Adversarial Deep Structural Networks for Mammographic Mass Segmentation
This work addresses mass segmentation in mammograms for medical imaging analysis, but it is incremental as it builds on existing deep learning and structural learning methods.
The paper tackled mammographic mass segmentation by proposing an end-to-end network combining a fully convolutional network with conditional random fields and adversarial training, achieving state-of-the-art results on INbreast and DDSM-BCRP datasets.
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.