ABSTRACT
Glioma is the most common malignant brain tumor and classification of low grade glioma (LGG) and high grade glioma (HGG) is an important reference of making decisions on patient treatment options and prognosis. This work is largely done manually by pathologist based on an examination of whole slide image (WSI), which is arduous and heavily dependent on doctors' experience. In the World Health Organization (WHO) criteria, grade of glioma is closely related to hypercellularity, nuclear atypia and necrosis. Inspired by this, this paper designed and extracted cell density and atypia features to classify LGG and HGG. First, regions of interest (ROI) were located by analyzing cell density and global density features were extracted as well. Second, local density and atypia features were extracted in ROI. Third, balanced support vector machine (SVM) classifier was trained and tested using 10 selected features. The area under the curve (AUC) and accuracy (ACC) of 5-fold cross validation were 0.92 ± 0.01 and 0.82 ± 0.01 respectively. The results demonstrate that the proposed method of locating ROI is effective and the designed features of density and atypia can be used to predict glioma grade accurately, which can provide reliable basis for clinical diagnosis.
Subject(s)
Humans , Brain Neoplasms/diagnostic imaging , Glioma/diagnostic imaging , Magnetic Resonance Imaging , Neoplasm Grading , Support Vector MachineABSTRACT
Objective To investigate the diagnostic value of susceptibility weighted imaging (SWI)semiquantitative assessment of pathological vascularity in grading cerebral gliomas.Methods Images of thirty-six patients with gliomas(1 5 low-grade and 21 high-grade gliomas)were obtained before therapy.Standard clinical MR imaging and SWI were performed at GE 3.0T scanner.All SWI postprocessed images were reviewed independently by two neuroradiologists and the number of vessels in tumor region were scored. Tumor were graded according to the World Health Organization classification.Results In 1 5 cases of low-grade glioma,semiquanti-tative assessment of pathological vascularity scored 0 in 6 cases,1 in 9 cases.In 21 cases of high-grade gliomas,semiquantitative as-sessment of pathological vascularity scored 2 in 18 cases,3 in 2 cases,1 in 1 case.There was a statistical significance between low-grade and high-grade gliomas(Z =-5.327,P <0.05).The grade of intratumoral pathological vascularity detected on SWI was asso-ciated with tumor grade.Conclusion It is usefull that SWI semiquantitative assessment of pathlogical vascularity in grading cerebral gliomas between low-grade and high-grade.