SegAN: Adversarial Network with Multi-scale L 1 Loss for Medical Image Segmentation

• Published in: Neuroinformatics (Totowa, N.J.) Vol. 16; no. 3-4; pp. 383 - 392
• Main Authors: Xue, Yuan, Xu, Tao, Zhang, Han, Long, L Rodney, Huang, Xiaolei
• Format: Journal Article
• Language: English
• Published: United States Springer Nature B.V 01.10.2018
• Subjects: Brain tumors; Image processing; Neural networks; Segmentation
• ISSN: 1539-2791; 1559-0089
• DOI: 10.1007/s12021-018-9377-x

Inspired by classic Generative Adversarial Networks (GANs), we propose a novel end-to-end adversarial neural network, called SegAN, for the task of medical image segmentation. Since image segmentation requires dense, pixel-level labeling, the single scalar real/fake output of a classic GAN's discriminator may be ineffective in producing stable and sufficient gradient feedback to the networks. Instead, we use a fully convolutional neural network as the segmentor to generate segmentation label maps, and propose a novel adversarial critic network with a multi-scale L loss function to force the critic and segmentor to learn both global and local features that capture long- and short-range spatial relationships between pixels. In our SegAN framework, the segmentor and critic networks are trained in an alternating fashion in a min-max game: The critic is trained by maximizing a multi-scale loss function, while the segmentor is trained with only gradients passed along by the critic, with the aim to minimize the multi-scale loss function. We show that such a SegAN framework is more effective and stable for the segmentation task, and it leads to better performance than the state-of-the-art U-net segmentation method. We tested our SegAN method using datasets from the MICCAI BRATS brain tumor segmentation challenge. Extensive experimental results demonstrate the effectiveness of the proposed SegAN with multi-scale loss: on BRATS 2013 SegAN gives performance comparable to the state-of-the-art for whole tumor and tumor core segmentation while achieves better precision and sensitivity for Gd-enhance tumor core segmentation; on BRATS 2015 SegAN achieves better performance than the state-of-the-art in both dice score and precision.