Lists
Lists
Nya Yanga, Ornella Kelly and Homayounvala, Elaheh (2024) Breast cancer prediction and detection: comparison of the latest machine learning techniques. In: 7th International Conference on Innovative Computing and Communication (ICICC 2024), 16-17 February 2024, University of Delhi, New Delhi, India.
Breast cancer is a prevalent and potentially deadly disease affecting women in the UK, with 1 in 7 women and 1 in 1,000 men at risk Early diagnosis, effective treatment, awareness, lifestyle choices, genetic testing, and research efforts have helped reduce mortality and improve patient outcomes. Extensive research has enhanced our understanding of the disease and led to better patient survival rates and quality of life. However, breast cancer remains a significant global health challenge, requiring ongoing research and innovation. This paper discusses using machine learning and deep learning techniques, including Convolutional Neural Networks, Transfer Learning, and Ensemble Learning, to analyze a dataset primarily consisting of images. The main goal is to compare these methods based on performance, focusing on applying effective pre-processing techniques. using the Digital Database for Screening Mammography (DDMS) dataset. CNN exhibited favorable accuracy, and ResNet reached an impressive 93%.
![[thumbnail of Breast_Cancer_Prediction_and_Detection.pdf]](https://repository.londonmet.ac.uk/style/images/fileicons/text.png "Breast_Cancer_Prediction_and_Detection.pdf")
Restricted to Repository staff only until 1 August 2025.
Download (664kB) | Request a copy
 |
View Item |