International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 13 Issue: 02 | Feb 2026
p-ISSN: 2395-0072
www.irjet.net
A Comprehensive Review on Brain Tumor Classification Using Machine Learning and Deep Learning Techniques Ashish Cha nd1, Raj Kumar2 1Assistant Professor, Dept. of Electrical, Electronics & Communication Engineering, RIMT University, Punjab, India 2Assistant Professor, Dept. of Civil Engineering, RIMT University, Punjab, India
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Brain tumor classification plays a crucial role in
(CNNs), residual networks, hybrid models, and transfer learning approaches—have demonstrated remarkable success in medical image analysis by enabling robust feature extraction and accurate classification [2], [4], [6], [9], [10], [11]. Several studies have reported improved classification performance using data augmentation techniques, hybrid deep learning architectures, and large-scale public MRI datasets such as TCIA and Kaggle repositories [4], [16], [19], [21]. Consequently, this review systematically examines existing ML- and DL-based approaches for brain tumor classification, highlighting their methodologies, strengths, limitations, and emerging research trends [1], [14], [17].
early diagnosis, treatment planning, and patient prognosis. Magnetic Resonance Imaging (MRI) is the most widely used non-invasive imaging modality for detecting and analyzing brain tumors due to its high soft-tissue contrast. However, manual interpretation of MRI scans is time-consuming, subjective, and prone to inter-observer variability. To overcome these challenges, automated brain tumor classification systems based on Machine Learning (ML) and Deep Learning (DL) techniques have gained significant attention. This review paper presents a comprehensive analysis of traditional image processing methods, machine learning algorithms, and state-of-the-art deep learning models used for brain tumor classification. The paper discusses commonly used datasets, preprocessing techniques, feature extraction methods, classification strategies, evaluation metrics, and current challenges. Finally, future research directions and emerging trends in intelligent brain tumor diagnosis systems are highlighted.
2. BRAIN TUMOR TYPES AND MRI MODALITIES
2.1 Brain Tumor Types Brain tumors are characterized by abnormal cell growth within the brain and are broadly classified based on their origin, growth behavior, and degree of malignancy. In MRIbased brain tumor classification research, certain tumor types are more frequently studied due to their clinical prevalence, distinct radiological features, and availability in public datasets. Among these, gliomas, meningiomas, pituitary tumors, and healthy (no tumor) cases are the most commonly investigated categories [1], [14], [17].
Key Words: Brain Tumor Classification, MRI, Machine Learning, Deep Learning, CNN, Medical Image Analysis
1. INTRODUCTION Brain tumors are among the most life-threatening neurological disorders, characterized by abnormal and uncontrolled cell proliferation within the brain. According to the World Health Organization (WHO), brain tumors are broadly classified into benign and malignant categories, with gliomas, meningiomas, and pituitary tumors representing the most frequently occurring types [1], [14], [17]. Early and accurate classification of these tumors is critical for effective clinical decision-making, treatment planning, and improving patient survival rates [2], [15]. Magnetic Resonance Imaging (MRI) has become the imaging modality of choice for brain tumor diagnosis due to its superior soft-tissue contrast and absence of ionizing radiation. However, despite significant advancements in MRI technology, manual interpretation of brain MRI scans remains a challenging task for radiologists. Tumor heterogeneity, variations in size and shape, and overlapping intensity patterns between normal and abnormal tissues often lead to diagnostic uncertainty and inter-observer variability [1], [3], [18].To overcome these limitations, researchers have increasingly focused on automated brain tumor classification systems. In recent years, Machine Learning (ML) and Deep Learning (DL) techniques—particularly Convolutional Neural Networks
© 2026, IRJET
|
Impact Factor value: 8.315
2.1.1 Glioma Gliomas are malignant brain tumors that originate from glial cells, including astrocytes, oligodendrocytes, and ependymal cells. They represent the most aggressive and frequently occurring primary brain tumors in adults. Gliomas exhibit highly infiltrative growth patterns, making clear delineation from surrounding healthy tissue particularly challenging. On MRI scans, gliomas often display heterogeneous intensity patterns, irregular tumor boundaries, edema, and necrotic regions, especially in high-grade cases. These complex characteristics make glioma detection and classification a critical yet challenging task for automated machine learning and deep learning systems [2], [11], [15], [21].
2.1.2 Meningioma Meningiomas are generally benign tumors that arise from the meninges, the protective membranes covering the brain and spinal cord. They are typically slow-growing and wellcircumscribed, which facilitates their detection and
|
ISO 9001:2008 Certified Journal
|
Page 97