| Autor: |
de Vente C; Radboud University Medical Center, Donders Institute for Brain, Cognition and BehaviourDepartment of Medical Imaging6525GANijmegenThe Netherlands.; Informatics Institute, Faculty of ScienceUniversity of Amsterdam 1012 WX Amsterdam The Netherlands., Boulogne LH; Radboud University Medical Center, Radboud Institute for Health SciencesDepartment of Medical Imaging 6525 GA Nijmegen The Netherlands., Venkadesh KV; Radboud University Medical Center, Radboud Institute for Health SciencesDepartment of Medical Imaging 6525 GA Nijmegen The Netherlands., Sital C; Radboud University Medical Center, Radboud Institute for Health SciencesDepartment of Medical Imaging 6525 GA Nijmegen The Netherlands., Lessmann N; Radboud University Medical Center, Radboud Institute for Health SciencesDepartment of Medical Imaging 6525 GA Nijmegen The Netherlands., Jacobs C; Radboud University Medical Center, Radboud Institute for Health SciencesDepartment of Medical Imaging 6525 GA Nijmegen The Netherlands., Sanchez CI; Informatics Institute, Faculty of ScienceUniversity of Amsterdam 1012 WX Amsterdam The Netherlands., van Ginneken B; Radboud University Medical Center, Radboud Institute for Health SciencesDepartment of Medical Imaging 6525 GA Nijmegen The Netherlands. |
| Jazyk: |
angličtina |
| Zdroj: |
IEEE transactions on artificial intelligence [IEEE Trans Artif Intell] 2021 Oct 08; Vol. 3 (2), pp. 129-138. Date of Electronic Publication: 2021 Oct 08 (Print Publication: 2022). |
| DOI: |
10.1109/TAI.2021.3115093 |
| Abstrakt: |
Amidst the ongoing pandemic, the assessment of computed tomography (CT) images for COVID-19 presence can exceed the workload capacity of radiologists. Several studies addressed this issue by automating COVID-19 classification and grading from CT images with convolutional neural networks (CNNs). Many of these studies reported initial results of algorithms that were assembled from commonly used components. However, the choice of the components of these algorithms was often pragmatic rather than systematic and systems were not compared to each other across papers in a fair manner. We systematically investigated the effectiveness of using 3-D CNNs instead of 2-D CNNs for seven commonly used architectures, including DenseNet, Inception, and ResNet variants. For the architecture that performed best, we furthermore investigated the effect of initializing the network with pretrained weights, providing automatically computed lesion maps as additional network input, and predicting a continuous instead of a categorical output. A 3-D DenseNet-201 with these components achieved an area under the receiver operating characteristic curve of 0.930 on our test set of 105 CT scans and an AUC of 0.919 on a publicly available set of 742 CT scans, a substantial improvement in comparison with a previously published 2-D CNN. This article provides insights into the performance benefits of various components for COVID-19 classification and grading systems. We have created a challenge on grand-challenge.org to allow for a fair comparison between the results of this and future research. |
| Databáze: |
MEDLINE |
| Externí odkaz: |
|
