NORMA eResearch @NCI Library

Breast Cancer Detection using Deep Learning Techniques

Rodrigues, Melwin Francis (2020) Breast Cancer Detection using Deep Learning Techniques. Masters thesis, Dublin, National College of Ireland.

[img]
Preview
PDF (Master of Science)
Download (1MB) | Preview
[img]
Preview
PDF (Configuration manual)
Download (731kB) | Preview

Abstract

Breast cancer is a major health problem in women especially for the women who are above the age of 50. Early detection can help in saving many lives. Cancer begins when cells grow out of control to form a mass called a tumour. A tumour can be cancerous or benign. The most common symptoms of breast cancer are formation of lump. The detection of cancerous cells can prevent the loss of lives and help the women to take corrective actions before the condition gets worse. This was the motivation for this research in this research the data is divided into two classes i.e malignant and benign. The data is again sub divided into magnifications from 40 x, 100x, 200x, 400x. The dataset was pre-processed by using zoom, horizontal flip and rescale. Classification methods such as Dense Net 121, Inception V3 and CNN was used. The best classification results were given by Dense Net 121 with 95% accuracy. The accuracy and validation accuracy obtained was the better than most of the previous research results. This research will benefit the women and the doctors to detect the cancer cells in the preliminary stage.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science

Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Dan English
Date Deposited: 25 Jan 2021 14:14
Last Modified: 25 Jan 2021 14:14
URI: http://norma.ncirl.ie/id/eprint/4464

Actions (login required)

View Item View Item