Deep Multi-instance Networks with Sparse Label Assignment for Whole Mammogram Classification
This addresses the problem of reducing annotation costs in medical imaging for clinicians and researchers, though it appears incremental as it builds on existing multi-instance learning and deep convolutional methods.
The paper tackles mammogram classification for breast cancer diagnosis by proposing deep multi-instance networks that eliminate the need for costly manual annotations in training, achieving robust results on the INbreast dataset.
Mammogram classification is directly related to computer-aided diagnosis of breast cancer. Traditional methods requires great effort to annotate the training data by costly manual labeling and specialized computational models to detect these annotations during test. Inspired by the success of using deep convolutional features for natural image analysis and multi-instance learning for labeling a set of instances/patches, we propose end-to-end trained deep multi-instance networks for mass classification based on whole mammogram without the aforementioned costly need to annotate the training data. We explore three different schemes to construct deep multi-instance networks for whole mammogram classification. Experimental results on the INbreast dataset demonstrate the robustness of proposed deep networks compared to previous work using segmentation and detection annotations in the training.