2018 · 140 citations · 11 references
ComputingComputer ScienceRadiologyComputer VisionDiagnostic ImagingMachine LearningBreast ImagingDeep LearningInstance SegmentationMedical ImagingPattern RecognitionAutomatic SegmentationConditional Random FieldsConvolutional Neural Network SegmentationDeep Learning In RadiologyFully Convolutional NetworksMass DistributionMass Distribution EffectsSegmentation
Mass segmentation provides effective morphological features which are important for mass diagnosis. In this work, we propose a novel end-to-end network for mammographic mass segmentation which employs a fully convolutional network (FCN) to model a potential function, followed by a conditional random field (CRF) to perform structured learning. Because the mass distribution varies greatly with pixel position, the FCN is combined with a position priori. Further, we employ adversarial training to eliminate over-fitting due to the small sizes of mammogram datasets. Multi-scale FCN is employed to improve the segmentation performance. Experimental results on two public datasets, IN breast and DDSM-BCRP, demonstrate that our end-to-end network achieves better performance than state-of-the-art approaches.
11
Fully convolutional networks for semantic segmentation
Jonathan Long, Evan Shelhamer, Trevor Darrell · 2015 · 36.9K citations
Intriguing properties of neural networks
Christian Szegedy, Wojciech Zaremba, Ilya Sutskever et al. · arXiv (Cornell University) · 2013 · 5.7K citations · Full text
Conditional Random Fields as Recurrent Neural Networks
Shuai Zheng, Sadeep Jayasumana, Bernardino Romera‐Paredes et al. · 2015 · 2.4K citations · Full text