Breast Cancer Survival Prediction Using Machine Learning and Deep Learning
Authors
Roy, Marteena
Issue Date
2023-08
Degree
MSc in Data Analytics
Publisher
Dublin Business School
Rights holder
Rights
Items in eSource are protected by copyright. Previously published items are made available in accordance with the copyright policy of the publisher/copyright holder.
Abstract
Breast cancer continues to be a highly widespread and formidable kind of malignancy on a global
scale. The precise estimation of survival is of utmost importance in order to customize treatment
plans and enhance patient outcomes. The objective of this study was to improve the accuracy of
breast cancer survival prediction by combining two well-known datasets: METABRIC, which
provides extensive molecular profiling data, and CBIS-DDSM, a valuable collection of
mammographic images. The study utilized three sophisticated machine learning models, namely
Inception Net, Adam Net, and DenseNet, to make the most of how molecular and imaging
information can work together effectively. The DenseNet model stood out, achieving an 81%
accuracy in predicting breast cancer patient survival, surpassing Inception Net (66%) and Adam
Net (71%). We can create a helpful tool using DenseNet121 to study how well breast cancer
patients might survive by looking at their mammograms.