An efficient brain mass detection with adaptive clustered based fuzzy C-mean and thresholding

Image segmentation plays an important role in analyzing medical images. Brain tumor detection is one of the applications that require brain image segmentation. Due to the complex nature of brain magnetic resonance images (MRI), the accurate computer aided detection (CAD) system for brain tumor segmentation has a lot of advantages over manual segmentation as it requires a lot of time and its results may vary from expert to expert. In this paper, a novel automatic tumor detection technique is proposed using Fuzzy C-means(FCM) where the number of clusters is determined automatically and conformed threshold is used instead of global threshold. Also a preprocessing stage is added to enhance the detection accuracy. The performance of the proposed method is evaluated by calculating completeness, correctness and accuracy of brain magnetic resonance (MR) tumor images. The proposed technique gives promising results for completeness, correctness, accuracy and processing time. Also, a comparison between the proposed technique results and the global threshold technique results is given.