Synthetic Sampling for Multi-Class Malignancy Prediction
This work addresses the challenge of class imbalance in medical image analysis for CADx systems, offering an incremental improvement in sensitivity for minority malignancy classes.
The paper tackled the problem of imbalanced multi-label classification in Computer-Aided Diagnosis systems by using synthetic oversampling techniques to improve per-class performance in malignancy prediction, resulting in an average sensitivity increase of 7.22% points for minority classes, with up to a 19.88% point increase for a specific class.
We explore several oversampling techniques for an imbalanced multi-label classification problem, a setting often encountered when developing models for Computer-Aided Diagnosis (CADx) systems. While most CADx systems aim to optimize classifiers for overall accuracy without considering the relative distribution of each class, we look into using synthetic sampling to increase per-class performance when predicting the degree of malignancy. Using low-level image features and a random forest classifier, we show that using synthetic oversampling techniques increases the sensitivity of the minority classes by an average of 7.22% points, with as much as a 19.88% point increase in sensitivity for a particular minority class. Furthermore, the analysis of low-level image feature distributions for the synthetic nodules reveals that these nodules can provide insights on how to preprocess image data for better classification performance or how to supplement the original datasets when more data acquisition is feasible.