Artikel
Fully automated detection and segmentation of meningiomas using deep learning on routine multiparametric MRI
Vollautomatische Detektion und Segmentation von Meningiomen durch „deep learning“ an multiparametrischen MRTs
Suche in Medline nach
Autoren
-
Marco Timmer
- University Hospital Cologne, University of Cologne, Neurosurgery, Köln, Deutschland
-
Kai Roman Laukamp
- University Hospital Cologne, University of Cologne, Neurosurgery, Köln, Deutschland
-
Frank Thiele
- University Hospital Cologne, University of Cologne, Neurosurgery, Köln, Deutschland
-
Georgy Shakirin
- University Hospital Cologne, University of Cologne, Neurosurgery, Köln, Deutschland
-
David Zopfs
- University Hospital Cologne, University of Cologne, Neurosurgery, Köln, Deutschland
-
Andrea Faymonville
- University Hospital Cologne, University of Cologne, Neurosurgery, Köln, Deutschland
-
David Maintz
- University Hospital Cologne, University of Cologne, Neurosurgery, Köln, Deutschland
-
Roland Goldbrunner
- University Hospital Cologne, University of Cologne, Neurosurgery, Köln, Deutschland
-
Michael Perkuhn
- University Hospital Cologne, University of Cologne, Neurosurgery, Köln, Deutschland
-
Jan Borggrefe
- University Hospital Cologne, University of Cologne, Neurosurgery, Köln, Deutschland
| Veröffentlicht: | 4. Juni 2021 |
|---|
Gliederung
Text
Objective: Magnetic resonance imaging (MRI) is the method of choice for imaging meningiomas. Volumetric assessment of meningiomas is highly relevant for therapy planning and monitoring. We used a multiparametric deep-learning model (DLM) on routine MRI data including images from diverse referring institutions to investigate DLM performance in automated detection and segmentation of meningiomas in comparison to manual segmentations.
Methods: We included 56 of 136 consecutive preoperative MRI datasets [T1/T2-weighted, T1-weighted contrast-enhanced (T1CE), FLAIR] of meningiomas that were treated surgically and graded histologically as tumour grade I (n = 38) or grade II (n = 18). The DLM was trained on an independent dataset of 249 glioma cases and segmented different tumour classes as defined in the brain tumour image segmentation benchmark (BRATS benchmark). The DLM was based on the DeepMedic architecture. Results were compared to manual segmentations by two radiologists in a consensus reading in FLAIR and T1CE.
Results: The DLM detected meningiomas in 55 of 56 cases. Further, automated segmentations correlated strongly with manual segmentations: average Dice coefficients were 0.81 ± 0.10 (range, 0.46-0.93) for the total tumour volume (union of tumour volume in FLAIR and T1CE) and 0.78 ± 0.19 (range, 0.27-0.95) for contrast-enhancing tumour volume in T1CE.
Conclusion: The DLM yielded accurate automated detection and segmentation of meningioma tissue despite diverse scanner data and thereby may improve and facilitate therapy planning as well as monitoring of this highly frequent tumour entity.
