Zoom in to where it matters: a hierarchical graph based model for mammogram analysis
This work addresses breast cancer diagnosis for medical imaging, but it is incremental as it builds on existing graph-based methods with a focus on mimicking radiologist zoom behavior.
The authors tackled the problem of detecting abnormal lesions in mammograms for breast cancer diagnosis by proposing a hierarchical graph neural network that automatically zooms into regions of interest, achieving comparable AUC with state-of-the-art methods on the INbreast dataset.
In clinical practice, human radiologists actually review medical images with high resolution monitors and zoom into region of interests (ROIs) for a close-up examination. Inspired by this observation, we propose a hierarchical graph neural network to detect abnormal lesions from medical images by automatically zooming into ROIs. We focus on mammogram analysis for breast cancer diagnosis for this study. Our proposed network consist of two graph attention networks performing two tasks: (1) node classification to predict whether to zoom into next level; (2) graph classification to classify whether a mammogram is normal/benign or malignant. The model is trained and evaluated on INbreast dataset and we obtain comparable AUC with state-of-the-art methods.