Dataset Information

Differentiation Between Glioblastoma Multiforme and Metastasis From the Lungs and Other Sites Using Combined Clinical/Routine MRI Radiomics

ABSTRACT:

Background

Differentiation between cerebral glioblastoma multiforme (GBM) and solitary brain metastasis (MET) is important. The existing radiomic differentiation method ignores the clinical and routine magnetic resonance imaging (MRI) features.

Purpose

To differentiate between GBM and MET and between METs from the lungs (MET-lung) and other sites (MET-other) through clinical and routine MRI, and radiomics analyses.

Methods and Materials

A total of 350 patients were collected from two institutions, including 182 patients with GBM and 168 patients with MET, which were all proven by pathology. The ROI of the tumor was obtained on axial postcontrast MRI which was performed before operation. Seven radiomic feature selection methods and four classification algorithms constituted 28 classifiers in two classification strategies, with the best classifier serving as the final radiomics model. The clinical and combination models were constructed using the nomograms developed. The performance of the nomograms was evaluated in terms of calibration, discrimination, and clinical usefulness. Student’s t-test or the chi-square test was used to assess the differences in the clinical and radiological characteristics between the training and internal validation cohorts. Receiver operating characteristic curve analysis was performed to assess the performance of developed models with the area under the curve (AUC).

Results

The classifier fisher_decision tree (fisher_DT) showed the best performance (AUC: 0.696, 95% CI:0.608-0.783) for distinguishing between GBM and MET in internal validation cohorts; the classifier reliefF_random forest (reliefF_RF) showed the best performance (AUC: 0.759, 95% CI: 0.613-0.904) for distinguishing between MET-lung and MET-other in internal validation cohorts. The combination models incorporating the radiomics signature and clinical-radiological characteristics were superior to the clinical-radiological models in the two classification strategies (AUC: 0.764 for differentiation between GBM in internal validation cohorts and MET and 0.759 or differentiation between MET-lung and MET-other in internal validation cohorts). The nomograms showed satisfactory performance and calibration and were considered clinically useful, as revealed in the decision curve analysis.

Data Conclusion

The combination of radiomic and non-radiomic features is helpful for the differentiation among GBM, MET-lung, and MET-other.

SUBMITTER: Han Y

PROVIDER: S-EPMC8427511 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:PurposeTo build a framework for investigation of the associations between imaging, clinical target volumes (CTVs), and metabolic tumor volumes (MTVs) features for better understanding of the underlying information in the CTVs and dependencies between these volumes. High-throughput extraction of imaging and metabolomic quantitative features from magnetic resonance imaging (MRI) and magnetic resonance spectroscopic imaging of glioblastoma multiforme (GBM) results in tens of variables per patient. In radiation therapy of GBM the relevant metabolic tumor volumes (MTVs) are related to aberrant levels of N-acetyl aspartate (NAA) and choline (Cho). The corresponding clinical target volumes (CTVs) for radiation therapy are based on contrast-enhanced T1-weighted (CE-T1w) and T2-weighted (T2w)/fluid-attenuated inversion recovery MRI.Methods and materialsNecrotic portions, enhancing lesion, and edema were manually contoured on CE-T1w/T2w images for 17 GBM patients. Clinical target volumes and MTVs for NAA (MTVNAA) and Cho (MTVCho) were constructed. Imaging and metabolic features related to size, shape, and signal intensities of the volumes were extracted. Tumors were also scored categorically for 10 semantic imaging traits by a neuroradiologist. All features were investigated for redundancy. Two-way correlations between imaging and CTVs/MTVs features were visualized as heatmaps. Associations between MTVNAA and MTVCho and imaging features were studied using Spearman correlation.ResultsForty-eight imaging features were extracted per patient. Half of the imaging traits were replaced with automatically extracted continuous variables. Twenty features were extracted from CTVs and MTVs. A series of semantic imaging traits were replaced with automatically extracted continuous variables. There were multiple (22) significant correlations of imaging measures with CTVs/MTVNAA, whereas there were only 6 with CTVs/MTVCho.ConclusionsA framework for investigation of codependencies between MRI and magnetic resonance spectroscopic imaging radiomic features and CTVs/MTVs has been established. The MTV for NAA was found to be closely associated with MRI volumes, whereas very few imaging features were related to MTVCho, indicating that Cho provides additional information to imaging.