An improved watershed segmentation technique for microbleeds detection in MRI images

The magnetic resonance imaging (MRI) is very effective, yet non-invasive medical imaging technique for clinical diagnosis and for monitoring the abnormalities in neurological order. Currently, the analysis of microbleeds is performed by experienced neurologist based on their knowledge that is by scanning the image, detecting the black dots and identifying whether black dots are micro-bleeds or mimics. Medical image processing has made a great impact on medicine, diagnosis, and treatment. The most important part of image processing in medical is image segmentation. Watershed segmentation is an example of a robust technique for image segmentation. The common watershed transformation used for segmentation is the marker controlled segmentation. This conventional watershed algorithms for medical images is widespread because of its advantage to completely segment the medical images. However, the common drawback of watershed segmentation which is over-segmentation and its sensitivity to false edges segmentation. This paper introduces a new scheme of process to overcome the listed drawback by first applying clustering technique to produce the primary segmentation before applying the improved watershed algorithm. The uses of k-means algorithms which is unsupervised learning algorithms will help watershed segmentation to improve segmentation process. Then, the improved watershed segmentation used the level set thresholding based on gradient magnitude map to reduce the number of false edges and over segmentations. This proposed method demonstrates a significant improvement that may serves as a computer aided tools for radiologists in detecting microbleeds in MRI images.