Classification and Detection in Mammograms with Weak Supervision via Dual Branch Deep Neural Net
This work addresses the challenge of limited expert annotations in medical imaging for clinicians, though it is incremental as it builds on existing weakly-supervised strategies.
The authors tackled the problem of high annotation costs in medical imaging by proposing a dual branch deep neural network for multi-class classification and localization of anomalies in mammograms using only global image tags, achieving improved performance over previous weakly-supervised methods on a dataset of approximately 3,000 mammograms.
The high cost of generating expert annotations, poses a strong limitation for supervised machine learning methods in medical imaging. Weakly supervised methods may provide a solution to this tangle. In this study, we propose a novel deep learning architecture for multi-class classification of mammograms according to the severity of their containing anomalies, having only a global tag over the image. The suggested scheme further allows localization of the different types of findings in full resolution. The new scheme contains a dual branch network that combines region-level classification with region ranking. We evaluate our method on a large multi-center mammography dataset including $\sim$3,000 mammograms with various anomalies and demonstrate the advantages of the proposed method over a previous weakly-supervised strategy.