A Review on an Efficient Technique for Detection and Classification of Early Stage Tumor

Sangeeta, H. Nagendra

K-means; DWT; GLCM; PCA; KSVM; MRI Classification.

To reduce the death by tumor disease it is important for the classification and identification of the early stage tumor for diagnosis. The brain tumor is categorized into two types those are primary and secondary brain tumor. Again, primary brain tumor is categorized into two types those are malignant and benign tumor. Benign tumor is non-cancerous it does not affect other parts but malignant brain tumors are cancerous they may spread into spine of our body. This paper reviews various techniques utilized to classify the brain tumors with the help of MR images. Brain tumor classification can be divided into four phases as preprocessing, segmentation, feature reduction and extraction, classification. As segmentation is important step to classify the brain tumors. Median filter is efficient to eliminate the noise. Combination of K means cluster and otsu binarization is enough for segmentation. DWT (Discrete wavelet transform) and GLCM (Grey Level co-occurrence matrix) efficient for transform and spatial feature extraction. PCA (Principal component analysis) reduces the feature vector to maintain the classification accuracy of brain MRI images. For the performance of MRIs classification, the significant features have been submitted to KSVM (kernel support vector machine). The proposed system will reduce processing time and better accuracy can be achieved. The proposed method is validated on BRATS 2015 dataset.

https://doi.org/10.31871/IJNTR.6.10.5