A Radiomic-Based Machine Learning Model Predicts Endometrial Cancer Recurrence Using Preoperative CT Radiomic Features: A Pilot Study.
Camelia Alexandra Coada, Miriam Santoro, Vladislav Zybin, Marco Di Stanislao, Giulia Paolani, Cecilia Modolon, Stella Di Costanzo, Lucia Genovesi, Marco Tesei, Antonio De Leo, Gloria Ravegnini, Dario De Biase, Alessio Giuseppe Morganti, Luigi Lovato, Pierandrea De Iaco, Lidia Strigari, Anna Myriam Perrone
Author Information
Camelia Alexandra Coada: Department of Medical and Surgical Sciences, University of Bologna, 40126 Bologna, Italy. ORCID
Miriam Santoro: Department of Medical Physics, IRCCS Azienda Ospedaliero-Universitaria di Bologna, 40138 Bologna, Italy. ORCID
Vladislav Zybin: Pediatric and Adult CardioThoracic and Vascular, Oncohematologic and Emergency Radiology Unit, IRCCS Azienda Ospedaliero-Universitaria di Bologna, 40138 Bologna, Italy.
Marco Di Stanislao: Department of Medical and Surgical Sciences, University of Bologna, 40126 Bologna, Italy.
Giulia Paolani: Department of Medical Physics, IRCCS Azienda Ospedaliero-Universitaria di Bologna, 40138 Bologna, Italy.
Cecilia Modolon: Pediatric and Adult CardioThoracic and Vascular, Oncohematologic and Emergency Radiology Unit, IRCCS Azienda Ospedaliero-Universitaria di Bologna, 40138 Bologna, Italy.
Stella Di Costanzo: Division of Oncologic Gynecology, IRCCS Azienda Ospedaliero-Universitaria di Bologna, 40138 Bologna, Italy.
Lucia Genovesi: Department of Medical and Surgical Sciences, University of Bologna, 40126 Bologna, Italy.
Marco Tesei: Division of Oncologic Gynecology, IRCCS Azienda Ospedaliero-Universitaria di Bologna, 40138 Bologna, Italy. ORCID
Antonio De Leo: Department of Medical and Surgical Sciences, University of Bologna, 40126 Bologna, Italy. ORCID
Gloria Ravegnini: Department of Pharmacy and Biotechnology, University of Bologna, 40126 Bologna, Italy. ORCID
Dario De Biase: Solid Tumor Molecular Pathology Laboratory, IRCCS Azienda Ospedaliero-Universitaria di Bologna, 40138 Bologna, Italy. ORCID
Alessio Giuseppe Morganti: Radiation Oncology, IRCCS Azienda Ospedaliero-Universitaria di Bologna, 40138 Bologna, Italy.
Luigi Lovato: Pediatric and Adult CardioThoracic and Vascular, Oncohematologic and Emergency Radiology Unit, IRCCS Azienda Ospedaliero-Universitaria di Bologna, 40138 Bologna, Italy. ORCID
Pierandrea De Iaco: Department of Medical and Surgical Sciences, University of Bologna, 40126 Bologna, Italy.
Lidia Strigari: Department of Medical Physics, IRCCS Azienda Ospedaliero-Universitaria di Bologna, 40138 Bologna, Italy. ORCID
Anna Myriam Perrone: Department of Medical and Surgical Sciences, University of Bologna, 40126 Bologna, Italy. ORCID
BACKGROUND: Current prognostic models lack the use of pre-operative CT images to predict recurrence in endometrial cancer (EC) patients. Our study aimed to investigate the potential of radiomic features extracted from pre-surgical CT scans to accurately predict disease-free survival (DFS) among EC patients. METHODS: Contrast-Enhanced CT (CE-CT) scans from 81 EC cases were used to extract the radiomic features from semi-automatically contoured volumes of interest. We employed a 10-fold cross-validation approach with a 6:4 training to test set and utilized data augmentation and balancing techniques. Univariate analysis was applied for feature reduction leading to the development of three distinct machine learning (ML) models for the prediction of DFS: LASSO-Cox, CoxBoost and Random Forest (RFsrc). RESULTS: In the training set, the ML models demonstrated AUCs ranging from 0.92 to 0.93, sensitivities from 0.96 to 1.00 and specificities from 0.77 to 0.89. In the test set, AUCs ranged from 0.86 to 0.90, sensitivities from 0.89 to 1.00 and specificities from 0.73 to 0.90. Patients classified as having a high recurrence risk prediction by ML models exhibited significantly worse DSF (-value < 0.001) across all models. CONCLUSIONS: Our findings demonstrate the potential of radiomics in predicting EC recurrence. While further validation studies are needed, our results underscore the promising role of radiomics in forecasting EC outcomes.
