Abstract
ObjectiveTo construct and validate a radiomics nomogram for preoperative prediction of survival stratification in glioblastoma (GBM) patients with standard treatment according to radiomics features extracted from multiparameter magnetic resonance imaging (MRI), which could facilitate clinical decision-making.MethodsA total of 125 eligible GBM patients (53 in the short and 72 in the long survival group, separated by an overall survival of 12 months) were randomly divided into a training cohort (n = 87) and a validation cohort (n = 38). Radiomics features were extracted from the MRI of each patient. The T-test and the least absolute shrinkage and selection operator algorithm (LASSO) were used for feature selection. Next, three feature classifier models were established based on the selected features and evaluated by the area under curve (AUC). A radiomics score (Radscore) was then constructed by these features for each patient. Combined with clinical features, a radiomics nomogram was constructed with independent risk factors selected by the logistic regression model. The performance of the nomogram was assessed by AUC, calibration, discrimination, and clinical usefulness.ResultsThere were 5,216 radiomics features extracted from each patient, and 5,060 of them were stable features judged by the intraclass correlation coefficients (ICCs). 21 features were included in the construction of the radiomics score. Of three feature classifier models, support vector machines (SVM) had the best classification effect. The radiomics nomogram was constructed in the training cohort and exhibited promising calibration and discrimination with AUCs of 0.877 and 0.919 in the training and validation cohorts, respectively. The favorable decision curve analysis (DCA) indicated the clinical usefulness of the radiomics nomogram.ConclusionsThe presented radiomics nomogram, as a non-invasive tool, achieved satisfactory preoperative prediction of the individualized survival stratification of GBM patients.
Highlights
Glioblastoma (GBM) is the most frequent primary malignant tumor of the central nervous system with the characteristics of highly aggressive growth, high recurrence rate, and poor prognosis, defined as Grade IV glioma or glioblastoma multiforme according to the 2016 World Health Organization classification of brain tumors [1]
There were 5,216 radiomics features extracted from each patient, and 5,060 of them were stable features judged by the intraclass correlation coefficients (ICCs). 21 features were included in the construction of the radiomics score
The radiomics nomogram was constructed in the training cohort and exhibited promising calibration and discrimination with area under curve (AUC) of 0.877 and 0.919 in the training and validation cohorts, respectively
Summary
Glioblastoma (GBM) is the most frequent primary malignant tumor of the central nervous system with the characteristics of highly aggressive growth, high recurrence rate, and poor prognosis, defined as Grade IV glioma or glioblastoma multiforme according to the 2016 World Health Organization classification of brain tumors [1]. The current standard treatment includes maximal safe surgical resection followed by concomitant radiotherapy and adjuvant chemotherapy with temozolomide, maintenance with 6–12 months of temozolomide as single-agent therapy [2, 3]. The median overall survival (OS) of GBM patients remains 10–14 months [4, 5]. Magnetic resonance imaging (MRI), as a noninvasive and non-radioactive inspection method, has indicated great potential in predicting the prognosis of GBM patients based on providing a comprehensive macro-image of the whole tumor [9, 10]. As a potentially non-invasive high-throughput method of acquiring tumor characteristics, radiomics has been used in many tumors, including the pancreatic ductal adenocarcinomas, colorectal cancer, and pituitary adenomas [11–13]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
