Multi-Level Deep Generative Adversarial Networks for Brain Tumor Classification on Magnetic Resonance Images

The brain tumor is an abnormal and hysterical growth of brain tissues,and the leading cause of death affected patients worldwide.Even in this technol-ogy-based arena,brain tumor images with proper labeling and acquisition still have a problem with the accurate and reliable generation of realistic images of brain tumors that are completely different from the original ones.The artificially created medical image data would help improve the learning ability of physicians and other computer-aided systems for the generation of augmented data.To over-come the highlighted issue,a Generative Adversarial Network(GAN)deep learn-ing technique in which two neural networks compete to become more accurate in creating artificially realistic data for MRI images.The GAN network contains mainly two parts known as generator and discriminator.Commonly,a generator is the convolutional neural network,and a discriminator is the deconvolutional neural network.In this research,the publicly accessible Contrast-Enhanced Mag-netic Resonance Imaging(CE-MRI)dataset collected from 2005-to 2020 from different hospitals in China consists of four classes has been used.Our proposed method is simple and achieved an accuracy of 96%.We compare our technique results with the existing results,indicating that our proposed technique outper-forms the best results associated with the existing methods.

Automated Leukemia Screening and Sub-types Classification Using Deep Learning

Leukemia is a kind of blood cancer that damages the cells in the blood and bone marrow of the human body.It produces cancerous blood cells that disturb the human’s immune system and significantly affect bone marrow’s production ability to effectively create different types of blood cells like red blood cells(RBCs)and white blood cells(WBC),and platelets.Leukemia can be diagnosed manually by taking a complete blood count test of the patient’s blood,from which medical professionals can investigate the signs of leukemia cells.Furthermore,two other methods,microscopic inspection of blood smears and bone marrow aspiration,are also utilized while examining the patient for leukemia.However,all these methods are labor-intensive,slow,inaccurate,and require a lot of human experience and dedication.Different authors have proposed automated detection systems for leukemia diagnosis to overcome these limitations.They have deployed digital image processing and machine learning algorithms to classify the cells into normal and blast cells.However,these systems are more efficient,reliable,and fast than previous manual diagnosing methods.However,more work is required to classify leukemia-affected cells due to the complex characteristics of blood images and leukemia cells having much intra-class variability and inter-class similarity.In this paper,we have proposed a robust automated system to diagnose leukemia and its sub-types.We have classified ALL into its sub-types based on FAB classification,i.e.,L1,L2,and L3 types with better performance.We have achieved 96.06%accuracy for subtypes classification,which is better when compared with the state-of-the-art methodologies.

A Novel Inherited Modeling Structure of Automatic Brain Tumor Segmentation from MRI

Brain tumor is one of the most dreadful worldwide types of cancer and affects people leading to death.Magnetic resonance imaging methods capture skull images that contain healthy and affected tissue.Radiologists checked the affected tissue in the slice-by-slice manner,which was timeconsuming and hectic task.Therefore,auto segmentation of the affected part is needed to facilitate radiologists.Therefore,we have considered a hybrid model that inherits the convolutional neural network(CNN)properties to the support vector machine(SVM)for the auto-segmented brain tumor region.The CNN model is initially used to detect brain tumors,while SVM is integrated to segment the tumor region correctly.The proposed method was evaluated on a publicly available BraTS2020 dataset.The statistical parameters used in this work for the mathematical measures are precision,accuracy,specificity,sensitivity,and dice coefficient.Overall,our method achieved an accuracy value of 0.98,which is most prominent than existing techniques.Moreover,the proposed approach is more suitable for medical experts to diagnose the early stages of the brain tumor.