• Yang Yang, Lin-Feng Yan, Xin Zhang, Hai-Yan Nan, Yu-Chuan Hu, Yu Han, Jin Zhang, Zhi-Cheng Liu, Ying-Zhi Sun, Qiang Tian, Ying Yu, Qian Sun, Si-Yuan Wang, Xiao Zhang, Wen Wang, and Guang-Bin Cui.
• Functional and Molecular Imaging Key Lab of Shaanxi Province, Department of Radiology, Tangdu Hospital, Air Force Medical University (Fourth Military Medical University), Xi'an, Shaanxi, China.
• J Magn Reson Imaging. 2019 May 1; 49 (5): 1263-1274.

BackgroundAccurate glioma grading plays an important role in patient treatment.PurposeTo investigate the influence of varied texture retrieving models on the efficacy of grading glioma with support vector machine (SVM).Study TypeRetrospective.PopulationIn all, 117 glioma patients including 25, 29, and 63 grade II, III, and IV gliomas, respectively, based on WHO 2007.Field Strength/Sequence3.0T MRI/ T1 WI, T2 fluid-attenuated inversion recovery, contrast enhanced T1 , arterial spinal labeling, diffusion-weighted imaging (0, 30, 50, 100, 200, 300, 500, 800, 1000, 1500, 2000, 3000, and 3500 sec/mm2 ), and dynamic contrast-enhanced.AssessmentTexture attributes from 30 parametric maps were retrieved using four models, including Global, gray-level co-occurrence matrix (GLCM), gray-level run-length matrix (GLRLM), and gray-level size-zone matrix (GLSZM). Attributes derived from varied models were input into radial basis function SVM (RBF-SVM) combined with attribute selection using SVM-recursive feature elimination (SVM-RFE). The SVM model was trained and established with 80% randomly selected data of each category using 10-fold crossvalidation. The model performance was further tested using the remaining 20% data.Statistical TestsTen-fold crossvalidation was used to validate the model performance.ResultsBased on 30 parametric maps, 90, 240, 390, or 390 texture attributes were retrieved using the Global, GLCM, GLRLM, or GLSZM model, respectively. SVM-RFE was able to reduce attribute redundancy as well as improve RBF-SVM performance. Training data were oversampled by applying the Synthetic Minority Oversampling Technique (SMOTE) method to overcome the data imbalance problem; test results were able to further demonstrate the classifying performance of the final models. GLSZM using gray-level 64 was the optimal model to retrieve powerful image texture attributes to produce enough classifying power with an accuracy / area under the curve of 0.760/0.867 for the training and 0.875/0.971 for the independent test. Fifteen attributes were selected with SVM-RFE to provide comparable classifying efficacy.Data ConclusionWhen using image textures-based SVM classification of gliomas, the GLSZM model in combination with gray-level 64 and attribute selection may be an optimized solution.Level Of Evidence2 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;49:1263-1274.© 2018 International Society for Magnetic Resonance in Medicine.

22 keywords...

hide…