Date of Graduation
5-2021
Document Type
Thesis
Degree Name
Bachelor of Science in Biomedical Engineering
Degree Level
Undergraduate
Department
Biomedical Engineering
Advisor/Mentor
Quinn, Kyle
Abstract
With deep learning being leveraged more regularly in the field of image classification, particularly in medical imaging, network optimizations have become a field in and of itself. With open source, comprehensive medical image datasets few and far, computational dataset expansion has become a useful tool for researchers without the ability to further manually collect data. However, with the rich amount of data that imaging modalities like multi-photon microscopy collect at a time, there is potential to expand datasets through proper utilization of this data that often time goes unused. Previous deep learning studies have shown that improper expansion can conflate network accuracies and incorrectly train the network. Through the metrics of mean-squared error and correlation coefficient, I want to explore the expansion of image datasets while avoiding this phenomenon that arises from not using independent data.
Keywords
Deep Learning; Bioengineering; Image Classification; Neural Network; Image Expansion; Computer Science; Service Learning
Citation
Yousef, A. (2021). Expanding Image Datasets for Deep Learning by Evaluating Independence through Coefficient Correlation and Mean-Squared Error. Biomedical Engineering Undergraduate Honors Theses Retrieved from https://scholarworks.uark.edu/bmeguht/99
Included in
Computational Engineering Commons, Other Biomedical Engineering and Bioengineering Commons, Service Learning Commons
