1. |
- Ellingson, Benjamin M., et al.
(författare)
-
Validation of postoperative residual contrast-enhancing tumor volume as an independent prognostic factor for overall survival in newly diagnosed glioblastoma
- 2018
-
Ingår i: Neuro-Oncology. - : OXFORD UNIV PRESS INC. - 1522-8517 .- 1523-5866. ; 20:9, s. 1240-1250
-
Tidskriftsartikel (refereegranskat)abstract
- Background. In the current study, we pooled imaging data in newly diagnosed glioblastoma (GBM) patients from international multicenter clinical trials, single institution databases, and multicenter clinical trial consortiums to identify the relationship between postoperative residual enhancing tumor volume and overall survival (OS). Methods. Data from 1511 newly diagnosed GBM patients from 5 data sources were included in the current study: (i) a single institution database from UCLA (N = 398; Discovery); (ii) patients from the Ben and Cathy Ivy Foundation for Early Phase Clinical Trials Network Radiogenomics Database (N = 262 from 8 centers; Confirmation); (iii) the chemoradiation placebo arm from an international phase III trial (AVAglio; N = 394 from 120 locations in 23 countries; Validation); (iv) the experimental arm from AVAglio examining chemoradiation plus bevacizumab (N = 404 from 120 locations in 23 countries; Exploratory Set 1); and (v) an Alliance (N0874) phase I/II trial of vorinostat plus chemoradiation (N = 53; Exploratory Set 2). Postsurgical, residual enhancing disease was quantified using T1 subtraction maps. Multivariate Cox regression models were used to determine influence of clinical variables, O-6-methylguanine-DNA methyltransferase (MGMT) status, and residual tumor volume on OS. Results. A log-linear relationship was observed between postoperative, residual enhancing tumor volume and OS in newly diagnosed GBM treated with standard chemoradiation. Postoperative tumor volume is a prognostic factor for OS (P < 0.01), regardless of therapy, age, and MGMT promoter methylation status. Conclusion. Postsurgical, residual contrast-enhancing disease significantly negatively influences survival in patients with newly diagnosed GBM treated with chemoradiation with or without concomitant experimental therapy.
|
|
2. |
- Mehta, Raghav, et al.
(författare)
-
QU-BraTS : MICCAI BraTS 2020 Challenge on QuantifyingUncertainty in Brain Tumor Segmentation - Analysis of Ranking Scores and Benchmarking Results
- 2022
-
Ingår i: Journal of Machine Learning for Biomedical Imaging. - 2766-905X. ; , s. 1-54
-
Tidskriftsartikel (refereegranskat)abstract
- Deep learning (DL) models have provided the state-of-the-art performance in a wide variety of medical imaging benchmarking challenges, including the Brain Tumor Segmentation (BraTS) challenges. However, the task of focal pathology multi-compartment segmentation (e.g., tumor and lesion sub-regions) is particularly challenging, and potential errors hinder the translation of DL models into clinical workflows. Quantifying the reliability of DL model predictions in the form of uncertainties, could enable clinical review of the most uncertain regions, thereby building trust and paving the way towards clinical translation. Recently, a number of uncertainty estimation methods have been introduced for DL medical image segmentation tasks. Developing scores to evaluate and compare the performance of uncertainty measures will assist the end-user in making more informed decisions. In this study, we explore and evaluate a score developed during the BraTS 2019-2020 task on uncertainty quantification (QU-BraTS), and designed to assess and rank uncertainty estimates for brain tumor multi-compartment segmentation. This score (1) rewards uncertainty estimates that produce high confidence in correct assertions, and those that assign low confidence levels at incorrect assertions, and (2) penalizes uncertainty measures that lead to a higher percentages of under-confident correct assertions. We further benchmark the segmentation uncertainties generated by 14 independent participating teams of QU-BraTS 2020, all of which also participated in the main BraTS segmentation task. Overall, our findings confirm the importance and complementary value that uncertainty estimates provide to segmentation algorithms, and hence highlight the need for uncertainty quantification in medical image analyses. Our evaluation code is made publicly available at https://github.com/RagMeh11/QU-BraTS
|
|