Abstract
Brain tumor is not most common, but truculent type of cancer. Therefore, correct prediction of its aggressiveness nature at an early stage would influence the treatment strategy. Although several diagnostic methods based on different modalities exist, a pre-operative method for determining tumor malignancy state still remains as an active research area. In this regard, the paper presents a new method for the assessment of tumor grades using conventional MR sequences namely, T1, T1 with contrast enhancement, T2 and FLAIR. The proposed method for tumor gradation is mainly based on feature extraction using multiresolution image analysis and classification using support vector machine. Since the wavelet features of different tumor subregions, obtained from single MR sequence, do not carry equally important information, a wavelet fusion technique is proposed based on the texture information content of each voxel. The concept of texture gradient, used in the proposed algorithm, fuses the wavelet coefficients of the given MR sequences. The feature vector is then derived from the co-occurrence of fused wavelet coefficients. As each wavelet subband contains distinct detail information, a novel concept of multispectral co-occurrence of wavelet coefficients is introduced to capture the spatial correlation among different subbands. It enables to convey more informative features to characterize the tumor type. The effectiveness of the proposed method is analyzed, with respect to six classification performance indices, on BRATS 2012 and BRATS 2014 data sets. The classification accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and area under curve assessed by the ten-fold cross-validation are 91.3%, 96.8%, 66.7%, 92.4%, 88.4%, and 92.0%, respectively, on real brain MR data.
Highlights
Brain tumor is not very common, but it is among the most fatal cancers [1]
Analyzing the feature values reported in these tables, it is seen that the values of Haralick features are almost similar for both simulated images as well as for high grade and low grade brain tumor images at each wavelet subband when the co-occurrence matrix is computed within single subband
The performance of the proposed method is analyzed with respect to six quantitative indices namely, accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and area under the receiver operating characteristic (ROC) curve (AUC)
Summary
Brain tumor is not very common, but it is among the most fatal cancers [1]. It can be defined as an abnormal lump of tissues, which infiltrates surrounding brain tissues and interferes the normal brain activities. The wavelet based multiresolution analysis [6] is the most effective technique for extracting the textural features from brain MR images [7,8,9]. In [7], the wavelet analysis is performed on apparent diffusion coefficient images to predict the degree of malignancy of brain tumor. These include entropy, obtained from gray level co-occurrence matrices, and the skewness and kurtosis of the image histogram These texture and histogram features act as the parameters to discriminate between low and high grade gliomas using an unpaired student’s t-test. The proposed method introduces a fusion algorithm that combines the wavelet coefficients of the MR sequences, depending on the texture information content of different tumor subregions. In order to capture the spatial correlation among different wavelet subbands, a novel concept called
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
