Data belonging to Predicting the 1p/19q co-deletion status of presumed low grade glioma with an externally validated machine learning algorithm

Published: 10-07-2020| Version 3 | DOI: 10.17632/rssf5nxxby.3
Contributors:
Sebastian van der Voort,
Fatih Incekara,
Maarten Wijnenga,
Georgios Kapas,
Mayke Gardeniers,
Joost Schouten,
Martijn Starmans,
Rishie Nandoe Tewarie,
Geert Lycklama,
Pim French,
Hendrikus Dubbink,
Martin van den Bent,
Arnaud Vincent,
Wiro Niessen,
Stefan Klein,
Marion Smits

Description

Data belonging to the 'Predicting the 1p/19q co-deletion status of presumed low grade glioma with an externally validated machine learning algorithm' paper, as publisched in Clinical Cancer Research. When using this data please cite: Predicting the 1p/19q Codeletion Status of Presumed Low-Grade Glioma with an Externally Validated Machine Learning Algorithm. Sebastian R. van der Voort, Fatih Incekara, Maarten M.J. Wijnenga, Georgios Kapas, Mayke Gardeniers, Joost W. Schouten, Martijn P.A. Starmans, Rishie Nandoe Tewarie, Geert J. Lycklama, Pim J. French, Hendrikus J. Dubbink, Martin J. van den Bent, Arnaud J.P.E. Vincent, Wiro J. Niessen, Stefan Klein and Marion Smits. Clin Cancer Res December 15 2019 (25) (24) 7455-7462; DOI: 10.1158/1078-0432.CCR-19-1127 Data includes trained SVM models, image features derived for all patients, labels for all patients, PCE models used to derive feature importance and segmentations made for the LGG-1p19qDeletion dataset from The Cancer Imaging Archive (https://wiki.cancerimagingarchive.net/display/Public/LGG-1p19qDeletion#a888d85b04c640eeaf802e12db2dc8ad)

Files

Steps to reproduce

Feature files and trained models can be used by PREDICT (https://github.com/Svdvoort/PREDICT), or can be loaded using sklearn and hdf5.