Deep learning for glioblastoma segmentation using preoperative magnetic resonance imaging identifies volumetric features
- PDF / 1,208,568 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 42 Downloads / 207 Views
ORIGINAL ARTICLE - BRAIN TUMORS
Deep learning for glioblastoma segmentation using preoperative magnetic resonance imaging identifies volumetric features associated with survival Yizhou Wan 1
&
Roushanak Rahmat 1 & Stephen J. Price 1
Received: 29 April 2020 / Accepted: 2 July 2020 # The Author(s) 2020
Abstract Background Measurement of volumetric features is challenging in glioblastoma. We investigate whether volumetric features derived from preoperative MRI using a convolutional neural network–assisted segmentation is correlated with survival. Methods Preoperative MRI of 120 patients were scored using Visually Accessible Rembrandt Images (VASARI) features. We trained and tested a multilayer, multi-scale convolutional neural network on multimodal brain tumour segmentation challenge (BRATS) data, prior to testing on our dataset. The automated labels were manually edited to generate ground truth segmentations. Network performance for our data and BRATS data was compared. Multivariable Cox regression analysis corrected for multiple testing using the false discovery rate was performed to correlate clinical and imaging variables with overall survival. Results Median Dice coefficients in our sample were (1) whole tumour 0.94 (IQR, 0.82–0.98) compared to 0.91 (IQR, 0.83–0.94 p = 0.012), (2) FLAIR region 0.84 (IQR, 0.63–0.95) compared to 0.81 (IQR, 0.69–0.8 p = 0.170), (3) contrast-enhancing region 0.91 (IQR, 0.74–0.98) compared to 0.83 (IQR, 0.78–0.89 p = 0.003) and (4) necrosis region were 0.82 (IQR, 0.47–0.97) compared to 0.67 (IQR, 0.42–0.81 p = 0.005). Contrast-enhancing region/tumour core ratio (HR 4.73 [95% CI, 1.67–13.40], corrected p = 0.017) and necrotic core/tumour core ratio (HR 8.13 [95% CI, 2.06–32.12], corrected p = 0.011) were independently associated with overall survival. Conclusion Semi-automated segmentation of glioblastoma using a convolutional neural network trained on independent data is robust when applied to routine clinical data. The segmented volumes have prognostic significance. Keywords Glioblastoma . Volumetric . Segmentation . MRI . Survival . Deep learning
Abbreviations AIC Akaike information criterion 5-ALA 5-Aminoleuvenic acid ASA American Association of Anesthesiologists BRATS Multimodal brain tumour segmentation challenge CER Contrast-enhancing region
This article is part of the Topical Collection on Brain Tumors Electronic supplementary material The online version of this article (https://doi.org/10.1007/s00701-020-04483-7) contains supplementary material, which is available to authorized users. * Yizhou Wan [email protected] 1
Division of Neurosurgery, Department of Clinical Neurosciences, University of Cambridge, Level 3 A Block Box 165, Cambridge Biomedical Campus, Cambridge CB2 0QQ, UK
CRET CNN EOR FOV FLAIR HR IDH KPS PTE MGMT MRI NC NET OS PACS PRET RTV SVZ
Complete resection of enhancing tumour Convolutional neural network Extent of resection Field of view Fluid attenuated inversion recovery Hazard ratio Isocitrate dehydrogenase Karnofsky Performance Scale Peritumoural oe
Data Loading...
