Comparative Study of Classification Methods for the Mitigation of Class Imbalance Issues in Medical Imaging Applications
Nathan K. Kueterman · OhioLink ETD Center (Ohio Library and Information Network) · 2020
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 imbalance.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.