Brain Tumor Area Segmentation of MRI Images

Abstract

Accurate and timely detection of the brain tumor area has a great impact on the choice of treatment, its success rate, and following the disease process during treatment. The existing algorithms for brain tumor diagnosis have 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 also reliable diagnosis of tumors in the early stages of formation. In this study, a two-stage segmentation method for accurate detection of the tumor area in magnetic resonance imaging of the brain is presented. In the first stage, after performing the necessary preprocessing on the image, the location of the tumor is located using a threshold-based segmentation method, and in the second stage, it is used as an indicator in a pond segmentation method based on the marker used. Placed. Given that in the first stage there is not much emphasis on accurate detection of the tumor area, the selection of threshold values over a large range of values will not affect the final results. In the second stage, the use of the marker-based pond segmentation method will lead to accurate detection of the tumor area. The results of the implementations show that the proposed method for accurate detection of the tumor area in a large range of changes in input parameters has the same and accurate results.