An approach to examine Magnetic Resonance Angiography based on Tsallis entropy and deformable snake model

This paper proposes a hybrid approach with the integration of a pre-processing and a post-processing technique to examine Magnetic Resonance Angiography (MRA) images. In pre-processing stage, a tri-level thresholding is implemented on the 2D MRA test image using the Chaotic Firefly Algorithm (CFA) and Tsallis entropy in order to improve the contrast enhanced regions by grouping the similar pixel levels. During post-processing stage, contrast enhanced regions of test image is extracted using the Active Contour (AC) procedure known as the deformable snake. Finally, the texture property of extracted aneurysm region is then computed using Minkowski distance function. The advantage of AC is validated using other segmentation procedures, such as watershed algorithm, level set, and Markov random field procedure existing in the literature. Further, the effectiveness of the proposed technique is validated using the TIC, Flair and T2 modality brain images existing in the BraTS MRI dataset. The experimental study established that the proposed two stage approach extracted efficiently the contrast enhanced regions from the MRA and T1C brain images. The segmentation result on - T1C confirmed that the proposed methodology achieved superior values of 89.65%, 93.05%, 98.16%, 98.36%, 98.17% and 90.88% for the Jaccard, dice, sensitivity, specificity, accuracy and precision respectively.