Classification of brain tumor type and grade using MRI texture and shape in a machine learning scheme

Abstract

The objective of this study is to investigate the use of pattern classification methods for distinguishing different types of brain tumors, such as primary gliomas from metastases, and also for grading of gliomas. The availability of an automated computer analysis tool that is more objective than human readers can potentially lead to more reliable and reproducible brain tumor diagnostic procedures. A computer-assisted classification method combining conventional MRI and perfusion MRI is developed and used for differential diagnosis. The proposed scheme consists of several steps including region-of-interest definition, feature extraction, feature selection, and classification. The extracted features include tumor shape and intensity characteristics, as well as rotation invariant texture features. Feature subset selection is performed using support vector machines with recursive feature elimination. The method was applied on a population of 102 brain tumors histologically diagnosed as metastasis (24), meningiomas (4), gliomas World Health Organization grade II (22), gliomas World Health Organization grade III (18), and glioblastomas (34). The binary support vector machine classification accuracy, sensitivity, and specificity, assessed by leave-one-out cross-validation, were, respectively, 85%, 87%, and 79% for discrimination of metastases from gliomas and 88%, 85%, and 96% for discrimination of high-grade (grades III and IV) from low-grade (grade II) neoplasms. Multiclass classification was also performed via a one-vs-all voting scheme.

Fig. 1

Examples of filters used to extract texture features. The 1^st row shows Gabor filters for same frequency and different orientations and the 2^nd row the rotation-invariant filters.

Fig. 2

MR images of different of brain tumor types and an example of texture images extracted from the edematous area. From left to right: meningioma, glioma grade II, grade III, grade IV and metastasis. 1^st row: T1ce image with the tumoral region of interest. 2^nd row: FLAIR image (zoomed in the tumor region) overlaid with one of the textural patterns (λ = 8). This pattern is shown here as voxel-wise texture for illustration purposes and is not equivalent to our calculations. The average texture values (calculated before FFT) (feature ${\mathit{\text{g}}}_4^5$) proved to be significant in discrimination of meningiomas.

Fig. 3

Classification accuracy (with SVM-RFE) versus number of retained features for classification of metastasis versus gliomas grade II, III, or IV (1^st row) and glioma grading (2^nd row).

Fig. 4

Classification accuracy (with SVM-RFE) versus number of retained features (1^st row) and ROC analysis (2^nd row) for two main classification problems: metastases versus primary gliomas (grade II, III, IV) shown in the 1^st column and low versus high grade gliomas (grade II versus III and IV) shown in the 2^nd column.