False Positive Reduction by Actively Mining Negative Samples for Pulmonary Nodule Detection in Chest Radiographs
This addresses the bottleneck of limited labeled data in medical imaging for improving nodule detection accuracy, though it appears incremental as it refines an existing detection network.
The paper tackled the problem of false positives in pulmonary nodule detection in chest radiographs by proposing a semi-supervised learning method that uses pseudo-negative labels from unlabeled data, reducing the false positive rate from 0.4864 to 0.1266 while maintaining sensitivity at 0.89.
Generating large quantities of quality labeled data in medical imaging is very time consuming and expensive. The performance of supervised algorithms for various tasks on imaging has improved drastically over the years, however the availability of data to train these algorithms have become one of the main bottlenecks for implementation. To address this, we propose a semi-supervised learning method where pseudo-negative labels from unlabeled data are used to further refine the performance of a pulmonary nodule detection network in chest radiographs. After training with the proposed network, the false positive rate was reduced to 0.1266 from 0.4864 while maintaining sensitivity at 0.89.