| About this Abstract |
| Meeting |
2024 TMS Annual Meeting & Exhibition
|
| Symposium
|
Materials Science for Global Development -- Health, Energy, and Environment: An SMD Symposium in Honor of Wole Soboyejo
|
| Presentation Title |
A Data Science Approach for Detecting Breast Cancer Using Shear Assay Measurements and Functional Principal Component Analysis |
| Author(s) |
Jolene Cao, Killian Onwudiwe, Jingjie Hu, Meenal Datta, Wole Soboyejo |
| On-Site Speaker (Planned) |
Jolene Cao |
| Abstract Scope |
Functional principal component analysis (FPCA) has developed rapidly in the "big data" revolution as an important data science tool to better analyze time series data. This work presents a novel approach for breast cancer detection using FPCA methodology to study the mechanical responses of live breast cells subjected to shear flow in microfluidic channels under in-situ microscopy observation. The measured temporal variations in strain in shear assay experiments are analyzed using FPCA to discover critical features of cells' in-situ temporal creep responses. Differences in the creep compliance responses of the nuclei and cytoplasm are explained along with the local creep properties of the actin cytoskeletal structures of non-tumorigenic breast cells (MCF-10A), less metastatic triple-negative breast cancer (TNBC) cells (MDA-MB-468), and highly metastatic breast cancer cells (MDA-MB-231). The implications of the results are discussed for the detection of non-tumorigenic and tumorigenic breast cells at different stages of cancer progression. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Biomaterials, Machine Learning, Mechanical Properties |