Improving Diagnosis and Predicting Treatment Response in High-Grade Serous Ovarian Cancer Using Multiple Data Types and AI to Guide Personalized Therapy

What this Trial Is About

Chemotherapy resistance is a major cause of death in advanced cancers, especially in high-grade serous ovarian cancer (HGSOC), which is often diagnosed after it has spread widely in the abdomen. Standard treatment includes surgery followed by platinum-taxane chemotherapy and maintenance therapy. Although 90% of patients show no clinical signs of cancer after treatment, only 43% survive five years due to chemoresistant cancer. This research aims to identify key mechanisms behind chemotherapy resistance in HGSOC and develop personalized treatment plans for resistant cases using advanced data and AI methods. Participants newly diagnosed with advanced HGSOC will be closely monitored throughout their cancer treatment. The study collects various samples over time, such as digitalized histology slides, fresh tumor and ascites samples for detailed genetic and protein analyses, plasma for circulating tumor DNA testing, and imaging scans like FDG PET/CT. Researchers will analyze these data using AI to predict treatment responses and identify genomic changes. Long-term organoid cell lines from tumor tissues will be grown to test drugs outside the body. The study also aims to create AI tools and software to assist clinical decisions and personalized therapy choices. During the study, participants will undergo regular clinical assessments, imaging, laboratory tests, and sample collections. Researchers will gather broad clinical data, including treatment details and outcomes. The main goals are to translate these detailed findings into clinical practice over five years and successfully predict patient outcomes using AI. This approach hopes to improve diagnosis, predict therapy resistance, and suggest targeted treatments for HGSOC patients.

Multi-layer Data to Improve Diagnosis, Predict Therapy Resistance and Suggest Targeted Therapies in HGSOC