A Novel Segmentation of MRI Brain Tumor using Red Fox Optimization

Background: Brain tumors are abnormal growths of tissue within the brain and are associated with a high mortality rate, with most patients dying within 9 to 12 months and less than 3% surviving beyond 3 years. Early and effective detection is crucial for improving survival rates. One of the critical tasks in medical image processing is the segmentation of brain tumors from MRI images, a process that is challenging to perform manually due to the large volume of data generated during clinical procedures.Methods: The proposed method aims to automate brain tumor segmentation using a hybrid approach involving red fox optimization (RFO), OTSU image segmentation, and Expectation Maximization. Initially, MRI images are denoised using various filters such as bilateral, mean, morphological, and wiener filters. The morphological filter, which demonstrated superior performance, is then selected for further processing. Subsequently, the segmentation is optimized using Red Fox Optimization and the tumor is segmented using OTSU segmentation.Results: The denoising process using various filters was evaluated, and the morphological filter was found to outperform the others in terms of SNR and PSNR values. This filter was consequently used in the subsequent steps of the segmentation process. The application of Red Fox Optimization and OTSU segmentation resulted in the effective isolation of tumors from the MRI images, demonstrating the potential for this hybrid method to facilitate early detection of brain tumors.Conclusion: The hybrid method combining red fox optimization, OTSU segmentation, and Expectation Maximization presents a viable approach for the automated segmentation of brain tumors from MRI images. The superior performance of the morphological filter in the denoising process, coupled with the effective optimization and segmentation techniques, underscores the potential for this method to contribute to earlier and more accurate detection of brain tumors, ultimately aiding in reducing the high mortality rate associated with this disease.