Search

Recently computer aided diagnosis is largely used in many clinical processes to detect, predict and analyze many abnormalities. It is clear that in medical image processing, brain tumor classification and detection plays a significant task. MRI gives anatomical structure's information, and the potential abnormal tissues' information. Hence in this paper a new system is proposed for detection and classification of brain tumors. The proposed system consists of feature extraction and tumor classification. In feature extraction, Rough set theory (RST) is used and for classification task particle swam optimization neural network (PSONN) is trained and tested in order to classify the MRI brain images into normal and abnormal. [ABSTRACT FROM AUTHOR]

Nowadays, the medical images upsurge because of numerous major disease predictions. The medical image size needed vast volumes of memory and taking additional bandwidth for storage as well as transmission. With the aim of decreasing the size of the storage and as well for greater transmission image compression is needed. The prior research presented a completely automatic technique for skin lesion segmentation by leveraging 19-layer deep convolutional neural networks (CNNs), which is skilled end to-end and does not depend on past acquittance of the data. On the other hand it contains problem with storage for the period of the medical image transmission and transmission speed. With the aim of resolving this issue the presented system developed a compression method. In this research, magnetic resonance imaging are pre-processed by means of median filter. The preprocessed image is split into region of interest (ROI) and non region of interest by means of deep fully convolutional networks with Jaccard distance. Subsequent to the ROI segmentation, the ROI edge is taken out and encrypted with Freeman chain coding. At that point the ROI part is compressed by hybrid Lempel–Ziv–Welch and clipped histogram equalization (CHE). In CHE, ideal threshold value is chosen by means of particle swarm optimization technique for enhancing the brightness maintenance. The Non ROI part is compressed by means of enhanced zero tree wavelet (EZW). In this EZW technique, a preliminary threshold is chosen by making use of firefly algorithm. Lastly the decompression is carried out at the receiving end. The experimentation outcomes prove that the presented method attains greater performance when matched up with the previous technique in regard to compression ratio, peak signal to noise ratio and mean square error. [ABSTRACT FROM AUTHOR]

The paper focuses on how a brain image is being segmented to diagnose the brain tumor by using spatial fuzzy clustering algorithm. The segmentation process may cause error while diagonizing MR images due to the artifacts and noises exist in it. This may leads to misclassify the normal tissue as abnormal tissue. The proposed method is to segment normal tissues such as White Matter, Gray Matter, Cerebrospinal fluid and abnormal tissue like tumor part from MR images automatically. It comprises of pre-processing step, using wrapping based curvelet transform to remove noise and modified spatial fuzzy C-Means algorithm (Liu et al. in Tsinghua Sci Technol 19(6):578–595, 2014; Kwak and Choi in IEEE Trans Neural Netw 13(1):143–159, 2014) segments normal tissues by considering spatial information. The neighboring pixels are highly correlated and construct initial membership matrix randomly. The process is also intended to segment the tumor cells as well as the removal of background noises for smoothening the region, results in presenting segmented tissues and parameter evaluation to produce the algorithm efficiency. [ABSTRACT FROM AUTHOR]