Reference : On the Composition and Limitations of Publicly Available COVID-19 X-Ray Imaging Datasets
E-prints/Working papers : Already available on another site
Engineering, computing & technology : Multidisciplinary, general & others
Systems Biomedicine; Computational Sciences
http://hdl.handle.net/10993/44138
On the Composition and Limitations of Publicly Available COVID-19 X-Ray Imaging Datasets
English
Garcia Santa Cruz, Beatriz mailto [University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB) > >]
Sölter, Jan mailto [University of Luxembourg > > >]
Bossa, Matias Nicolas mailto [University of Luxembourg > > >]
Husch, Andreas mailto [University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB) > >]
26-Aug-2020
1
12
No
[en] COVID-19 ; Machine Learning ; Computer Vision
[en]  Machine learning based methods for diagnosis and progression prediction of COVID-19 from imaging data have gained significant attention in the last months, in particular by the use of deep learning models. In this context hundreds of models where proposed with the majority of them trained on public datasets. Data scarcity, mismatch between training and target population, group imbalance, and lack of documentation are important sources of bias, hindering the applicability of these models to real-world clinical practice. Considering that datasets are an essential part of model building and evaluation, a deeper understanding of the current landscape is needed. This paper presents an overview of the currently public available COVID-19 chest X-ray datasets. Each dataset is briefly described and potential strength, limitations and interactions between datasets are identified. In particular, some key properties of current datasets that could be potential sources of bias, impairing models trained on them are pointed out. These descriptions are useful for model building on those datasets, to choose the best dataset according the model goal, to take into account the specific limitations to avoid reporting overconfident benchmark results, and to discuss their impact on the generalisation capabilities in a specific clinical setting.
COVID-19/2020-1/14702831/AICovIX/Husch
Researchers ; Professionals ; Students
http://hdl.handle.net/10993/44138
https://arxiv.org/abs/2008.11572

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
On_the_composition_and_limitations_of_publicly_available_covid19_x_ray_imaging_datasets.pdfPublisher postprint739.91 kBView/Open

Bookmark and Share SFX Query

All documents in ORBilu are protected by a user license.