GASNet: Weakly-supervised Framework for COVID-19 Lesion Segmentation

Abstract

Segmentation of infected areas in chest CT volumes is of great significance for further diagnosis and treatment of COVID-19 patients. Due to the complex shapes and varied appearances of lesions, a large number of voxel-level labeled samples are generally required to train a lesion segmentation network, which is a main bottleneck for developing deep learning based medical image segmentation algorithms. In this paper, we propose a weakly-supervised lesion segmentation framework by embedding the Generative Adversarial training process into the Segmentation Network, which is called GASNet. GASNet is optimized to segment the lesion areas of a COVID-19 CT by the segmenter, and to replace the abnormal appearance with a generated normal appearance by the generator, so that the restored CT volumes are indistinguishable from healthy CT volumes by the discriminator. GASNet is supervised by chest CT volumes of many healthy and COVID-19 subjects without voxel-level annotations. Experiments on three public databases show that when using as few as one voxel-level labeled sample, the performance of GASNet is comparable to fully-supervised segmentation algorithms trained on dozens of voxel-level labeled samples.

arXiv comment10 pages, 11 figures

References in corpus (14)

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Spectral Normalization for Generative Adversarial Networks
• ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
• Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem
• nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentation
• Task Driven Generative Modeling for Unsupervised Domain Adaptation: Application to X-ray Image Segmentation
• Discriminative Localization in CNNs for Weakly-Supervised Segmentation of Pulmonary Nodules
• MiniSeg: An Extremely Minimum Network for Efficient COVID-19 Segmentation
• When Unseen Domain Generalization is Unnecessary? Rethinking Data Augmentation
• Weakly supervised segmentation from extreme points
• Bounding boxes for weakly supervised segmentation: Global constraints get close to full supervision
• A Weakly Supervised Region-Based Active Learning Method for COVID-19 Segmentation in CT Images
• Learning Diagnosis of COVID-19 from a Single Radiological Image

Cited by in corpus (5)

• Diagnosis/Prognosis of COVID-19 Images: Challenges, Opportunities, and Applications
• Development and evaluation of a 3D annotation software for interactive COVID-19 lesion segmentation in chest CT
• COVID-Rate: An Automated Framework for Segmentation of COVID-19 Lesions from Chest CT Scans
• DACov: A Deeper Analysis of Data Augmentation on the Computed Tomography Segmentation Problem
• Dense Regression Activation Maps For Lesion Segmentation in CT scans of COVID-19 patients