Label-Free Segmentation of COVID-19 Lesions in Lung CT

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.

[1]  Zhiqiang He,et al.  Towards Efficient COVID-19 CT Annotation: A Benchmark for Lung and Infection Segmentation , 2020, ArXiv.

[2]  Ling Shao,et al.  Inf-Net: Automatic COVID-19 Lung Infection Segmentation From CT Images , 2020, IEEE Transactions on Medical Imaging.

[3]  Richard C. Pais,et al.  The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): a completed reference database of lung nodules on CT scans. , 2011, Medical physics.

[4]  Nassir Navab,et al.  Autoencoders for Unsupervised Anomaly Segmentation in Brain MR Images: A Comparative Study , 2020, Medical Image Anal..

[5]  P. Lambin,et al.  Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach , 2014, Nature Communications.

[6]  Anton van den Hengel,et al.  Deep Anomaly Detection with Deviation Networks , 2019, KDD.

[7]  Q. Tao,et al.  Serial Quantitative Chest CT Assessment of COVID-19: A Deep Learning Approach , 2020, Radiology. Cardiothoracic imaging.

[8]  Klaus H. Maier-Hein,et al.  Context-encoding Variational Autoencoder for Unsupervised Anomaly Detection , 2018, ArXiv.

[9]  Klaus H. Maier-Hein,et al.  Automated Design of Deep Learning Methods for Biomedical Image Segmentation , 2019 .

[10]  Yaozong Gao,et al.  Lung Infection Quantification of COVID-19 in CT Images with Deep Learning , 2020, ArXiv.

[11]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[12]  Ronghua Yan,et al.  Analysis and Recognition of Medical Images: 1. Elastic Deformation Transformation , 1993 .

[13]  Timo Kohlberger,et al.  Multi-stage Learning for Robust Lung Segmentation in Challenging CT Volumes , 2011, MICCAI.

[14]  Alexander Binder,et al.  Deep One-Class Classification , 2018, ICML.

[15]  Ender Konukoglu,et al.  Unsupervised Detection of Lesions in Brain MRI using constrained adversarial auto-encoders , 2018, ArXiv.

[16]  Bo Long,et al.  Deep Learning for Anomaly Detection , 2020, KDD.

[17]  C. Steger,et al.  Uninformed Students: Student-Teacher Anomaly Detection With Discriminative Latent Embeddings , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  S. Kevin Zhou.  Medical Image Recognition, Segmentation and Parsing: Machine Learning and Multiple Object Approaches , 2015 .

[19]  Ender Konukoglu,et al.  Unsupervised Lesion Detection via Image Restoration with a Normative Prior , 2018, MIDL.

[20]  Alexei A. Efros,et al.  Context Encoders: Feature Learning by Inpainting , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Konstantinos Kamnitsas,et al.  Unsupervised Lesion Detection in Brain CT using Bayesian Convolutional Autoencoders , 2018 .

[22]  Hichem Sahli,et al.  Anomaly Detection in Medical Image Analysis , 2009 .

[23]  Yi Li,et al.  Viral Pneumonia Screening on Chest X-ray Images Using Confidence-Aware Anomaly Detection , 2020 .

[24]  Zhiyong Xu,et al.  A Noise-Robust Framework for Automatic Segmentation of COVID-19 Pneumonia Lesions From CT Images , 2020, IEEE Transactions on Medical Imaging.

[25]  Seyed-Ahmad Ahmadi,et al.  Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional Neural Networks and 3D Conditional Random Fields , 2016, MICCAI.

[26]  Mamun Bin Ibne Reaz,et al.  Can AI Help in Screening Viral and COVID-19 Pneumonia? , 2020, IEEE Access.

[27]  Yee Whye Teh,et al.  Do Deep Generative Models Know What They Don't Know? , 2018, ICLR.

[28]  J. Goulet,et al.  POCOVID-Net: Automatic Detection of COVID-19 From a New Lung Ultrasound Imaging Dataset (POCUS) , 2020, ArXiv.

[29]  Nassir Navab,et al.  Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Images , 2018, BrainLes@MICCAI.

[30]  H. Kauczor,et al.  The Role of Chest Imaging in Patient Management during the COVID-19 Pandemic: A Multinational Consensus Statement from the Fleischner Society , 2020, Radiology.

[31]  Georg Langs,et al.  f‐AnoGAN: Fast unsupervised anomaly detection with generative adversarial networks , 2019, Medical Image Anal..

[32]  Yicheng Fang,et al.  Sensitivity of Chest CT for COVID-19: Comparison to RT-PCR , 2020, Radiology.

[33]  Örjan Smedby,et al.  Normal Appearance Autoencoder for Lung Cancer Detection and Segmentation , 2019, MICCAI.

[34]  Wenyu Liu,et al.  A Weakly-Supervised Framework for COVID-19 Classification and Lesion Localization From Chest CT , 2020, IEEE Transactions on Medical Imaging.

[35]  Klaus H. Maier-Hein,et al.  Unsupervised Anomaly Localization using Variational Auto-Encoders , 2019, MICCAI.

[36]  K. Yuen,et al.  Imaging Profile of the COVID-19 Infection: Radiologic Findings and Literature Review , 2020, Radiology. Cardiothoracic imaging.

[37]  Lawrence Carin,et al.  On Deep Learning for Medical Image Analysis. , 2018, JAMA.

[38]  Stephen M. Moore,et al.  The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository , 2013, Journal of Digital Imaging.

[39]  Thomas Brox,et al.  3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation , 2016, MICCAI.

[40]  Daniel A Low,et al.  Computed tomography studies of lung mechanics. , 2005, Proceedings of the American Thoracic Society.

[41]  Svetha Venkatesh,et al.  Memorizing Normality to Detect Anomaly: Memory-Augmented Deep Autoencoder for Unsupervised Anomaly Detection , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[42]  Dinggang Shen,et al.  Review of Artificial Intelligence Techniques in Imaging Data Acquisition, Segmentation, and Diagnosis for COVID-19 , 2020, IEEE Reviews in Biomedical Engineering.

[43]  Chandan Srivastava,et al.  Support Vector Data Description , 2011 .

[44]  Joseph Paul Cohen,et al.  COVID-19 Image Data Collection , 2020, ArXiv.

[45]  Carsten Steger,et al.  Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders , 2018, VISIGRAPP.

[46]  Hongbing Lu,et al.  Prior-Attention Residual Learning for More Discriminative COVID-19 Screening in CT Images , 2020, IEEE Transactions on Medical Imaging.

[47]  P. Xie,et al.  COVID-CT-Dataset: A CT Scan Dataset about COVID-19 , 2020, ArXiv.

[48]  Hayit Greenspan,et al.  Synthetic data augmentation using GAN for improved liver lesion classification , 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[49]  Long Jiang Zhang,et al.  Coronavirus Disease 2019 (COVID-19): A Perspective from China , 2020, Radiology.

[50]  Bo Zong,et al.  Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection , 2018, ICLR.

[51]  Georg Langs,et al.  Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery , 2017, IPMI.

[52]  Christoph Meinel,et al.  Deep Learning for Medical Image Analysis , 2018, Journal of Pathology Informatics.

[53]  P. Horby,et al.  A novel coronavirus outbreak of global health concern , 2020, The Lancet.

[54]  Georg Langs,et al.  Exploiting Epistemic Uncertainty of Anatomy Segmentation for Anomaly Detection in Retinal OCT , 2019, IEEE Transactions on Medical Imaging.

[55]  Jianjiang Feng,et al.  Longitudinal Assessment of COVID-19 Using a Deep Learning–based Quantitative CT Pipeline: Illustration of Two Cases , 2020, Radiology. Cardiothoracic imaging.

[56]  Miguel Cazorla,et al.  BIMCV COVID-19+: a large annotated dataset of RX and CT images from COVID-19 patients , 2020, ArXiv.

[57]  Thomas S. Huang,et al.  One-class SVM for learning in image retrieval , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[58]  Longbing Cao,et al.  Deep Learning for Anomaly Detection: A Review , 2020, ArXiv.

[59]  Yaozong Gao,et al.  Dual-Sampling Attention Network for Diagnosis of COVID-19 From Community Acquired Pneumonia , 2020, IEEE Transactions on Medical Imaging.

[60]  Lihua Li,et al.  A Rapid, Accurate and Machine-Agnostic Segmentation and Quantification Method for CT-Based COVID-19 Diagnosis , 2020, IEEE Transactions on Medical Imaging.

[61]  VARUN CHANDOLA,et al.  Anomaly detection: A survey , 2009, CSUR.