-PET will reveal systemic properties of energy homeostasis through probing the interrelationship between the individual regulatory systems centred in the CNS and periphery. For the analysis of these complex datasets, we will develop a CDS system for the early detection of CAC in LC patients. We will incorporate ethical consideration during the design of this CDS as an important adjunct to regulatory compliance and prior to the roll-out of potential CDS tools to participating clinical centres. Moreover, we aim to increase the understanding of the mechanics of the AI-based CDS by addressing pertinent challenges of “explainable AI” through the a priori engagement of relevant stakeholders. This comprehensive approach will provide added value to cancer patients at risk of developing cachexia.
Network	ERA PerMed
Call	4th Joint Transnational Call for Proposals (2021)

Project partner

Number	Name	Role	Country
1	Medical University Vienna	Coordinator	Austria
2	Azienda Ospedaliero Universitaria di Careggi	Partner	Italy
3	University Leipzig	Partner	Germany
4	University of Copenhagen	Partner	Denmark