Boundary Regularized Convolutional Neural Network for Layer Parsing of Breast Anatomy in Automated Whole Breast Ultrasound
A boundary regularized deep convolutional encoder-decoder network (ConvEDNet) is developed in this study to address the difficult anatomical layer parsing problem in the noisy Automated Whole Breast Ultrasound (AWBUS) images. To achieve better network initialization, a two-stage adaptive domain transfer (2DT) is employed to land the VGG-16 encoder on the AWBUS domain with the bridge of network training for AWBUS edge detector. The knowledge transferred encoder is denoted as VGG-USEdge. To further augment the training of ConvEDNet, a deep boundary supervision (DBS) strategy is introduced to regularize the feature learning for better robustness to speckle noise and shadowing effect. We argue that simply counting on the image context cue, which can be learnt with the guidance of label maps, may not be sufficient to deal with the intrinsic noisy property of ultrasound images. With the regularization of boundary cue, the segmentation learning can be boosted. The efficacy of the proposed 2DT-DBS ConvEDNet is corroborated with the extensive comparison to the state-of-the-art deep learning segmentation methods. The segmentation results may assist the clinical image reading, particularly for junior medical doctors and residents and help to reduce false-positive findings from a computer-aided detection scheme.
KeywordsSegmentation Ultrasound Breast Deep learning
This work was supported by the National Natural Science Funds of China (No. 61501305), the Shenzhen Basic Research Project (No. JCYJ20150525092940982), the Natural Science Foundation of SZU (No. 2016089).
- 3.Long, J., et al.: Fully convolutional networks for semantic segmentation. In: CVPR 2015, pp. 3431–3440 (2015)Google Scholar
- 4.Noh, H., et al.: Learning deconvolution network for semantic segmentation. In: ICCV 2015, pp. 1520–1528 (2015)Google Scholar
- 5.Badrinarayanan, V.: Segnet: a deep convolutional encoder-decoder architecture for robust semantic pixel-wise labelling. arXiv preprint arXiv:1505.07293 (2015)
- 7.Lee, C.-Y., et al.: Deeply-Supervised nets. In: AISTATS, 2015, June 2015Google Scholar
- 8.Chen, H., et al.: DCAN: deep contour-aware networks for accurate gland segmentation. In: CVPR 2016, pp. 2487–2496 (2016)Google Scholar
- 9.Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
- 10.Shin, H.-C., et al.: Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE TMI 35, 1285–1298 (2016)Google Scholar
- 11.Xie, S., Tu, Z.: Holistically-nested edge detection. In: ICCV 2015, pp. 1395–1403 (2015)Google Scholar
- 12.Jia, Y., et al.: Caffe: convolutional architecture for fast feature embedding. In: ACM MM 2014, pp. 675–678 (2014)Google Scholar
- 13.Gubern-Merida, A., et al.: Breast segmentation and density estimation in breast MRI: A fully automatic framework. IEEE JBHI 19, 349–357 (2015)Google Scholar
- 14.Huang, Q., et al.: Breast ultrasound image segmentation: a survey. IJCARS 12, 1–5 (2017)Google Scholar