Adversarial Deep Structural Networks for Mammographic Mass Segmentation

By Wentao Zhu, Xiaohui S. Xie. 2016

69 citations recorded by the source corpus.

Mass segmentation is an important task in mammogram analysis, providing effective morphological features and regions of interest (ROI) for mass detection and classification. Inspired by the success of using deep convolutional features for natural image analysis and conditional random fields (CRF) for structural learning, we propose an end-to-end network for mammographic mass segmentation. The network employs a fully convolutional network (FCN) to model potential function, followed by a CRF to perform structural learning. Because the mass distribution varies greatly with pixel position, the FCN is combined with position priori for the task. Due to the small size of mammogram datasets, we use adversarial training to control over-fitting. Four models with different convolutional kernels are further fused to improve the segmentation results. Experimental results on two public datasets, INbreast and DDSM-BCRP, show that our end-to-end network combined with adversarial training achieves the-state-of-the-art results.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Opportunities and obstacles for deep learning in biology and medicine (2017, background): “researchers constructed adversarial examples [60].”
Universal Adversarial Perturbations Against Semantic Image Segmentation (2017, methodology): “Moreover, training with adversarial examples has been applied to mammographic mass segmentation to reduce overfitting [32].”
Generative Adversarial Network in Medical Imaging: A Review (2018, background): “adversarial training scheme is to enforce network invariance to small perturbations of the training samples in order to reduce overfitting on small size dataset [177, 176].”
Deep Multi-instance Networks with Sparse Label Assignment for Whole Mammogram Classification (2016, methodology): “Several works have used deep networks to perform mammogram mass classification [11,6,25].”
Generative Adversarial Networks: A Survey and Taxonomy (2019, methodology): “GANs have been applied to various domains such as computer vision [7]–[14], natural language processing [15]–[18], time series synthesis [19]–[23], semantic segmentation [24]–[28] etc. GANs belong to the family of generative models.”
Deep semantic segmentation for automated driving: Taxonomy, roadmap and challenges (2017, methodology): “It has been used in robotics [1][2][3][4], medical applications [5][6], augmented reality [7], and most prominently automated driving [8][9][10][11].”
Visual SLAM for Automated Driving: Exploring the Applications of Deep Learning (2018, methodology): “It has been used in robotics [60, 6, 62, 36], medical applications [14, 71], augmented reality [43], and most prominently automated driving [69, 53, 9, Table 4: Semantic Competition on Cityscapes [15].”