Classification of patients with tumor using MR FLAIR images

• Published in: Pattern recognition letters Vol. 139; pp. 112 - 117
• Main Authors: Gupta, Tanvi, Gandhi, Tapan K., Gupta, R.K., Panigrahi, B.K.
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01.11.2020; Elsevier Science Ltd
• Subjects: Algorithms; Classification; Discrete Wavelet Transform; Feature extraction; FLAIR; Image acquisition; Image classification; Learning algorithms; Machine learning; Magnetic resonance imaging; Medical imaging; MRI; Principal components analysis; Regression analysis; Sensitivity; Support vector machines; SVM; Tumor; Tumors; Wavelet transforms; FLAIR; Tumor; SVM; MRI
• ISSN: 0167-8655; 1872-7344
• DOI: 10.1016/j.patrec.2017.10.037

•Classify pathology (cerebral tumors) and physiology using magnetic resonance FLAIR image.•DWT is used for feature extraction, using the entire patient slices as one feature set for each patient.•Different classifiers are tested with and without PCA to get highest accuracy in least computation time.•SVM is chosen for classification without the use of PCA with 88% accuracy in 62.28 s. Magnetic Resonance Imaging (MRI) is a fast growing imaging tool for neurodiagnosis. The radiologists time is at a premium due to increase in patient studies each having a large data set. This can be aided by classification using machine learning techniques. This paper evaluates its utility for accurate and rapid diagnosis of cerebral tumors. Two hundred subjects were classified into normal and abnormal using volumetric Fluid Attenuated Inversion Recovery (FLAIR) acquisition. The images are normalized to obtain 12 useful slices to be considered as the patient feature set for classification. Discrete Wavelet Transform (DWT) is used for feature extraction and Principal Component Analysis (PCA) is used for feature selection. Various classifiers like Support Vector Machine (SVM), k-Nearest Neighbor (k-NN), CART (Classification and Regression Tree) and Random forest are tested. Applying K-fold cross validation in each train-test ratios, we obtained ceiling level classification accuracy with coherent sensitivity and specificity using only linear SVM (negating the use of PCA). An accuracy of 88% is obtained with a sensitivity of 84% and specificity of 92% with 62.28 s computation time. The algorithm is robust to be tested in clinical settings.