Novel Framework of Segmentation 3D MRI of Brain Tumors

Abstract

Medical image segmentation is a crucial process for computer-aided diagnosis and surgery. Medical image segmentation refers to portioning the images into small, disjointed parts for simplifying the processes of analysis and examination. Rician and speckle noise are different types of noise in magnetic resonance imaging (MRI) that affect the accuracy of the segmentation process negatively. Therefore, image enhancement has a significant role in MRI segmentation. This paper proposes a novel framework that uses 3D MRI images from Kaggle and applies different diverse models to remove Rician and speckle noise using the best possible noise-free image. The proposed techniques consider the values of Peak Signal to Noise Ratio (PSNR) and the level of noise as inputs to the attention-U-Net model for segmentation of the tumor. The framework has been divided into three stages: removing speckle and Rician noise, the segmentation stage, and the feature extraction stage. The framework presents solutions for each problem at a different stage of the segmentation. In the first stage, the framework uses Vibrational Mode Decomposition (VMD) along with Block-matching and 3D filtering (Bm3D) algorithms to remove the Rician. Afterwards, the most significant Rician noise-free images are passed to the three different methods: Deep Residual Network (DeRNet), Dilated Convolution Auto-encoder Denoising Network (Di-Conv-AE-Net), and Denoising Generative Adversarial Network (DGAN-Net) for removing the speckle noise. VMD and Bm3D have achieved PSNR values for levels of noise (0, 0.25, 0.5, 0.75) for reducing the Rician

Classification of Brain Tumors Using Hybrid Feature Extraction Based on Modified Deep Learning Techniques

“…Automatic segmentation and diagnosis of brain cancer using deep-learning techniques can save lives and prevent further tumor growth. Numerous approaches, such as those in [1][2][3][4][5][6], were implemented to segment brain tumors using medical images, such as CT scans and MRIs. Nevertheless, various developed models provided an average accuracy between 90% and 98%.…”

“…Cancer is the leading cause of mortality worldwide, as around ten million patients died in 2020 [1,2]. Cancer, a term that encompasses any presence of one or many tumors, refers to the uncontrollable growth of cells inside the human body.…”

“…Cancer, a term that encompasses any presence of one or many tumors, refers to the uncontrollable growth of cells inside the human body. This growth can be slow or aggressive [2][3][4][5]. This phenomenon occurs suddenly at any age without any noticeable symptoms [5,6].…”

“…In many situations, cancer is fatal if no suitable treatment is provided [6,7]. The World Health Organization (WHO) reported that around 80,000 cases of BrT are discovered in the United States (US) yearly [1,2]. Among these cases, 32%-34% are considered very aggressive or malignant [1].…”

“…Brain cancer detection has been studied for over a decade using various imaging techniques, such as CT scans and MRIs. Multiple studies have been performed to improve brain tumor diagnoses using different technologies [2,[4][5][6][7][8][9][10]. These technologies aim to save lives, improve patients' quality of life, or reduce the need for surgery.…”