Integrated radiogenomics models predict response to neoadjuvant chemotherapy in high grade serous ovarian cancer.
High grade serous ovarian carcinoma (HGSOC) is a highly heterogeneous disease that typically presents at an advanced, metastatic state. The multi-scale complexity of HGSOC is a major obstacle to predicting response to neoadjuvant chemotherapy (NACT) and understanding critical determinants of response. Here we present a framework to predict the response of HGSOC patients to NACT integrating baseline clinical, blood-based, and radiomic biomarkers extracted from all primary and metastatic lesions. We use an ensemble machine learning model trained to predict the change in total disease volume using data obtained at diagnosis (n = 72). The model is validated in an internal hold-out cohort (n = 20) and an independent external patient cohort (n = 42). In the external cohort the integrated radiomics model reduces the prediction error by 8% with respect to the clinical model, achieving an AUC of 0.78 for RECIST 1.1 classification compared to 0.47 for the clinical model. Our results emphasize the value of including radiomics data in integrative models of treatment response and provide methods for developing new biomarker-based clinical trials of NACT in HGSOC.
Acknowledgements: We dedicate this work to the memory of Prof. Naveena Singh, whose invaluable contributions and enduring passion for the field have left an indelible mark, and she will be greatly missed. We acknowledge funding and support from Cancer Research UK and the Cancer Research UK Cambridge Centre [A22905, C9545/A29580, A25117, A17197, A19274, A20240], the Wellcome Trust Innovator Award [RG98755], The Mark Foundation for Cancer Research and the CRUK National Cancer Imaging Translational Accelerator (NCITA) [A27066]. Additional support was also provided by the National Institute of Health Research (NIHR) Cambridge Biomedical Research Centre [RC-1215-20014] and EPSRC Tier-2 capital grant [EP/P020259/1]. This research was also supported by Target Ovarian Cancer and the Medical Research Council through their Joint Clinical Research Training Fellowship for Dr Moore. Work in the Cancer Molecular Diagnostics Laboratory/Blood Processing Laboratory was supported by the NIHR Cambridge Biomedical Research Centre [BRC-1215-20014], Cancer Research UK Cambridge Centre and the Mark Foundation Institute for Integrated Cancer Medicine. Microsoft Radiomics was provided to Addenbrooke’s Hospital (Cambridge University Hospitals NHS Foundation Trust, Cambridge, UK) by the Microsoft InnerEye project. We thank all patients who participated in and donated samples and data to this study. We thank Karen Hosking and the OV04 study team for their help with clinical samples and data. We thank Oscar Rueda for useful discussions and support with data analysis. We thank staff from the Cancer Molecular Diagnostics Laboratory for performing blood collections. We thank the Cancer Research UK Cambridge Institute Compliance & Biobanking, Research Instrumentation and Cell Services, Genomics and Bioinformatics core facilities for their support with various aspects of this study. The views expressed are those of the authors and not necessarily those of the NHS, the NIHR or the Department of Health and Social Care. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.
Cancer Research UK (C14303/A17197)
Engineering and Physical Sciences Research Council (EP/P020259/1)
Cancer Research UK (A25117)
Cancer Research UK (A19274)
National Institute for Health and Care Research (IS-BRC-1215-20014)