AMADI, JESSICA CHINENYE (2025) EARLY DETECTION OF BREAST CANCER USING A HYBRID MACHINE LEARNING ALGORITHM. Other thesis, GODFREY OKOYE UNIVERSITY, ENUGU.
![[img]](https://eprints.gouni.edu.ng/style/images/fileicons/text.png) |
Text
REPO178.docx Download (3MB) |
Abstract
The field of information technology (IT) is gradually spreading around the world, and with the boom in the use of artificial intelligence, predictive systems are revolutionizing healthcare. However, this research project leverages advancements in artificial intelligence and machine learning to develop a predictive model for breast cancer diagnosis. Utilizing datasets from the Kaggle system, the project employs a Convolutional Neural Network (CNN) architecture, ResNet-50, and a custom model to classify images into three categories: benign, malignant, and also handle structured clinical data, including patient demographics and historical information, such as age, by the Custom model. The dataset used to train the model consists of 891 benign and 421 malignant cases. The developed system's CNN model comprises 17 convolutional layers and was trained over 50 epochs. The goal of this project is to evaluate the accuracy of our model in detecting breast cancer, and the results from the evaluation, after fine-tuning the ResNet-50 model using a custom model, indicate a high accuracy of 99.86%. Running locally on the user's machine, the developed system has the potential to assist healthcare professionals.
| Item Type: | Thesis (Other) |
|---|---|
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Divisions: | Faculty of Natural and Applied Sciences |
| Depositing User: | Uchenna Eneogwe |
| Date Deposited: | 19 Jun 2026 15:13 |
| Last Modified: | 19 Jun 2026 15:13 |
| URI: | http://eprints.gouni.edu.ng/id/eprint/5854 |
Actions (login required)
 |
View Item |
