Differentiation of Glioblastoma and Lymphoma Using Feature Extraction and Support Vector Machine

Abstract

Differentiation of glioblastoma multiformes (GBMs) and lymphomas using multi-sequence magnetic resonance imaging (MRI) is an important task that is valuable for treatment planning. However, this task is a challenge because GBMs and lymphomas may have a similar appearance in MRI images. This similarity may lead to misclassification and could affect the treatment results. In this paper, we propose a semi-automatic method based on multi-sequence MRI to differentiate these two types of brain tumors. Our method consists of three steps: 1) the key slice is selected from 3D MRIs and region of interests (ROIs) are drawn around the tumor region; 2) different features are extracted based on prior clinical knowledge and validated using a t-test; and 3) features that are helpful for classification are used to build an original feature vector and a support vector machine is applied to perform classification. In total, 58 GBM cases and 37 lymphoma cases are used to validate our method. A leave-one-out crossvalidation strategy is adopted in our experiments. The global accuracy of our method was determined as 96.84%, which indicates that our method is effective for the differentiation of GBM and lymphoma and can be applied in clinical diagnosis.

Glioblastoma and primary central nervous system lymphoma: differentiation using MRI derived first-order texture analysis – a machine learning study

“…Our results were also comparable to other prior studies that also evaluated the utility of texture analysis to differentiate glioblastoma from PCNSL (Supplemental Table 2). 2,20,[22][23][24][25][26][27][28][29][30][31] The higher performance of Kim et al 23 (AUC 0.956) and Nakagawa et al 25 (AUC 0.980) may be secondary to texture feature extraction from multiparametric images including three-dimensional (3D) T1 CE sequence, T2-weighted and diffusion-weighted images. In contrast, we performed texture analysis on a routinely acquired 2D T1 CE sequence which is performed universally.…”

“…Our results were also comparable to other prior studies that also evaluated the utility of texture analysis to differentiate glioblastoma from PCNSL (Supplemental Table 2). 2,20,22–31…”

Beyond Glioma: The Utility of Radiomic Analysis for Non-Glial Intracranial Tumors

“…The feature selection and model-building methods vary significantly among studies (see Table S1), and in some cases, the models include clinical or semantic variables. MRI sequences used for tumor differentiation vary as well and have, for example, CE T1 sequences only [46,52,54] as well as combinations of ADC and T1CE [55]; ADC, FLAIR, and CE T1 [47]; DWI, CE T1, and FLAIR [48]; CE T1, T2 and DWI [50]; T1, T2, and FLAIR [51,56]; or ADC and gradientecho [15]. A study involving 141 patients reported over 90% accuracy in differentiation between various tumor entities, including GBM, lymphoma, BM, and meningioma, using five MRI sequences in total [15].…”

“…The authors could identify two features that enabled the discrimination between these two entities with a very high accuracy. Alternatively to the conventional approach of tumor volumetry, a representative axial slice can be used to draw a region of interest and differentiate between GBM and lymphoma with high accuracy [56]. Despite the considerable heterogeneity of these approaches, it seems that radiomics is a promising tool for the differentiation of lymphoma and GBM, as evidenced by a satisfactory AUC in some of these models.…”

Machine learning applications for the differentiation of primary central nervous system lymphoma from glioblastoma on imaging: a systematic review and meta-analysis

“…1). 1,5,12,19,33,[36][37][38] Overall, 6 (75%) of the studies exclusively compared GBM to PCNSL, and 2 of the studies included other tumors as well ( Table 2). All studies only investigated de novo tumors that were imaged using T1-/T2-weighted MRI, FLAIR, and/or diffusion-weighted MRI prior to steroid administration, biopsy, or any other treatment.…”