cellular neural network based medical image segmentation using artificial bee colony algorithm

Magnetic Resonance Imaging (MRI) has become an efficient instrument for clinical diagnoses and research in recent years. It has become a very useful medical modality for the detection of various diseases through segmentation methods. In this paper, we have presented an effective CNN based segmentation method with lung and brain MRI images. This approach hits the target with the aid of the following major steps, which includes, 1) Preprocessing of the brain and lung images, 2) Segmentation using cellular neural network. Initially, the MRI image is pre-processed to make it fit for segmentation. Here, in the pre-processing step, image de-noising is done using the linear smoothing filters, such as Gaussian Filter. Then, the pre-processed image is segmented according to our proposed technique, CNN-based image segmentation. Finally, the different MRI images (brain and lung) are given to the proposed approach to evaluate the performance of the proposed approach in segmentation process. The Comparative analysis is carried out Fuzzy C-means (FCM) and K-means classification. From the comparative analysis, the accuracy of proposed segmentation approach produces better results (83.7% for lung and 93% for brain images) than that of existing Fuzzy C-means (FCM) and K-means classification.