TY - JOUR
T1 - Integrated radiogenomics models predict response to neoadjuvant chemotherapy in high grade serous ovarian cancer
AU - Crispin-Ortuzar, Mireia
AU - Woitek, Ramona
AU - Reinius, Marika A. V.
AU - Moore, Elizabeth
AU - Beer, Lucian
AU - Bura, Vlad
AU - Rundo, Leonardo
AU - Mccague, Cathal
AU - Ursprung, Stephan
AU - Escudero Sanchez, Lorena
AU - Martin-Gonzalez, Paula
AU - Mouliere, Florent
AU - Chandrananda, Dineika
AU - Morris, James
AU - Goranova, Teodora
AU - Piskorz, Anna M.
AU - Singh, Naveena
AU - Sahdev, Anju
AU - Pintican, Roxana
AU - Zerunian, Marta
AU - Rosenfeld, Nitzan
AU - Addley, Helen
AU - Jimenez-Linan, Mercedes
AU - Markowetz, Florian
AU - Sala, Evis
AU - Brenton, James D.
PY - 2023
Y1 - 2023
N2 - 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.
AB - 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.
KW - Artificial Intelligence
KW - Cancer Imaging
KW - Chemiotherapy
KW - HGSOC
KW - Machine Learning Models
KW - Ovarian Cancer
KW - Predictive Markers
KW - RECIST
KW - Radiogenomics
KW - Artificial Intelligence
KW - Cancer Imaging
KW - Chemiotherapy
KW - HGSOC
KW - Machine Learning Models
KW - Ovarian Cancer
KW - Predictive Markers
KW - RECIST
KW - Radiogenomics
UR - http://hdl.handle.net/10807/277356
U2 - 10.1038/s41467-023-41820-7
DO - 10.1038/s41467-023-41820-7
M3 - Article
SN - 2041-1723
VL - 14
SP - N/A-N/A
JO - Nature Communications
JF - Nature Communications
ER -