Tilborghs, S., Dirks, I., Fidon, L., Willems, S., Eelbode, T., Bertels, J., Ilsen, B., Brys, A., Dubbeldam, A., Buls, N., Gonidakis, P., Sánchez, S. A., Snoeckx, A., Parizel, P. M., Mey, J. D., Vandermeulen, D., Vercauteren, T., Robben, D., Smeets, D., ... Suetens, P. (2020). Comparative study of deep learning methods for the automatic segmentation of lung, lesion and lesion type in CT scans of COVID-19 patients. ArXiv. https://doi.org/10.48550/arXiv.2007.15546

@techreport{8638fa49d2fa4ee985176631d72e8b6d,
title = "Comparative study of deep learning methods for the automatic segmentation of lung, lesion and lesion type in CT scans of COVID-19 patients",
abstract = " Recent research on COVID-19 suggests that CT imaging provides useful information to assess disease progression and assist diagnosis, in addition to help understanding the disease. There is an increasing number of studies that propose to use deep learning to provide fast and accurate quantification of COVID-19 using chest CT scans. The main tasks of interest are the automatic segmentation of lung and lung lesions in chest CT scans of confirmed or suspected COVID-19 patients. In this study, we compare twelve deep learning algorithms using a multi-center dataset, including both open-source and in-house developed algorithms. Results show that ensembling different methods can boost the overall test set performance for lung segmentation, binary lesion segmentation and multiclass lesion segmentation, resulting in mean Dice scores of 0.982, 0.724 and 0.469, respectively. The resulting binary lesions were segmented with a mean absolute volume error of 91.3 ml. In general, the task of distinguishing different lesion types was more difficult, with a mean absolute volume difference of 152 ml and mean Dice scores of 0.369 and 0.523 for consolidation and ground glass opacity, respectively. All methods perform binary lesion segmentation with an average volume error that is better than visual assessment by human raters, suggesting these methods are mature enough for a large-scale evaluation for use in clinical practice. ",
keywords = "eess.IV, cs.CV",
author = "Sofie Tilborghs and Ine Dirks and Lucas Fidon and Siri Willems and Tom Eelbode and Jeroen Bertels and Bart Ilsen and Arne Brys and Adriana Dubbeldam and Nico Buls and Panagiotis Gonidakis and S{\'a}nchez, \{Sebasti{\'a}n Amador\} and Annemiek Snoeckx and Parizel, \{Paul M.\} and Mey, \{Johan de\} and Dirk Vandermeulen and Tom Vercauteren and David Robben and Dirk Smeets and Frederik Maes and Jef Vandemeulebroucke and Paul Suetens",
note = "Updated acknowledgments",
year = "2020",
month = jul,
day = "29",
doi = "10.48550/arXiv.2007.15546",
language = "English",
publisher = "ArXiv",
type = "WorkingPaper",
institution = "ArXiv",
}