Perkuhn, Michael, Stavrinou, Pantelis ORCID: 0000-0001-8653-1395, Thiele, Frank, Shakirin, Georgy, Mohan, Manoj, Garmpis, Dionysios, Kabbasch, Christoph and Borggrefe, Jan ORCID: 0000-0003-2908-7560 (2018). Clinical Evaluation of a Multiparametric Deep Learning Model for Glioblastoma Segmentation Using Heterogeneous Magnetic Resonance Imaging Data From Clinical Routine. Invest. Radiol., 53 (11). S. 647 - 655. PHILADELPHIA: LIPPINCOTT WILLIAMS & WILKINS. ISSN 1536-0210

Full text not available from this repository.

Abstract

Objectives: The aims of this study were, first, to evaluate a deep learning-based, automatic glioblastoma (GB) tumor segmentation algorithm on clinical routine data from multiple centers and compare the results to a ground truth, manual expert segmentation, and second, to evaluate the quality of the segmentation results across heterogeneous acquisition protocols of routinely acquired clinical magnetic resonance imaging (MRI) examinations from multiple centers. Materials and Methods: The data consisted of preoperative MRI scans (T1, T2, FLAIR, and contrast-enhanced [CE] T1) of 64 patients with an initial diagnosis of primary GB, which were acquired in 15 institutions with varying protocols. All images underwent preprocessing (coregistration, skull stripping, resampling to isotropic resolution, normalization) and were fed into an independently trained deep learning model based on DeepMedic, a multilayer, multiscale convolutional neural network for detection and segmentation of tumor compartments. Automatic segmentation results for the whole tumor, necrosis, and CE tumor were compared with manual segmentations. Results: Whole tumor and CE tumor compartments were correctly detected in 100% of the cases; necrosis was correctly detected in 91% of the cases. A high segmentation accuracy comparable to interrater variability was achieved for the whole tumor (mean dice similarity coefficient [DSC], 0.86 +/- 0.09) and CE tumor (DSC, 0.78 +/- 0.15). The DSC for tumor necrosis was 0.62 +/- 0.30. We have observed robust segmentation quality over heterogeneous image acquisition protocols, for example, there were no correlations between resolution and segmentation accuracy of the single tumor compartments. Furthermore, no relevant correlation was found between quality of automatic segmentation and volume of interest properties (surface-to-volume ratio and volume). Conclusions: The proposed approach for automatic segmentation of GB proved to be robust on routine clinical data and showed on all tumor compartments a high automatic detection rate and a high accuracy, comparable to interrater variability. Further work on improvements of the segmentation accuracy for the necrosis compartments should be guided by the evaluation of the clinical relevance. Therefore, we propose this approach as a suitable building block for automatic tumor segmentation to support radiologists or neurosurgeons in the preoperative reading of GB MRI images and characterization of primary GB.

Item Type: Journal Article
Creators:
CreatorsEmailORCIDORCID Put Code
Perkuhn, MichaelUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Stavrinou, PantelisUNSPECIFIEDorcid.org/0000-0001-8653-1395UNSPECIFIED
Thiele, FrankUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Shakirin, GeorgyUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Mohan, ManojUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Garmpis, DionysiosUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Kabbasch, ChristophUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Borggrefe, JanUNSPECIFIEDorcid.org/0000-0003-2908-7560UNSPECIFIED
URN: urn:nbn:de:hbz:38-168386
DOI: 10.1097/RLI.0000000000000484
Journal or Publication Title: Invest. Radiol.
Volume: 53
Number: 11
Page Range: S. 647 - 655
Date: 2018
Publisher: LIPPINCOTT WILLIAMS & WILKINS
Place of Publication: PHILADELPHIA
ISSN: 1536-0210
Language: English
Faculty: Unspecified
Divisions: Unspecified
Subjects: no entry
Uncontrolled Keywords:
KeywordsLanguage
BRAIN; RADIOMICSMultiple languages
Radiology, Nuclear Medicine & Medical ImagingMultiple languages
Refereed: Yes
URI: http://kups.ub.uni-koeln.de/id/eprint/16838

Downloads

Downloads per month over past year

Altmetric

Export

Actions (login required)

View Item View Item