Automatic defects detection in MR images is very important in many diagnostic and therapeutic applications. Because of the high quantity of data in MR images and blurred boundaries, tumor segmentation and classification is very hard. This work has introduced one automatic brain tumor detection method to increase the accuracy and yield and decrease the diagnosis time. The goal is to classify the tissues into three classes normal, begin, and malignant. . In MR images, the amount of data is too much for manual interpretation and analysis. During the past few years, brain tumor segmentation in magnetic resonance imaging (MRI) has become an emergent research area in the field of the medical imaging system. Accurate detection of the size and location of brain tumor plays a vital role in the diagnosis of tumors. The diagnosis method consists of four stages, pre-processing of MR images, feature extraction, and classification. After histogram equalization of the image, the features are extracted based on Dual-Tree Complex wavelet transformation (DTCWT). In the last stage, Convolutional neural networks (CNN) are employed to classify the Normal and abnormal brain. An efficient algorithm is proposed for tumor detection based on the Spatial Fuzzy C-Means Clustering.
Brain tumor incidence is a significant contributing factor to the global death rate. According to the Cure Brain Cancer Foundation, brain tumors kill more people under 40 in Australia than any other cancer. In addition, its survival rates are low and have not changed significantly in 30 years, despite the remarkable increase in the survival rate of other types of cancer in Australia.
- Partial derivatives
- Wavelet-based denoising
- Thresholding and K mean clustering methods for segmentation
- Loss of edge details
- In wavelet denoising, failure to detect edge details at curved region.
- K means – It is not suitable for all lighting conditions of images
- Difficult to measure the cluster quality
 Ardizzone. E, Pirrone. R, and Orazio. O.G, “Fuzzy C-Means Segmentation on Brain MR Slices Corrupted by RF-Inhomogeneity,” In Proc. The 7th international workshop on Fuzzy Logic and Applications: Applications of Fuzzy Sets Theory, WILF ’07, Springer- Verlag, pp: 378-384, 2007.
 Binary. P.M, Ashtiyani.M, and Asadi.S, “MRI Segmentation Using Fuzzy C-means Clustering Algorithm Basis Neural Network,” In Proc. ICTT A 3rdInternationai Conference on Information and Communication Technologies: From Theory to Applications, pp: 1-5, 2008.
 Sikka. K, Sinha. N, Singh. P.K, and “A fully automated algorithm under modified FCM framework for improved brain MR image segmentation,” Magn. Reson. Imag, vol. 27, pp. 994–1004, Jul. 2009.
 Xiao. K, Ho. S.H, and Bargiela. B, “Automatic Brain MRI Segmentation Scheme Based on Feature Weighting Factors Selection on Fuzzy C means Clustering Algorithms with Gaussian