Improving Object Detection in Medical Image Analysis through Multiple Expert Annotators: An Empirical Investigation
This work addresses labeling variability in medical image analysis, which is an incremental improvement for enhancing diagnostic accuracy in healthcare applications.
The paper tackled the problem of subjectivity in medical image labeling by aggregating annotations from multiple experts and using a re-weighted loss function, resulting in improved object detection performance that outperformed baselines on a real-world dataset.
The work discusses the use of machine learning algorithms for anomaly detection in medical image analysis and how the performance of these algorithms depends on the number of annotators and the quality of labels. To address the issue of subjectivity in labeling with a single annotator, we introduce a simple and effective approach that aggregates annotations from multiple annotators with varying levels of expertise. We then aim to improve the efficiency of predictive models in abnormal detection tasks by estimating hidden labels from multiple annotations and using a re-weighted loss function to improve detection performance. Our method is evaluated on a real-world medical imaging dataset and outperforms relevant baselines that do not consider disagreements among annotators.