Multi-task Graph Convolutional Neural Network for Calcification Morphology and Distribution Analysis in Mammograms

2021/05/14 by Hao Du, Du, Hao, Melissa Min-Szu Yao +7
Computer Science · Medicine · #AI in cancer detection #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Global Cancer Incidence and Screening #Radiomics and Machine Learning in Medical Imaging

paper · pdf · doi:10.48550/arxiv.2105.06822

openalex publication_date 2021/05/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The morphology and distribution of microcalcifications in a cluster are the most important characteristics for radiologists to diagnose breast cancer. However, it is time-consuming and difficult for radiologists to identify these characteristics, and there also lacks of effective solutions for automatic characterization. In this study, we proposed a multi-task deep graph convolutional network (GCN) method for the automatic characterization of morphology and distribution of microcalcifications in mammograms. Our proposed method transforms morphology and distribution characterization into node and graph classification problem and learns the representations concurrently. Through extensive experiments, we demonstrate significant improvements with the proposed multi-task GCN comparing to the baselines. Moreover, the achieved improvements can be related to and enhance clinical understandings. We explore, for the first time, the application of GCNs in microcalcification characterization that suggests the potential of graph learning for more robust understanding of medical images.

Citations

• Distilling the Knowledge in a Neural Network
• An introduction to ROC analysis
• Semi-Supervised Classification with Graph Convolutional Networks
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• RGCNN: Regularized Graph CNN for Point Cloud Segmentation
• Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries
• Improving Multi-Task Deep Neural Networks via Knowledge Distillation for Natural Language Understanding
• DeepGCNs: Can GCNs Go as Deep as CNNs?
• Dynamic Graph CNN for Learning on Point Clouds
• DeeperGCN: All You Need to Train Deeper GCNs
• Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries

Related

• Convolutional Neural Networks for the segmentation of microcalcification\n in Mammography Imaging
• Abnormality Detection in Mammography using Deep Convolutional Neural Networks
• Dual Convolutional Neural Networks for Breast Mass Segmentation and Diagnosis in Mammography
• MS-GWNN:multi-scale graph wavelet neural network for breast cancer diagnosis
• Zoom in to where it matters: a hierarchical graph based model for mammogram analysis