Angela Di Giannatale1, Pier Luigi Di Paolo2, Davide Curione2, Jacopo Lenkowicz3, Antonio Napolitano4, Aurelio Secinaro2, Paolo Tomà2, Franco Locatelli1,5, Aurora Castellano1, Luca Boldrini3. 1. Department of Pediatric Hematology/Oncology and Cell and Gene Therapy, IRCCS Ospedale Pediatrico Bambino Gesù, Rome, Italy. 2. Department of Imaging, IRCCS Ospedale Pediatrico Bambino Gesù, Rome, Italy. 3. UOC Radioterapia Oncologica, Dipartimento di Diagnostica per Immagini, Radioterapia Oncologica ed Ematologia, Fondazione Policlinico Universitario "A. Gemelli" IRCCS, Rome, Italy. 4. Medical Physics Department, IRCCS Ospedale Pediatrico Bambino Gesù, Rome, Italy. 5. Department of Gynecology/Obstetrics and Pediatrics, Sapienza University of Rome, Rome, Italy.
Abstract
BACKGROUND: MYCN amplification represents a powerful prognostic factor in neuroblastoma (NB) and may occasionally account for intratumoral heterogeneity. Radiomics is an emerging field of advanced image analysis that aims to extract a large number of quantitative features from standard radiological images, providing valuable clinical information. PROCEDURE: In this retrospective study, we aimed to create a radiogenomics model by correlating computed tomography (CT) radiomics analysis with MYCN status. NB lesions were segmented on pretherapy CT scans and radiomics features subsequently extracted using a dedicated library. Dimensionality reduction/features selection approaches were then used for features procession and logistic regression models have been developed for the considered outcome. RESULTS: Seventy-eight patients were included in this study, as training dataset, of which 24 presented MYCN amplification. In total, 232 radiomics features were extracted. Eight features were selected through Boruta algorithm and two features were lastly chosen through Pearson correlation analysis: mean of voxel intensity histogram (p = .0082) and zone size non-uniformity (p = .038). Five-times repeated three-fold cross-validation logistic regression models yielded an area under the curve (AUC) value of 0.879 on the training set. The model was then applied to an independent validation cohort of 21 patients, of which five presented MYCN amplification. The validation of the model yielded a 0.813 AUC value, with 0.85 accuracy on previously unseen data. CONCLUSIONS: CT-based radiomics is able to predict MYCN amplification status in NB, paving the way to the in-depth analysis of imaging based biomarkers that could enhance outcomes prediction.
BACKGROUND: MYCN amplification represents a powerful prognostic factor in neuroblastoma (NB) and may occasionally account for intratumoral heterogeneity. Radiomics is an emerging field of advanced image analysis that aims to extract a large number of quantitative features from standard radiological images, providing valuable clinical information. PROCEDURE: In this retrospective study, we aimed to create a radiogenomics model by correlating computed tomography (CT) radiomics analysis with MYCN status. NB lesions were segmented on pretherapy CT scans and radiomics features subsequently extracted using a dedicated library. Dimensionality reduction/features selection approaches were then used for features procession and logistic regression models have been developed for the considered outcome. RESULTS: Seventy-eight patients were included in this study, as training dataset, of which 24 presented MYCN amplification. In total, 232 radiomics features were extracted. Eight features were selected through Boruta algorithm and two features were lastly chosen through Pearson correlation analysis: mean of voxel intensity histogram (p = .0082) and zone size non-uniformity (p = .038). Five-times repeated three-fold cross-validation logistic regression models yielded an area under the curve (AUC) value of 0.879 on the training set. The model was then applied to an independent validation cohort of 21 patients, of which five presented MYCN amplification. The validation of the model yielded a 0.813 AUC value, with 0.85 accuracy on previously unseen data. CONCLUSIONS: CT-based radiomics is able to predict MYCN amplification status in NB, paving the way to the in-depth analysis of imaging based biomarkers that could enhance outcomes prediction.