Development and clinical implementation of tailored image analysis tools for COVID-19 in the midst of the pandemic

TY - JOUR

T1 - Development and clinical implementation of tailored image analysis tools for COVID-19 in the midst of the pandemic

T2 - The synergetic effect of an open, clinically embedded software development platform and machine learning

AU - Anastasopoulos, Constantin

AU - Weikert, Thomas

AU - Yang, Shan

AU - Abdulkadir, Ahmed

AU - Schmülling, Lena

AU - Bühler, Claudia

AU - Paciolla, Fabiano

AU - Sexauer, Raphael

AU - Cyriac, Joshy

AU - Nesic, Ivan

AU - Twerenbold, Raphael

AU - Bremerich, Jens

AU - Stieltjes, Bram

AU - Sauter, Alexander W

AU - Sommer, Gregor

N1 - Copyright © 2020 The Author(s). Published by Elsevier B.V. All rights reserved.

PY - 2020/10

Y1 - 2020/10

N2 - PURPOSE: During the emerging COVID-19 pandemic, radiology departments faced a substantial increase in chest CT admissions coupled with the novel demand for quantification of pulmonary opacities. This article describes how our clinic implemented an automated software solution for this purpose into an established software platform in 10 days. The underlying hypothesis was that modern academic centers in radiology are capable of developing and implementing such tools by their own efforts and fast enough to meet the rapidly increasing clinical needs in the wake of a pandemic.METHOD: Deep convolutional neural network algorithms for lung segmentation and opacity quantification on chest CTs were trained using semi-automatically and manually created ground-truth (Ntotal = 172). The performance of the in-house method was compared to an externally developed algorithm on a separate test subset (N = 66).RESULTS: The final algorithm was available at day 10 and achieved human-like performance (Dice coefficient = 0.97). For opacity quantification, a slight underestimation was seen both for the in-house (1.8 %) and for the external algorithm (0.9 %). In contrast to the external reference, the underestimation for the in-house algorithm showed no dependency on total opacity load, making it more suitable for follow-up.CONCLUSIONS: The combination of machine learning and a clinically embedded software development platform enabled time-efficient development, instant deployment, and rapid adoption in clinical routine. The algorithm for fully automated lung segmentation and opacity quantification that we developed in the midst of the COVID-19 pandemic was ready for clinical use within just 10 days and achieved human-level performance even in complex cases.

AB - PURPOSE: During the emerging COVID-19 pandemic, radiology departments faced a substantial increase in chest CT admissions coupled with the novel demand for quantification of pulmonary opacities. This article describes how our clinic implemented an automated software solution for this purpose into an established software platform in 10 days. The underlying hypothesis was that modern academic centers in radiology are capable of developing and implementing such tools by their own efforts and fast enough to meet the rapidly increasing clinical needs in the wake of a pandemic.METHOD: Deep convolutional neural network algorithms for lung segmentation and opacity quantification on chest CTs were trained using semi-automatically and manually created ground-truth (Ntotal = 172). The performance of the in-house method was compared to an externally developed algorithm on a separate test subset (N = 66).RESULTS: The final algorithm was available at day 10 and achieved human-like performance (Dice coefficient = 0.97). For opacity quantification, a slight underestimation was seen both for the in-house (1.8 %) and for the external algorithm (0.9 %). In contrast to the external reference, the underestimation for the in-house algorithm showed no dependency on total opacity load, making it more suitable for follow-up.CONCLUSIONS: The combination of machine learning and a clinically embedded software development platform enabled time-efficient development, instant deployment, and rapid adoption in clinical routine. The algorithm for fully automated lung segmentation and opacity quantification that we developed in the midst of the COVID-19 pandemic was ready for clinical use within just 10 days and achieved human-level performance even in complex cases.

KW - Betacoronavirus

KW - COVID-19

KW - Coronavirus Infections/diagnostic imaging

KW - Humans

KW - Machine Learning

KW - Neural Networks, Computer

KW - Pandemics

KW - Pneumonia, Viral/diagnostic imaging

KW - SARS-CoV-2

KW - Software

KW - Tomography, X-Ray Computed/methods

U2 - 10.1016/j.ejrad.2020.109233

DO - 10.1016/j.ejrad.2020.109233

M3 - SCORING: Journal article

C2 - 32927416

VL - 131

JO - EUR J RADIOL

JF - EUR J RADIOL

SN - 0720-048X

M1 - 109233

ER -