ITDS | SPMS

DETECTION OF LUNG CANCER USING CONVOLUTIONAL NEURAL NETWORK

Project Description
Supervisor

This project presents the development of an intelligent lung cancer detection system using Convolutional Neural Network (CNN) model trained on MRI images. The system classifies MRI scans into two, namely, cancerous and non-cancerous. Some of the key features include advanced preprocessing steps, such as histogram-based MRI verification, and integration with a Flutter front-end and Flask API. The evaluation metrics yielded promising results with an overall accuracy of 83 percent, F-1 score of 79 percent, precision and recall values of above 78 percent. The system is tailored to enhance early detection and diagnosis support especially in the Ghanaian health context, especially where radiological resources are limited. The application’s user interface offers scan history, real-time predictions, educational tips, and secure scan validation system. This project offers a cost-effective and scalable diagnostic tool that supports public heath efforts in reducing late-stage lung cancer diagnoses. The system uses Python, OpenCV and Tensorflow to perform advanced preprocessing operations to improve its performance. The system maintains high accuracy in Lung Cancer detection through these methods which handles noise and other issues during the detection. The overall structure of this project provides automatic detection of lung cancer lesions and flexible possibility of application in various health environments. It encourages early detection and enhances early treatment of Lung Cancer. This lung cancer detection system was adjusted to make use of only Magnetic Resonance Images to detect cancer in the lungs. Overall, the research demonstrated how Artificial Intelligence can transform cancer diagnostics and treatment in Ghana with solutions to limited radiologists in our part of the world.

Machine Learning: Machine Learning (ML) research in Computer Science and Information Technology focuses on the development of algorithms and models that enable computers to learn from data and improve their performance over time without being explicitly programmed. It is a subset of Artificial Intelligence that uses statistical techniques to give machines the ability to learn patterns, make decisions, and predict outcomes based on data. Supervised learning, a key area of ML research, involves training models on labeled data, where the input-output relationships are predefined. This method is widely used for tasks such as classification (e.g., spam detection) and regression (e.g., predicting house prices). Unsupervised learning, on the other hand, involves finding hidden patterns in data without predefined labels, with clustering and association being typical applications in areas such as customer segmentation and anomaly detection. Reinforcement learning is another area of ML that focuses on teaching agents to make decisions by interacting with their environment and receiving feedback in the form of rewards or penalties. It is often applied in robotics, game playing, and autonomous systems, where continuous learning and adaptation are required.