TY - JOUR
T1 - Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features
AU - Bakas, Spyridon
AU - Akbari, Hamed
AU - Sotiras, Aristeidis
AU - Bilello, Michel
AU - Rozycki, Martin
AU - Kirby, Justin S.
AU - Freymann, John B.
AU - Farahani, Keyvan
AU - Davatzikos, Christos
N1 - Funding Information:
Martin Rozycki (who did the final QC of the submitted data), Michel Bilello (who validated all manually-revised segmentation labels), Spyridon Bakas, and Christos Davatzikos had full access to all the data in the study and take responsibility for the integrity of the data and the accuracy of the data analysis. The authors would like to thank Dr Gaurav Shukla (Department of Radiation Oncology, Sidney Kimmel Cancer Center, Thomas Jefferson University, Philadelphia, PA, USA) for assisting in the extraction of the radiomic features. Furthermore, the authors would like to acknowledge the effort of Ke Zeng, Saima Rathore, Bilwaj Gaonkar, and Sarthak Pati, who all contributed in successfully developing GLISTRboost. This work was supported in part by the National Institutes of Health (NIH) R01 grant on ‘Predicting brain tumor progression via multiparametric image analysis and modeling’ (R01-NS042645), and in part by the NIH U24 grant of ‘Cancer imaging phenomics software suite: application to brain and breast cancer’ (U24-CA189523).
Publisher Copyright:
© The Author(s) 2017.
PY - 2017/9/5
Y1 - 2017/9/5
N2 - Gliomas belong to a group of central nervous system tumors, and consist of various sub-regions. Gold standard labeling of these sub-regions in radiographic imaging is essential for both clinical and computational studies, including radiomic and radiogenomic analyses. Towards this end, we release segmentation labels and radiomic features for all pre-operative multimodal magnetic resonance imaging (MRI) (n=243) of the multi-institutional glioma collections of The Cancer Genome Atlas (TCGA), publicly available in The Cancer Imaging Archive (TCIA). Pre-operative scans were identified in both glioblastoma (TCGA-GBM, n=135) and low-grade-glioma (TCGA-LGG, n=108) collections via radiological assessment. The glioma sub-region labels were produced by an automated state-of-the-art method and manually revised by an expert board-certified neuroradiologist. An extensive panel of radiomic features was extracted based on the manually-revised labels. This set of labels and features should enable i) direct utilization of the TCGA/TCIA glioma collections towards repeatable, reproducible and comparative quantitative studies leading to new predictive, prognostic, and diagnostic assessments, as well as ii) performance evaluation of computer-aided segmentation methods, and comparison to our state-of-the-art method.
AB - Gliomas belong to a group of central nervous system tumors, and consist of various sub-regions. Gold standard labeling of these sub-regions in radiographic imaging is essential for both clinical and computational studies, including radiomic and radiogenomic analyses. Towards this end, we release segmentation labels and radiomic features for all pre-operative multimodal magnetic resonance imaging (MRI) (n=243) of the multi-institutional glioma collections of The Cancer Genome Atlas (TCGA), publicly available in The Cancer Imaging Archive (TCIA). Pre-operative scans were identified in both glioblastoma (TCGA-GBM, n=135) and low-grade-glioma (TCGA-LGG, n=108) collections via radiological assessment. The glioma sub-region labels were produced by an automated state-of-the-art method and manually revised by an expert board-certified neuroradiologist. An extensive panel of radiomic features was extracted based on the manually-revised labels. This set of labels and features should enable i) direct utilization of the TCGA/TCIA glioma collections towards repeatable, reproducible and comparative quantitative studies leading to new predictive, prognostic, and diagnostic assessments, as well as ii) performance evaluation of computer-aided segmentation methods, and comparison to our state-of-the-art method.
UR - http://www.scopus.com/inward/record.url?scp=85028870080&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85028870080&partnerID=8YFLogxK
U2 - 10.1038/sdata.2017.117
DO - 10.1038/sdata.2017.117
M3 - Article
C2 - 28872634
AN - SCOPUS:85028870080
SN - 2052-4463
VL - 4
JO - Scientific Data
JF - Scientific Data
M1 - 170117
ER -