Brain Tumor Classification And Diagnosis Using Multilayer Symmetry Technique In Image Processing

Accurate and timely detection of the brain tumor area has a very high impact on choosing the type of treatment, its success rate and following the course of the disease during the treatment. Existing algorithms for brain tumor diagnosis face problems in terms of good performance on various brain images with different qualities, low sensitivity of the results to the parameters introduced in the algorithm, and reliable diagnosis of tumors in the early stages of formation. For this purpose, digital image processing methods along with machine learning help to diagnose the tumor as quickly as possible, as well as treatment and type of surgery. These combined techniques in understanding medical images are an important tool for researchers to increase the accuracy of diagnosis. In this thesis, we intend to perform the classification methods related to the MRI images of the human brain with a tumor, with the aim of reviewing the glands containing astrocytoma. The methods used for brain tumor classification include pre-processing steps, windowing, and extraction of histological and statistical features of the tumor using two types of T1-w and Flair brain MRI images, as well as the method of reducing the dimensions of the extracted features and how to train them for classification. The results have shown that by using the combined technique of symmetry and multi-layer clustering, while increasing the accuracy, the processing time is also reduced.

Brain Tumor Classification And Diagnosis Using Multilayer Symmetry Technique In Image Processing Keywords:

Brain tumor , MRI , Classification , Diagnosis , Image processing