Title |
Fully automated detection and segmentation of meningiomas using deep learning on routine multiparametric MRI
|
---|---|
Published in |
European Radiology, June 2018
|
DOI | 10.1007/s00330-018-5595-8 |
Pubmed ID | |
Authors |
Kai Roman Laukamp, Frank Thiele, Georgy Shakirin, David Zopfs, Andrea Faymonville, Marco Timmer, David Maintz, Michael Perkuhn, Jan Borggrefe |
Abstract |
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. We included 56 of 136 consecutive preoperative MRI datasets [T1/T2-weighted, T1-weighted contrast-enhanced (T1CE), FLAIR] of meningiomas that were treated surgically at the University Hospital Cologne 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. 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. 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. • Deep learning allows for accurate meningioma detection and segmentation • Deep learning helps clinicians to assess patients with meningiomas • Meningioma monitoring and treatment planning can be improved. |
X Demographics
Geographical breakdown
Country | Count | As % |
---|---|---|
United States | 9 | 60% |
Austria | 2 | 13% |
Netherlands | 1 | 7% |
Unknown | 3 | 20% |
Demographic breakdown
Type | Count | As % |
---|---|---|
Practitioners (doctors, other healthcare professionals) | 5 | 33% |
Members of the public | 4 | 27% |
Science communicators (journalists, bloggers, editors) | 4 | 27% |
Scientists | 2 | 13% |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
Unknown | 217 | 100% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Researcher | 28 | 13% |
Student > Master | 24 | 11% |
Student > Bachelor | 20 | 9% |
Student > Ph. D. Student | 18 | 8% |
Other | 12 | 6% |
Other | 36 | 17% |
Unknown | 79 | 36% |
Readers by discipline | Count | As % |
---|---|---|
Medicine and Dentistry | 44 | 20% |
Computer Science | 27 | 12% |
Engineering | 16 | 7% |
Agricultural and Biological Sciences | 7 | 3% |
Neuroscience | 5 | 2% |
Other | 25 | 12% |
Unknown | 93 | 43% |