SegAN: Adversarial Network with Multi-scale $L_1$ Loss for Medical Image Segmentation

Abstract

Inspired by classic generative adversarial networks (GAN), 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 $L_1$ 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 takes as input a pair of images, (original_image $\ast$ predicted_label_map, original_image $\ast$ ground_truth_label_map), and then is trained by maximizing a multi-scale loss function; 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.

Cited by in corpus (33)

• GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification
• U-Net and its variants for medical image segmentation: theory and applications
• Generative Adversarial Network in Medical Imaging: A Review
• Recent advances and clinical applications of deep learning in medical image analysis
• CovidGAN: Data Augmentation Using Auxiliary Classifier GAN for Improved Covid-19 Detection
• How Generative Adversarial Networks and Their Variants Work: An Overview
• Anomaly Detection with Generative Adversarial Networks for Multivariate Time Series
• Selective Synthetic Augmentation with HistoGAN for Improved Histopathology Image Classification
• Learning to Segment from Scribbles using Multi-scale Adversarial Attention Gates
• FocusNetv2: Imbalanced Large and Small Organ Segmentation with Adversarial Shape Constraint for Head and Neck CT Images
• Deep and Statistical Learning in Biomedical Imaging: State of the Art in 3D MRI Brain Tumor Segmentation
• Data synthesis and adversarial networks: A review and meta-analysis in cancer imaging
• Class-Aware Adversarial Transformers for Medical Image Segmentation
• Towards Goal-Oriented Semantic Signal Processing: Applications and Future Challenges
• Translating and Segmenting Multimodal Medical Volumes with Cycle- and Shape-Consistency Generative Adversarial Network
• A Transformer-based Generative Adversarial Network for Brain Tumor Segmentation
• Jekyll: Attacking Medical Image Diagnostics using Deep Generative Models
• Exploiting the Generative Adversarial Network Approach to Create a Synthetic Topography Corneal Image
• Brain MRI Tumor Segmentation with Adversarial Networks
• Multi-structure bone segmentation in pediatric MR images with combined regularization from shape priors and adversarial network
• Deep Learning in Medical Ultrasound Image Segmentation: a Review
• SegDiff: Image Segmentation with Diffusion Probabilistic Models
• Multi-organ segmentation: a progressive exploration of learning paradigms under scarce annotation
• A Style-Aware Content Loss for Real-time HD Style Transfer
• Advances in Medical Image Segmentation: A Comprehensive Survey with a Focus on Lumbar Spine Applications
• Semantics-Aware Image to Image Translation and Domain Transfer
• A multi-stage GAN for multi-organ chest X-ray image generation and segmentation
• Nonasymptotic Guarantees for Spiked Matrix Recovery with Generative Priors
• Bayesian Cycle-Consistent Generative Adversarial Networks via Marginalizing Latent Sampling
• Comparing Adversarial and Supervised Learning for Organs at Risk Segmentation in CT images
• ROIsGAN: A Region Guided Generative Adversarial Framework for Murine Hippocampal Subregion Segmentation
• Precise Top-Layer Fabric Segmentation for Fabric Destacking with Edge- and Shape-Aware Deep Networks
• Is Supervised Learning With Adversarial Features Provably Better Than Sole Supervision?