# Zoom in to where it matters: a hierarchical graph based model for mammogram analysis

arXiv: https://arxiv.org/abs/1912.07517 · HTML: https://mlsanity.com/paper/1912.07517/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Dec 2019.

## Built on by (most cited first, 8 of 8)

- [Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future](https://mlsanity.com/paper/2105.13137/) (2021)
- [Multimodal Data Integration for Oncology in the Era of Deep Neural Networks: A Review](https://mlsanity.com/paper/2303.06471/) (2023)
- [RA-GCN: Graph Convolutional Network for Disease Prediction Problems with Imbalanced Data](https://mlsanity.com/paper/2103.00221/) (2021)
- [IA-GCN: Interpretable Attention based Graph Convolutional Network for Disease prediction](https://mlsanity.com/paper/2103.15587/) (2021)
- [Efficient High-Resolution Deep Learning: A Survey](https://mlsanity.com/paper/2207.13050/) (2022)
- [U-GAT: Multimodal Graph Attention Network for COVID-19 Outcome Prediction](https://mlsanity.com/paper/2108.00860/) (2021)
- [GKD: Semi-supervised Graph Knowledge Distillation for Graph-Independent Inference](https://mlsanity.com/paper/2104.03597/) (2021)
- [iPac: Incorporating Intra-image Patch Context into Graph Neural Networks for Medical Image Classification](https://mlsanity.com/paper/2510.23504/) (2025)

## Abstract (arXiv)

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.