Automated Chest CT Image Segmentation of COVID-19 Lung Infection based on 3D U-Net

TL;DR

This paper presents a robust automated 3D U-Net based segmentation method for COVID-19 lung infection in CT images, effectively handling small datasets through extensive data augmentation and patch-based training.

Contribution

It introduces a novel pipeline that improves COVID-19 lesion segmentation accuracy using standard 3D U-Net and data augmentation, addressing data scarcity issues.

Findings

Achieved Dice score of 0.956 for lungs

Achieved Dice score of 0.761 for infection

Outperforms existing methods in limited data scenarios

Abstract

The coronavirus disease 2019 (COVID-19) affects billions of lives around the world and has a significant impact on public healthcare. Due to rising skepticism towards the sensitivity of RT-PCR as screening method, medical imaging like computed tomography offers great potential as alternative. For this reason, automated image segmentation is highly desired as clinical decision support for quantitative assessment and disease monitoring. However, publicly available COVID-19 imaging data is limited which leads to overfitting of traditional approaches. To address this problem, we propose an innovative automated segmentation pipeline for COVID-19 infected regions, which is able to handle small datasets by utilization as variant databases. Our method focuses on on-the-fly generation of unique and random image patches for training by performing several preprocessing methods and exploiting extensive data augmentation. For further reduction of the overfitting risk, we implemented a standard 3D U-Net architecture instead of new or computational complex neural network architectures. Through a 5-fold cross-validation on 20 CT scans of COVID-19 patients, we were able to develop a highly accurate as well as robust segmentation model for lungs and COVID-19 infected regions without overfitting on the limited data. Our method achieved Dice similarity coefficients of 0.956 for lungs and 0.761 for infection. We demonstrated that the proposed method outperforms related approaches, advances the state-of-the-art for COVID-19 segmentation and improves medical image analysis with limited data. The code and model are available under the following link: https://github.com/frankkramer-lab/covid19.MIScnn