Advisor | Herndon, Nic | |
Author | Rose, Madison | |
Date Accessioned | 2023-07-13T16:59:06Z | |
Date Available | 2023-07-13T16:59:06Z | |
Date Created | 2023-05 | |
Date of Issue | 2023-05-03 | |
xmlui.metadata.dc.date.submitted | May 2023 | |
Identifier (URI) | http://hdl.handle.net/10342/12971 | |
Description | Breast cancer is a leading cause of cancer death and one of the most common cancers among women. Treatment looks different for every patient due to a variety of factors. One factor that can change a patient’s treatment plan is how aggressive their cancer is. Aggressive cancers are more likely to reoccur and require intense treatment options such as chemotherapy. Cancer aggression is currently measured by a recurrence score which can be determined by a pathologist viewing hematoxylin and eosin-stained slides (HE slides) from breast biopsies. Recurrence scores are an important factor considered by oncologists when crafting a treatment plan for their patients. However, these tests are costly and in high demand which limits patient access. In this work, applications of machine learning to the issue of breast cancer recurrence are discussed. The use of machine learning could greatly benefit recurrence prediction by aiding pathologists. The proposed method uses a three-step pipeline to accomplish this. Utilizing digitized HE slides, the pipeline will perform the following steps: data processing, clustering, and classification. Overall, this work aims to aid pathologists in recurrence score prediction and make recurrence score testing more accessible to breast cancer patients. | |
Mimetype | application/pdf | |
Publisher | East Carolina University | |
Subject | machine learning | |
Subject | breast cancer recurrence | |
Subject | computer vision | |
Title | Machine Learning Techniques to Aid Breast Cancer Recurrence Prediction | |
Type | Honors Thesis | |
xmlui.metadata.dc.date.updated | 2023-06-30T13:45:23Z | |
Department | Computer Science | |
xmlui.metadata.dc.degree.name | BS | |
xmlui.metadata.dc.degree.level | Undergraduate | |
xmlui.metadata.dc.degree.discipline | Computer Science | |
xmlui.metadata.dc.degree.grantor | East Carolina University | |
xmlui.metadata.dc.degree.department | Computer Science | |
xmlui.metadata.dc.access.option | Open Access | |
xmlui.metadata.dc.type.material | text | |