Label-Free Segmentation of COVID-19 Lesions in Lung CT
arXiv:2009.06456
Abstract
Scarcity of annotated images hampers the building of automated solution for reliable COVID-19 diagnosis and evaluation from CT. To alleviate the burden of data annotation, we herein present a label-free approach for segmenting COVID-19 lesions in CT via pixel-level anomaly modeling that mines out the relevant knowledge from normal CT lung scans. Our modeling is inspired by the observation that the parts of tracheae and vessels, which lay in the high-intensity range where lesions belong to, exhibit strong patterns. To facilitate the learning of such patterns at a pixel level, we synthesize `lesions' using a set of surprisingly simple operations and insert the synthesized `lesions' into normal CT lung scans to form training pairs, from which we learn a normalcy-converting network (NormNet) that turns an 'abnormal' image back to normal. Our experiments on three different datasets validate the effectiveness of NormNet, which conspicuously outperforms a variety of unsupervised anomaly detection (UAD) methods.
arXiv commentAccepted by Transaction on Medical Imaging 2021
References in corpus (8)
- Auto-Encoding Variational Bayes
- Review of Artificial Intelligence Techniques in Imaging Data Acquisition, Segmentation and Diagnosis for COVID-19
- Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings
- COVID-CT-Dataset: A CT Scan Dataset about COVID-19
- Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders
- Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Images
- Exploiting Epistemic Uncertainty of Anatomy Segmentation for Anomaly Detection in Retinal OCT
- Viral Pneumonia Screening on Chest X-ray Images Using Confidence-Aware Anomaly Detection