Deep Adversarial Networks for Biomedical Image Segmentation Utilizing Unannotated Images

Semantic segmentation is a fundamental problem in biomedical image analysis. In biomedical practice, it is often the case that only limited annotated data are available for model training. Unannotated images, on the other hand, are easier to acquire. How to utilize unannotated images for training effective segmentation models is an important issue. In this paper, we propose a new deep adversarial network (DAN) model for biomedical image segmentation, aiming to attain consistently good segmentation results on both annotated and unannotated images. Our model consists of two networks: (1) a segmentation network (SN) to conduct segmentation; (2) an evaluation network (EN) to assess segmentation quality. During training, EN is encouraged to distinguish between segmentation results of unannotated images and annotated ones (by giving them different scores), while SN is encouraged to produce segmentation results of unannotated images such that EN cannot distinguish these from the annotated ones. Through an iterative adversarial training process, because EN is constantly “criticizing” the segmentation results of unannotated images, SN can be trained to produce more and more accurate segmentation for unannotated and unseen samples. Experiments show that our proposed DAN model is effective in utilizing unannotated image data to obtain considerably better segmentation.

[1]  Hao Chen,et al.  Gland segmentation in colon histology images: The glas challenge contest , 2016, Medical Image Anal..

[2]  Yang Li,et al.  Gland Instance Segmentation by Deep Multichannel Side Supervision , 2016, MICCAI.

[3]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[4]  George Papandreou,et al.  Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation , 2015, ArXiv.

[5]  Camille Couprie,et al.  Semantic Segmentation using Adversarial Networks , 2016, NIPS 2016.

[6]  Yang Li,et al.  Gland Instance Segmentation by Deep Multichannel Neural Networks , 2016, ArXiv.

[7]  Tapani Raiko,et al.  Semi-supervised Learning with Ladder Networks , 2015, NIPS.

[8]  Marc'Aurelio Ranzato,et al.  Semi-supervised learning of compact document representations with deep networks , 2008, ICML '08.

[9]  George Papandreou,et al.  Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[10]  Hao Chen,et al.  Deep Contextual Networks for Neuronal Structure Segmentation , 2016, AAAI.

[11]  S. C. Suddarth,et al.  Rule-Injection Hints as a Means of Improving Network Performance and Learning Time , 1990, EURASIP Workshop.

[12]  Seunghoon Hong,et al.  Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation , 2015, NIPS.

[13]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[14]  Hao Chen,et al.  DCAN: Deep Contour-Aware Networks for Accurate Gland Segmentation , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[16]  Thomas Brox,et al.  Discriminative Unsupervised Feature Learning with Convolutional Neural Networks , 2014, NIPS.

[17]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.