Affordable Access

deepdyve-link
Publisher Website

Development and clinical implementation of tailored image analysis tools for COVID-19 in the midst of the pandemic: The synergetic effect of an open, clinically embedded software development platform and machine learning

Authors
  • Anastasopoulos, Constantin1
  • Weikert, Thomas1
  • Yang, Shan2
  • Abdulkadir, Ahmed3, 4, 5
  • Schmülling, Lena1
  • Bühler, Claudia1
  • Paciolla, Fabiano1
  • Sexauer, Raphael1
  • Cyriac, Joshy2
  • Nesic, Ivan2
  • Twerenbold, Raphael6
  • Bremerich, Jens1
  • Stieltjes, Bram1, 2
  • Sauter, Alexander W.1
  • Sommer, Gregor1
  • 1 Department of Radiology, University Hospital Basel, University of Basel, Basel, Switzerland
  • 2 Department of Research and Analysis, University Hospital Basel, University of Basel, Basel, Switzerland
  • 3 Department of Old Age Psychiatry and Psychotherapy, Universitäre Psychiatrische Dienste Bern (UPD), University of Bern, Bern, Switzerland
  • 4 Center for Biomedical Image Computing and Analytics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
  • 5 Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
  • 6 COVID-19 Research Coordinator, Department of Cardiology, University Hospital Basel, University of Basel, Basel, Switzerland
Type
Published Article
Journal
European Journal of Radiology
Publisher
The Author(s). Published by Elsevier B.V.
Publication Date
Aug 28, 2020
Volume
131
Pages
109233–109233
Identifiers
DOI: 10.1016/j.ejrad.2020.109233
PMID: 32927416
PMCID: PMC7455238
Source
PubMed Central
Keywords
License
Unknown

Abstract

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.

Report this publication

Statistics

Seen <100 times