Revolutionizing Brain Tumor Diagnosis with Convolutional Neural Networks
Year: 2025
Type: conference-paper
Abstract: Historically, the diagnosis of brain tumors from magnetic resonance imaging (MRI) images has been a careful and extended endeavor that relies heavily on the expertise of radiologists and neurologists. In addition to being time-consuming, the complex nature of brain image analysis makes it vulnerable to cognitive biases and human error, which can affect the precision and effectiveness of diagnosis. Moreover, manual MRI scan interpretation might result in discrepancies between practitioners, which makes diagnosis even more difficult. These difficulties highlight the need for innovative approaches to improve the accuracy and speed of brain tumor identification as the need for quicker and more accurate medical evaluations keeps rising. To meet these difficulties, an innovative method based on image-driven Convolutional Neural Networks (CNNs) has been developed. Meningiomas, pituitary, gliomas, and absence tumors are the four major brain cancer groups that this research focuses on. With the basis of the EfficientNetB3 framework which had been pre-trained on the large-scale ImageNet dataset, the model uses a transfer learning method using a brain tumor dataset of 7023 images by adding extra layers that are exclusively meant to enhance classification and improved performance. The proposed method secures a notable accuracy of 99.84% and a precision of 99.33%. This advanced approach not only improves diagnostic precision but also significantly reduces the time required for neurologists to examine scans, enabling them to focus more on patient care and the development of preventive strategies. The efficiency of the proposed model underlines that it can become a breakthrough in clinical diagnostics and stimulate the progress of medical disciplines’ development. For a comprehensive overview of the model architecture and implementation, please visit the GitHub repository https://github.com/Aryansin1234/Brain-Tumor-Detection-EfficientNet.git . Additionally, a live demonstration of the model’s capabilities can be accessed on the website https://neurodetect.devopsjourney.tech/ .
Source: Procedia Computer Science
Authors: Aryan Singh, Mohd Shuaib, Manoj Diwakar, Aditya Joshi, Prabhishek Singh, Neha Pandey
Institutions: Bennett University, Graphic Era University
Language: English
Subfield: Neurology
Field: Neuroscience
Domain: Life Sciences
Open Access status: diamond
OpenAlex ID: W4410300429