Globally-Aware Multiple Instance Classifier for Breast Cancer Screening
This addresses the challenge of accurate and interpretable breast cancer screening for medical diagnosis, though it is incremental in adapting existing deep learning methods to medical images.
The authors tackled the problem of breast cancer screening by developing a neural network that uses global saliency maps and local patches to classify lesions, achieving radiologist-level performance in mammography interpretation.
Deep learning models designed for visual classification tasks on natural images have become prevalent in medical image analysis. However, medical images differ from typical natural images in many ways, such as significantly higher resolutions and smaller regions of interest. Moreover, both the global structure and local details play important roles in medical image analysis tasks. To address these unique properties of medical images, we propose a neural network that is able to classify breast cancer lesions utilizing information from both a global saliency map and multiple local patches. The proposed model outperforms the ResNet-based baseline and achieves radiologist-level performance in the interpretation of screening mammography. Although our model is trained only with image-level labels, it is able to generate pixel-level saliency maps that provide localization of possible malignant findings.