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

09/08/2020
by   Qingsong Yao, et al.
18

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.

READ FULL TEXT

page 1

page 3

page 5

page 7

page 8

page 9

research
07/04/2021

COVID-Rate: An Automated Framework for Segmentation of COVID-19 Lesions from Chest CT Scans

Novel Coronavirus disease (COVID-19) is a highly contagious respiratory ...
research
05/25/2021

CoRSAI: A System for Robust Interpretation of CT Scans of COVID-19 Patients Using Deep Learning

Analysis of chest CT scans can be used in detecting parts of lungs that ...
research
04/07/2017

Automated Unsupervised Segmentation of Liver Lesions in CT scans via Cahn-Hilliard Phase Separation

The segmentation of liver lesions is crucial for detection, diagnosis an...
research
10/27/2022

Full-scale Deeply Supervised Attention Network for Segmenting COVID-19 Lesions

Automated delineation of COVID-19 lesions from lung CT scans aids the di...
research
01/12/2022

ECONet: Efficient Convolutional Online Likelihood Network for Scribble-based Interactive Segmentation

Automatic segmentation of lung lesions associated with COVID-19 in CT im...
research
08/02/2021

Bringing AI pipelines onto cloud-HPC: setting a baseline for accuracy of COVID-19 AI diagnosis

HPC is an enabling platform for AI. The introduction of AI workloads in ...
research
10/30/2018

Soft Activation Mapping of Lung Nodules in Low-Dose CT images

As a popular deep learning model, the convolutional neural network (CNN)...

Please sign up or login with your details

Forgot password? Click here to reset