Brain Tumor Detection

Authors: Swati Bhoir, Sakshi Tambe, Nilam Chaudhari, Kaushal Sand, Nilesh Sharma

Country: India

Full-text Research PDF File:   View   |   Download

Abstract: Accurate detection and diagnosis of brain tumors from MRI scans are crucial to mitigate the risks associated with this complex and often life-threatening condition. The intricate structure of the brain, characterized by interconnected tissues, poses a significant challenge for tumor detection. Despite various existing approaches, efficient detection remains a considerable hurdle due to the variability in tumor shapes, appearances, and locations. In this paper, we propose a deep learning-based approach for the detection of brain tumors from MRI scans.
Our proposed method utilizes Convolutional Neural Networks (CNNs) to effectively learn discriminative features from the MRI images. The CNN architecture is optimized to detect tumors accurately, leveraging the rich structural information available in MRI scans.
We also integrate multiple modalities of MRI images to enhance detailed structural information, which improves the robustness of our approach. The fusion of different MRI modalities enables the model to capture complementary information and overcome the limitations of using single-modal MRI.
Experimental results on a publicly available brain tumor dataset demonstrate the effectiveness of the proposed method. Our approach outperforms existing state-of-the-art methods in terms of both detection accuracy and computational efficiency. The results indicate that the proposed method can provide reliable and accurate detection of brain tumors, thus contributing significantly to the early diagnosis and treatment planning of this life-threatening condition

Keywords: Brain Tumor Detection, MRI Scans, Deep Learning, Convolutional Neural Networks (CNNs), Tumor Diagnosis

Paper Id: 232337

Published On: 2025-03-30

Published In: Volume 13, Issue 2, March-April 2025

Share this