SegAN: Adversarial Network with Multi-scale L1 Loss for Medical Image Segmentation

By Yuan Xue, Tao Xu, Han Zhang, L. Rodney Long, Xiaolei Huang. Neuroinformatics, 2017

601 citations recorded by the source corpus.

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 L1 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.

Subfields: Computer Vision and Pattern Recognition, Neurology

View Paper: https://www.semanticscholar.org/paper/2d81914c1855f2d2873fd5cc26897330b42c0472

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Neurology

Citations in the corpus

Translating and Segmenting Multimodal Medical Volumes with Cycle- and Shape-Consistency Generative Adversarial Network (2018, methodology): “Apart from synthesizing data, several studies [20, 23, 36, 35] use adversarial learning as an extra supervision on the segmentation or detection networks.”
A survey of deep learning-based network anomaly detection (2017, background): “For instance, generative adversarial network (GAN) has been actively employed to detect anomalies in image data [43,44], but it has not been studied for network anomaly detection in great detail.”
Deep learning based brain tumor segmentation: a survey (2020, background): “[70] proposed an adversarial network with multi-scale L1 loss function called segAN.”
Recent advances and clinical applications of deep learning in medical image analysis (2021, methodology): “Besides the redesigned skip connections and modified architectures, U-Net based segmentation approaches also benefit from adversarial training (Xue et al., 2018; Zhang et al., 2020b), attention mechanism (Jetley et al., 2018; Anderson et al., 2018; Oktay et al., 2018; Nie et al., 2018; Sinha and…”
A Survey on Generative Adversarial Networks: Variants, Applications, and Training (2020, methodology): “tenographic applications [67 - 69], image manipulation applications [70 - 73, 234], visual saliency prediction [74 - 76], object detection [77 - 80], 3D image synthesis [81, 82], medical applications [86, 87], facial makeup transfer [94 - 96], facial landmark d1etection [97, 98], image super-resolut”
Infinite Brain MR Images: PGGAN-based Data Augmentation for Tumor Detection (2019, unknown): “Recently, researchers applied GANs to medical imaging, mainly for imageto-image translation, such as segmentation [25], super-resolution [26], and crossmodality translation [27].”
The History Began from AlexNet: A Comprehensive Survey on Deep Learning Approaches (2018, methodology): “A General medical image segmentation approach is proposed using a GAN called SegAN [217].”
Watch Your Up-Convolution: CNN Based Generative Deep Neural Networks Are Failing to Reproduce Spectral Distributions (2020, background): “…images [29, 6], image-to-image [45, 26, 61, 9, 42, 30] and text-to-image translations [48, 11, 58, 59], style transfer [27, 60, 61, 25], image inpainting [45, 54, 33, 26, 56], transfer learning [5, 10, 15] or even for training semantic segmentation tasks [35, 53], just to name a few.”
CovidGAN: Data Augmentation Using Auxiliary Classifier GAN for Improved Covid-19 Detection (2020, background): “Xue et al. [15] suggested two GAN networks called a Segmentor and a Critic which studied the connection between a binary brain tumor segmentation map and brain MRI pictures.”
U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications (2020, methodology): “rus [159]. Table 1. Applications of U-net based models for MR image analysis. Reference Model/Methods used Brain tumor [106], [107], [110] – [112], [114]– [118] Base U-net [18], [109], [120] 3D U-net [81] Adversarial net; GAN [59], [108] Residual block [113] Dense block [87] Cascaded U-net [92] Resi”
Generative Adversarial Networks for Electronic Health Records: A Framework for Exploring and Evaluating Methods for Predicting Drug-Induced Laboratory Test Trajectories (2017, methodology): “Besides use cases in medical imaging such as SegAN presented by Xue et al. [16] for medical image segmentation, two GANs architectures applied to electronic health records (EHR) stand out: the RCGAN, a Recurrent Conditional GAN capable of generating real-values time series evaluated with supervised…”