International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 12 Issue: 03 | Mar 2025
p-ISSN: 2395-0072
www.irjet.net
TumorTrace – Brain Tumor Detection System Mohammed A. Shekhani1, Ayush Sahane2, Arya Singasane3, Harshal Tupe4, Prof. Vijay Bhosale5 1,2,3,4Student, Dept of Computer Engineering, MGM's College of Engineering and Technology, Kamothe,
Navi Mumbai, India Dept of Computer Engineering, MGM's College of Engineering and Technology, Kamothe, Navi Mumbai, India ---------------------------------------------------------------------***--------------------------------------------------------------------5Prof. Vijay Bhosale: Professor,
Abstract - Brain tumours are among the most critical
Keras and TensorFlow for model development, OpenCV for image preprocessing, and Streamlit for creating a userfriendly web interface.
medical conditions requiring early and accurate detection for successful treatment. Traditional diagnostic methods, such as manual interpretation of MRI scans, are prone to human error and may lead to delays in diagnosis. TumourTrace is an AIdriven system that leverages Convolutional Neural Networks (CNNs) to automate brain tumour detection from MRI scans. The system provides real-time analysis, reducing human error and improving diagnostic accuracy. The dataset comprises preprocessed MRI images, and the model achieves high accuracy in detecting tumours. TumourTrace offers a userfriendly interface for radiologists and clinicians, enabling quick and reliable tumour detection. Future enhancements include expanding the dataset, improving early-stage detection, and integrating cloud-based platforms for broader accessibility.
The primary objective of TumourTrace is to improve the accuracy and efficiency of brain tumour detection, particularly in resource-constrained environments where access to specialized radiologists may be limited. By providing a reliable second opinion, the system can assist healthcare professionals in making more informed decisions, ultimately leading to better patient outcomes. Furthermore, the system is designed to be scalable, allowing it to handle large volumes of MRI scans and adapt to different healthcare environments, from small clinics to large hospitals.
1.1 Motivation The motivation behind developing TumourTrace stems from the critical need for early and accurate detection of brain tumours. Early diagnosis is essential for improving patient outcomes, as it allows for timely intervention and more effective treatment options. However, traditional diagnostic methods, which rely on manual interpretation of MRI scans, are often slow and prone to human error. TumourTrace aims to address these challenges by providing an automated, AI-driven solution that can assist radiologists in making faster and more accurate diagnoses.
Key Words: Brain Tumor Detection, Convolutional Neural Network (CNN), Keras, TensorFlow, Streamlit, Medical Imaging, Deep Learning.
1.INTRODUCTION Brain tumours are among the most severe and lifethreatening medical conditions, with early detection playing a critical role in determining the success of treatment and patient outcomes. According to the World Health Organization (WHO), brain tumours account for a significant percentage of cancer-related deaths worldwide, primarily due to late diagnosis and the complexity of treatment options. Traditional diagnostic methods for brain tumours rely heavily on the manual interpretation of Magnetic Resonance Imaging (MRI) scans by radiologists. While MRI is a powerful imaging tool, the manual analysis of these scans is time-consuming, and prone to human error,
Another key motivation is the potential to reduce the workload of radiologists, particularly in regions with a shortage of specialized medical professionals. By automating the tumour detection process, TumourTrace can help healthcare providers in resource-constrained environments deliver better care to their patients. Additionally, the system's ability to provide real-time results can significantly reduce the time required for diagnosis, enabling faster treatment decisions and improving patient outcomes.
TumourTrace is an AI-powered system designed to address the challenges associated with traditional brain tumour detection methods. The system utilizes a CNN-based deep learning model to automatically detect and classify brain tumours from MRI scans. By automating the tumour detection process, TumourTrace aims to reduce the reliance on manual interpretation, minimize diagnostic errors, and provide real-time results to healthcare professionals. The system is built using state-of-the-art technologies, including
© 2025, IRJET
|
Impact Factor value: 8.315
The rapid evolution of deep learning and computer vision technologies presents a unique opportunity to revolutionize medical diagnostics. Traditional tumor detection methods, while effective, cannot leverage the pattern-recognition capabilities of modern AI systems. TumourTrace harnesses these advancements through its CNN-based architecture, which continuously improves with more data a capability absent in conventional approaches. This technological leap is
|
ISO 9001:2008 Certified Journal
|
Page 949