ITDS | SPMS

Prostate Cancer Diagnosis Using Machine Learning Algorithms

Project Description
Supervisor

It envisages applying the ML algorithms for early prostate cancer detection, considering MRI images downloaded from the ProstateX dataset available at The Cancer Imaging Archive. Specifically, in this research context, an attempt will be made to investigate the efficiency of CNN, Random Forest, and SVM with the aim of enhancing the diagnostic accuracy. Advanced computational tools and Python-based libraries featuring Scikit-learn and TensorFlow are hereby proposed to be utilized in this study; the computation shall be carried out on Kaggle. In view of that, each of the ML algorithms makes the diagnosis in order to find their comparative accuracies, precisions, recalls, and F1-scores. The result showed that the ML algorithms significantly raised diagnostic accuracy by reducing overdiagnosis. Among the algorithms listed for comparison, the Random Forest algorithm attained the highest overall testing accuracy and hence is more robust and clinically deployable. Overall, results in these studies underpin the transformational role of ML in diagnosis for improving outcomes in patients, besides pointing toward affordable health care. If such new computational capabilities were introduced into a clinical setting, it would hold great promise for modernizing the diagnosis of prostate cancer and would strengthen the broader role of machine learning approaches to health.

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.

To conduct a comprehensive comparative analysis of various ML algorithms on their performance in detecting prostate cancer using MRI scans, aiming to identify the most effective techniques for practical clinical application.

2023/2024

Nov 18, 2024

ABDUL AZIZ MASAUDU OPPONG ABERESE SOLOMON BISMARK JOE-OWUYAW YEBOAH FELIX KYERE PHILEMON KOFI

BSc Information Technology