CompLS - Round 5 - Joint project: ATLAS - Al and Simulation for Tumor Liver Assessment - Development of a system for clinical decision support in the diagnosis and treatment of liver tumors based on artificial intelligence and simulation - Subproject B

Malignant tumors in the liver are the second leading cause of cancer-related deaths. The required diagnoses and therapies are time-critical and require highly patient-specific diagnostic and treatment pathways. Here, medical decision making is based on a variety of interdependent factors involving different medical specialties, personal experience, and clinical guidelines. The consideration of all decision factors in combination with the possible therapy approaches is a challenge for physicians and often cannot be solved optimally even in an interdisciplinary tumor board. In this project, we are developing ATLAS, a tool to support clinical decision making. Based on AI methods, ATLAS processes all relevant patient data from databases, systems medicine and continuum biomechanical in silico modeling data, and individual patient data. The tool is developed in a co-design approach by experts in surgical oncology, mathematical modeling and machine learning. The chosen methods combine automated understanding of a highly complex patient situation by simulating liver functions with expert knowledge and ontology-based learning with knowledge graphs from retrospective cases of liver tumors. Here, ATLAS is based on a detailed historical data cohort of more than 6,000 patients with liver tumors and is evaluated by case studies. The integration of expert medical knowledge, mathematical modeling, and AI represents a highly innovative and promising approach for high-quality diagnosis and treatment of liver tumors, leading to patient-specific prognosis improvement. In addition, the development of ATLAS provides sustainable utility for future commercial applications.