Performance evaluation of active contours based methods for the detection of brain tumours in MR images
G. Sandhya, Giri Babu Kande, Tirumala Satya Savithri · International Journal of Biomedical Engineering and Technology · 2015
Image segmentation is a process to extract suspicious region from complex medical images. Automatic detection of brain tumour through MRI can provide the valuable outlook and accuracy. Early detection and diagnosis increases the chances of survival. Therefore, in order to accurately segment out and measure the size of tumour from MRI, well-established methods are active contour models, which have been widely used in image segmentation with promising results. These can achieve sub-pixel accuracy and provide closed and smooth contours/surfaces. Active contours are curves defined within an image domain that can move under the influence of internal forces within the curve itself and external forces derived from the image data. These forces are defined so that the contour will conform to an object boundary or other desired features within an image. This paper presents performance of various active contours based methods for the detection of tumours in MR images.