Detection and Identification of Prostate Cancer using deep learning

Chakari, Ahmed Ozair (2025) Detection and Identification of Prostate Cancer using deep learning. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (2MB) | Preview
Preview	PDF (Configuration Manual) Download (918kB) | Preview

Abstract

Some of the difficult diseases to diagnose effectively, Prostatitis, may also disrupt normal testing tests such as the prostate-specific antigen (PSA), which often provide inconclusive results and require unnecessary invasive treatment. To overcome these shortcomings, this paper presents a deep learning based method of detecting and classifying MRI images of prostate Cancer. The system is constructed with the use of Convolutional Neural Network (CNN) models, including ResNet50, DenseNet121, and also Stacking Hybrid Model, which combines a number of models to enhance the quality of predictions. The models are trained and evaluated on the publicly available Transverse Plane Prostate MRI Dataset in Kaggle. Preprocessing, data augmentation and optimization methods are used to boost generalisation. This research shows the proposed framework is much better in the accuracy of diagnosis (achieving 94.44% accuracy, exceeding the ensemble baseline of Yoo et al. (2019) by 7.44%), misdiagnosis, and unnecessary biopsies than the traditional ways. The automated system is a dependable that aids in the detection of this specific cancer, which is less invasive, faster, and accurate (94.44% accuracy, surpassing the multi-modal hybrid model of Passera et al. (2021) by 2.44% in classifying the cancer.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Sahni, Vikas UNSPECIFIED
Uncontrolled Keywords:	Prostate Cancer; Deep Learning; MRI; Image Classification; Convolutional Neural Network; ResNet50; DenseNet121; Stacking Hybrid Model
Subjects:	Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence Q Science > Life sciences > Medical sciences > Pathology > Tumors > Cancer R Medicine > Healthcare Industry Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Artificial Intelligence
Depositing User:	Ciara O'Brien
Date Deposited:	02 Sep 2026 08:45
Last Modified:	02 Sep 2026 08:45
URI:	https://norma.ncirl.ie/id/eprint/9751

Actions (login required)

View Item