We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Optimizing Texture Retrieving Model for Multimodal MR Image-Based Support Vector Machine for Classifying Glioma.
- Authors
Yang, Yang; Yan, Lin‐Feng; Zhang, Xin; Nan, Hai‐Yan; Hu, Yu‐Chuan; Han, Yu; Zhang, Jin; Liu, Zhi‐Cheng; Sun, Ying‐Zhi; Tian, Qiang; Yu, Ying; Sun, Qian; Wang, Si‐Yuan; Zhang, Xiao; Wang, Wen; Cui, Guang‐Bin; Yan, Lin-Feng; Nan, Hai-Yan; Hu, Yu-Chuan; Liu, Zhi-Cheng
- Abstract
<bold>Background: </bold>Accurate glioma grading plays an important role in patient treatment.<bold>Purpose: </bold>To investigate the influence of varied texture retrieving models on the efficacy of grading glioma with support vector machine (SVM).<bold>Study Type: </bold>Retrospective.<bold>Population: </bold>In all, 117 glioma patients including 25, 29, and 63 grade II, III, and IV gliomas, respectively, based on WHO 2007.<bold>Field Strength/sequence: </bold>3.0T 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.<bold>Assessment: </bold>Texture 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.<bold>Statistical Tests: </bold>Ten-fold crossvalidation was used to validate the model performance.<bold>Results: </bold>Based 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.<bold>Data Conclusion: </bold>When 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.<bold>Level Of Evidence: </bold>2 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;49:1263-1274.
- Publication
Journal of Magnetic Resonance Imaging, 2019, Vol 49, Issue 5, p1263
- ISSN
1053-1807
- Publication type
journal article
- DOI
10.1002/jmri.26524