Skip to Main Content
 

Global Search Box

 
 
 

ETD Abstract Container

Abstract Header

Comparative Study of Classification Methods for the Mitigation of Class Imbalance Issues in Medical Imaging Applications

Kueterman, Nathan
http://rave.ohiolink.edu/etdc/view?acc_num=dayton1591611376235015

Abstract Details

2020, Master of Science in Electrical Engineering, University of Dayton, Electrical and Computer Engineering.
The rapid development and popularization of Machine Learning (ML) has paved the way to state of the art solutions in many domains, namely image-based applications such as image classification, object detection and tracking to name a few. The medical imaging field is a bountiful source for image data with high potential for impacting the common good. One glaring issue persists; most medical imaging datasets tend to have class imbal- ance. As a result, many ML computer aided detection (CAD) algorithms have surfaced to mitigate this issue. The focus of this work is to comparatively analyze a portion of them on multiple medical imaging datasets. Traditional Deep Learning (DL) classifiers are used in one and two stage architectures as well as combined with Support Vector Machines. The CIFAR10 dataset is utilized for benchmarking and determining the relationship between classifier performance and class imbalance ratio. Performances vary across the datasets and although the two-stage architectures did not always have the highest overall accuracy, they are warranted in specific class imbalance scenarios.
Russell Hardie, Ph.D. (Advisor)
Barath Narayanan, Ph.D. (Committee Member)
John Loomis, Ph.D. (Committee Member)
Robert Wilkens, Ph.D. (Other)
Eddy Rojas, Ph.D. (Other)
80 p.
Computer Engineering; Electrical Engineering; Medical Imaging
medical imaging; machine learning; deep learning; class imbalance; data augmentation, sampling methods; diabetic retinopathy; leukemia; CIFAR-10; CIFAR10; leukocyte; ensemble networks; neural networks; comparative study

Recommended Citations

Citations

  • Kueterman, N. (2020). Comparative Study of Classification Methods for the Mitigation of Class Imbalance Issues in Medical Imaging Applications [Master's thesis, University of Dayton]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1591611376235015

    APA Style (7th edition)

  • Kueterman, Nathan. Comparative Study of Classification Methods for the Mitigation of Class Imbalance Issues in Medical Imaging Applications. 2020. University of Dayton, Master's thesis. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=dayton1591611376235015.

    MLA Style (8th edition)

  • Kueterman, Nathan. "Comparative Study of Classification Methods for the Mitigation of Class Imbalance Issues in Medical Imaging Applications." Master's thesis, University of Dayton, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1591611376235015

    Chicago Manual of Style (17th edition)

dayton1591611376235015
822
© 2020, all rights reserved.
This open access ETD is published by University of Dayton and OhioLINK.