Date of Graduation
5-2025
Document Type
Thesis
Degree Name
Master of Science in Biomedical Engineering (MSBME)
Degree Level
Graduate
Department
Biomedical Engineering
Advisor/Mentor
Rajaram, Narasimhan
Committee Member
Quinn, Kyle P.
Second Committee Member
Muldoon, Timothy J.
Keywords
Breast cancer; Deep learning; Machine learning; Multiphoton microscopy
Abstract
Accurate prediction of breast cancer recurrence plays a critical role in guiding treatment decisions, particularly regarding the use of systemic therapy for patients. While genomic assays such as the Oncotype DX Recurrence Score offer valuable prognostic information, they are limited in accessibility and application. The work presented in this thesis explores an imaging-based approach for the prediction of breast cancer recurrence that combines multiphoton microscopy (MPM) with deep learning to classify individual breast cancer biopsy samples by risk of recurrence. Genomic differences in tumors with different recurrence potentials may translate to distinct optical and structural information that can be captured by MPM techniques and subsequently extracted by deep learning models. Deep learning, particularly in the form of convolutional neural networks (CNNs), has proven to be a powerful tool in biomedical image analysis in areas such as image segmentation and disease classification. In this work, a custom CNN was designed and trained on MPM autofluorescence images of breast cancer core needle biopsy samples, using Oncotype DX Recurrence Scores as a ground truth for classification. This model was refined and evaluated on multiple combinations of training inputs through a robust cross-validation approach to ensure consistent performance across the entire dataset. Several combinations of image inputs led to highly accurate classifications, suggesting that the CNN is able to detect complex patterns in the MPM images that correspond to risk of breast cancer recurrence.
Citation
Powell, N. (2025). Using Deep Learning and Two-Photon Excitation Fluorescence Microscopy to Predict Breast Cancer Recurrence and Response to Chemotherapy. Graduate Theses and Dissertations Retrieved from https://scholarworks.uark.edu/etd/5779
