Optimal DeepMRSeg based tumor segmentation with GAN for brain tumor classification

What is it about?

The accurate and timely treatment of brain tumor is considered as an imperative part in effectual planning of treatment. However, the manual categorization of tumor in Magnetic resonance imaging (MRI) with same structures or appearance is complex that relies on expertise to discover brain tumor. This paper devises an automatic mechanism that can perform the cataloguing of tumor with MRI. The pre-processing is termed as initial measure to normalize intensity. Here, pre-processing is carried out with min-max normalization. The segmentation is performed with Optimal DeepMRSeg strategy, wherein the DeepMRSeg is trained using newly devised sailfish Political Optimizer (SPO) algorithm. The proposed SPO is devised by combining sailfish optimization algorithm (SOA) and Political Optimizer (PO). Then the Convolutional neural network (CNN) features are extracted and data augmentation is performed. The data augmentation, like random translation, randomized left or right flipping, brightness, rotation or adjustment of contrast is done with CNN. Then, the classification is done with Generative Adversial network (GAN), and trained using Conditional Autoregressive Value at Risk-based sailfish political Optimizer (CAViaR-SPO) by combining CAViaR, SOA and PO. The proposed CAViaR-SPO-based GAN offered enhanced performance with elevated accuracy of 91.7%, segmentation accuracy of 90%, sensitivity of 92.8%, and specificity of 92.5%.

Featured Image

Why is it important?

Automated MRI is a non-invasive imaging modality utilized in Computer aided diagnosis (CAD) for visualizing internal configuration and body functions, like Alzheimer disease, disorders in movements, like Parkinson or brain diseases. The values of diagnosis are exaggerated with automated and precise MRI classification. Various techniques are devised for automatic detection of brain tumor and poses suitable techniques. The strongest technique is mining of Wavelet transform. This is considered as an effectual tool for extracting 2D image feature as it permits for analyzing the images at different resolution levels. The MRI of brain is utilized for discovering the tumor and progression of tumor modeling procedure. This data is utilized for detecting tumor and its diagnosis process MRI provides more data regarding brain as compared to ultrasound or CT. In addition, the MRI offers complete information regarding structure of brain and anomaly discovery of brain tissues. The scholars provided automatic techniques for detecting the tumor and cataloguing types with brain MRI in order to transfer medical images to computer

Perspectives

“

This paper presents a novel optimization driven classifier for determining the brain tumor using MRI. The first step to be performed is pre-processing wherein the noise is removed and intensity of image is normalized. The pre-processing is done with min-max normalization for scaling the value of intensity into 0 to1. Thereafter, the segmentation of brain tumor is done to generate the segments. Here, the segmentation is performed with optimal DeepMRSeg.

”