Fully automatic GBM segmentation in the TCGA-GBM dataset: Prognosis and correlation with VASARI features

Полностью автоматическая сегментация ГБМ в наборе данных TCGA-GBM: прогнозирование и корреляция с признаками VASARI
David A. Gutman, Roland Wiest, Raphael Meier, Mauricio Reyes, Hugo J.W.L. Aerts, Emmanuel Rios Velazquez, Brian Michael Alexander, William D. Dunn, Stefan Bauer
2015-11-18

BraTumIAGBM segmentationMRI imaging biomarkersTCGA-GBM datasetVASARI features
Reproducible definition and quantification of imaging biomarkers is essential. We evaluated a fully automatic MR-based segmentation method by comparing it to manually defined sub-volumes by experienced radiologists in the TCGA-GBM dataset, in terms of sub-volume prognosis and association with VASARI features. MRI sets of 109 GBM patients were downloaded from the Cancer Imaging archive. GBM sub-compartments were defined manually and automatically using the Brain Tumor Image Analysis (BraTumIA). Spearman's correlation was used to evaluate the agreement with VASARI features. Prognostic significance was assessed using the C-index. Auto-segmented sub-volumes showed moderate to high agreement with manually delineated volumes (range (r): 0.4 - 0.86). Also, the auto and manual volumes showed similar correlation with VASARI features (auto r = 0.35, 0.43 and 0.36; manual r = 0.17, 0.67, 0.41, for contrast-enhancing, necrosis and edema, respectively). The auto-segmented contrast-enhancing volume and post-contrast abnormal volume showed the highest AUC (0.66, CI: 0.55-0.77 and 0.65, CI: 0.54-0.76), comparable to manually defined volumes (0.64, CI: 0.53-0.75 and 0.63, CI: 0.52-0.74, respectively). BraTumIA and manual tumor sub-compartments showed comparable performance in terms of prognosis and correlation with VASARI features. This method can enable more reproducible definition and quantification of imaging based biomarkers and has potential in high-throughput medical imaging research.
1
Automatically and manually segmented tumor volumes demonstrated comparable correlations with VASARI imaging features across contrast-enhancing tumor, necrosis, and edema.
2
Automatically segmented contrast-enhancing and post-contrast abnormal volumes achieved the strongest prognostic discrimination, with AUCs of 0.66 and 0.65, respectively.
3
BraTumIA’s fully automatic MRI segmentation showed moderate-to-high agreement with expert manual GBM sub-volume delineations, with correlations ranging from 0.4 to 0.86.
4
Prognostic performance of automatic segmentation was comparable to manual volumes, whose corresponding AUCs were 0.64 and 0.63.
5
The results support BraTumIA as a reproducible tool for high-throughput imaging biomarker quantification and medical imaging research.

MRI-defined glioblastoma (GBM) tumor sub-compartments in the TCGA-GBM dataset

The agreement, prognostic significance, and association with VASARI imaging features of automatically versus manually segmented GBM sub-volumes

Publication Details
Publication Date
2015-11-18
Journal
Publisher
ISSN
Cited by
96
Access Type
Author Information
Authors
David A. Gutman
Roland Wiest
Raphael Meier
Mauricio Reyes
Hugo J.W.L. Aerts
Emmanuel Rios Velazquez
Brian Michael Alexander
William D. Dunn
Stefan Bauer
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%