A Novel Data Augmentation-Based Brain Tumor Detection Using Convolutional Neural Network

Abstract

Brain tumor is a severe cancer and a life-threatening disease. Thus, early detection is crucial in the process of treatment. Recent progress in the field of deep learning has contributed enormously to the health industry medical diagnosis. Convolutional neural networks (CNNs) have been intensively used as a deep learning approach to detect brain tumors using MRI images. Due to the limited dataset, deep learning algorithms and CNNs should be improved to be more efficient. Thus, one of the most known techniques used to improve model performance is Data Augmentation. This paper presents a detailed review of various CNN architectures and highlights the characteristics of particular models such as ResNet, AlexNet, and VGG. After that, we provide an efficient method for detecting brain tumors using magnetic resonance imaging (MRI) datasets based on CNN and data augmentation. Evaluation metrics values of the proposed solution prove that it succeeded in being a contribution to previous studies in terms of both deep architectural design and high detection success.

Ensemble deep learning for brain tumor detection

“…Authors in Alsaif et al (2022) provides the result in term of accuracy 93%, precision 94%, recall 93% and F1-measure 93%. Authors in Rehman et al (2020) achieved the result in terms of accuracy 98% and precision 88%.…”

“…Different types of medical imaging and diagnostic techniques are used to obtain information related to tumors. Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) are methods for identifying normal and abnormal growing cells in the brain (Houssein et al, 2021b;Alsaif et al, 2022). The Computed Tomography (CT) scan is used to diagnose the patient using an X-ray and the computer to create the brain images in the axial fragments (Bekhet et al, 2020;Fahmi et al, 2020;Mubashar et al, 2022).…”

“…The detailed review of CNN architectures is presented inAlsaif et al (2022) and provides the characteristics of different models such as VGG, ResNet, and AlexNet. The method based on CNN and data augmentation is applied to the MRI dataset to detect the brain tumor, and the result showed that the VGG model achieved a high value with a 0.93% accuracy,0.93% F1-score, 0.94% precision, and 0.93% recall.Some gaps can be utilized to recognize and detect brain tumors, including ensemble classifiers, machine learning methods, and numerous datasets used to test the generalizability of methods like BRATS, T1-weighted MRI dataset, and deep learning model to categorize the MRI brain pictures.…”

Data Complexity Based Evaluation of the Model Dependence of Brain MRI Images for Classification of Brain Tumor and Alzheimer’s Disease

“…The transfer learning technique is one of the most used techniques that have been adopted to develop robust and efficient methods for the classification of Brain Tumors. Reference [1] used brain MRI data from Kaggle to detect tumors that contain 253 brain MRI images out of which 155 image samples are tumorous and 98 images are non-tumorous. The authors have implemented three image augmentation techniques, namely flipping, rotation and translation, and produced 3700 new augmented images.…”

“…Brain Tumor is a life-threatening disease that is a result of uncontrolled and abnormal growth of brain cells leading to Brain Tumors disrupting the operation of the brain. Brain Tumors have been reported as the 10th leading cause of deaths worldwide [1]. The main causes of Brain Tumors are still unknown and the successful treatment, detection, and identification of Brain Tumors at an early phase becomes vital.…”