¹⁸F-FDG-PET-Based Radiomics Features to Distinguish Primary Central Nervous System Lymphoma from Glioblastoma.

Background: The differential diagnosis of primary central nervous system (CNS) lymphoma from glioblastoma multiforme (GBM) is essential due to the difference in treatment strategies. This study aims to identify the distinguishable characteristics of primary CNS lymphoma and GBM in ¹⁸F-fluorodeocxyglucose (FDG) positron emission tomography (PET) images using a radiomics approach.

Methods: Seventy-seven patients (24 with lymphoma and 53 with GBM) were retrospectively reviewed, and regions of interest (ROIs) were manually segmented. Three groups of maps, namely, a standardized uptake value (SUV) map, an SUV map calibrated with the normal contralateral cortex (ncc) activity (SUV/ncc map), and an SUV map calibrated with the normal brain mean (nbm) activity (SUV/nbm map), were generated, and a total of 107 radiomics features, including shape, first order and texture features, were extracted from each SUV map. The area under the curve (AUC) of the receiver operating characteristic (ROC) curve of each feature was compared with the SUVmax to evaluate the distinguishability of the features, and the margins of the ROI were adjusted to assess the stability of the features. Tumors with solid metabolic patterns were also separately evaluated.

Results: Features extracted from the SUV map demonstrated higher AUCs than features from the further calibrated maps. Thirty-one radiomics features from the SUV map displayed better performance than SUVmax, and most of them remained stable after margin adjustment. Similar results have been revealed in solid metabolic tumors. Fifteen radiomics features that performed better than SUVmax in every circumstance were selected to distinguish lymphoma from glioblastoma, and they suggested that lymphoma has a higher SUV in most interval segments and is more mathematically heterogeneous than GBM.

Conclusions: ¹⁸F-FDG-PET-based radiomics provide a reliable noninvasive method to distinguish lymphoma and GBM.