Kai Laukamp1, Lenhard Pennig1, Frank Thiele1, Robert Reimer1, Lukas Goertz1, David Zopfs1, Georgy Shakirin1, Marco Timmer1, Michael Perkuhn1, and Jan Borggrefe1
1UKK, Cologne, Germany
Synopsis
We trained an established deep-learning-model architecture
(3D-Deep-Convolutional-Neural-Network, DeepMedic) on manual segmentations from
70 meningiomas independently segmented by two radiologists. The trained
deep-learning model was then validated in a group of 55 meningiomas. Ground
truth segmentations were established by two further radiologists in a consensus
reading. In the validation-group the
comparison of the automated deep-learning-model and manual segmentations
revealed average dice-coefficients of 0.91±0.08 for contrast-enhancing-tumor
volume and 0.82±0.12 for total-lesion-volume. In the training-group,
interreader-variabilities of the two manual readers were 0.92±0.07 for
contrast-enhancing-tumor and 0.88±0.05 for total-lesion-volume. Deep-learning
based automated segmentation yielded high segmentation accuracy, comparable to
manual interreader-variability.
INTRODUCTION: Intracranial meningiomas are mostly benign intracranial lesions that
arise from the dura mater and account for approximately 30% of primary
intracranial tumors1–3. Patients that are treated conservatively usually
receive serial follow-up imaging in order to evaluate tumor growth4. Tumor progression pattern is known to be rather
slow, multifocal, and multidirectional. Volumetric evaluation of meningiomas is
therefore superior to traditional diametric methods when assessing tumor growth;
however, it is proven to be time-consuming5,6 and intra- and inter-reader variabilities in brain tumor
segmentation are high, ranging up to 30%7,8.
Technical specifications and segmentation performances of the available
deep-learning models differ7,9.
We hypothesized training an established deep-learning-model architecture
(3D-Deep-Convolutional-Neural-Network, DeepMedic) that already performed well
in brain tumor segmentation9–11 might allow for superior results and save
resources than creating an entirely new deep learning model from scratch. The
objective of our study was to train the above-mentioned architecture on manual meningioma
segmentations and then validate its performance on an independent group of
meningiomas from routine multiparametric MR imaging data.
METHODS: Our retrospective study was approved by the local institutional review
board. Only patients with a complete MR-dataset, consisting of
T1-/T2-weighted, T1-weighted contrast-enhanced [T1CE], and FLAIR as well
as
histopathological specimen were included. The final study population
consisted of 125 patients classified
according to the current World Health Organization (WHO) guideline12.
Patients were split into two groups: (i) training
data for the deep learning model (training-group, n=70) and (ii)
comparison
between manual and automated segmentations (validation group, n=55). MR
images
were acquired on different scanner types (from all major vendors) from
referring institutions (n=86) and our own institution (n=39), ranging
from 1.0
to 3.0 Tesla.
Manual segmentations were performed using IntelliSpace Discovery
(Philips Healthcare). In T1CE, contrast-enhancing tumor was segmented.
In
FLAIR, solid tumor and surrounding edema were segmented. For evaluation,
we applied a previously implemented method11 utilizing the following
defined tumor volumes: (i)
contrast-enhancing-tumor in T1CE and (ii) total-lesion-volume as the
union
of target volumes in T1CE and FLAIR, including solid contrast-enhancing
tumor
parts and surrounding edema. Manual
segmentations in the training group were performed by two radiologists
separately, resulting in two datasets of segmentations for each patient.
To
define optimal ground truth tumor volumes for the validation group, two
additional radiologists segmented tumor volumes in consensus.
DeepMedic-architecture9 was used, including
3D-convolutional-neural-network for segmentation and a
3D-post-processing-step to remove false-positives. For training of the
deep-learning-model, the two sets of manual segmentations from each
reader in
T1CE and FLAIR were used (totaling 140 image sets each including T1CE
and FLAIR
segmentations). For automated segmentation imaging data was
pre-processed
including registration, skull stripping, resampling, and normalization.
The dice-coefficient was used to assess similarity between manual ground
truth segmentations (S1) and automated deep-learning based segmentations
(S2)
and in the validation group, DSC(S1,S2)=(2|S1∩S2|)÷(|S1|+|S2|). The
dice-coefficient was also used to evaluate interreader-variabilities
between
the manual segmentations of the two readers of the training group13.
Wilcoxon signed rank test was used to evaluate any
statistical difference.
RESULTS:
The 125 meningioma patients consisted of 97 WHO grade I meningioma and
28 patients with WHO grade II meningioma.
Training group:
Manual segmentations for contrast-enhancing-tumor averaged 31.5±29.3 cm³ for the first and 31.1±28.9 cm³ for the
second reader as well as 57.4±56.4 cm³ and 59.6±59.2 cm³ for total-lesion-volume. The dice-coefficients were
0.92±0.07 for contrast-enhancing-tumor and 0.88±0.05 for total-lesion-volume.
Validation group:
Manual segmentations were 30.7±25.1 cm³ for contrast-enhancing-tumor
volume and 71.3±66.0 cm³ for total-lesion-volume. Automated segmentations were
comparable without significant differences, being 30.7±24.1 cm³ (p=0.95) in
contrast-enhancing-tumor and 71.4±65.0 cm³ (p=0.94) for total-lesion-volume.
The average dice-coefficients for comparing automated and manual
segmentations were 0.82±0.12 (range: 0.54-0.97) for contrast-enhancing-tumor
and 0.91±0.08 (range: 0.21-0.93) for total-lesion-volume. Automated segmentation performed significantly better
in contrast-enhancing-tumor volume than the total-lesion-volume (0.91±0.08 vs. 0.82±0.12, p<0.001). There was no significant difference in dice-coefficients between
grade I and II meningiomas or between skull base and convexity meningiomas.
DISCUSSION:
Our trained deep-learning-model segmented contrast-enhancing-tumor and total-lesion-volume very
accurately. The accuracy was comparable to the interreader-variabilities of the
two readers from the training group. Further, our results are either comparable
or superior to other recently published studies addressing automated brain
tumor segmentation7,9–11,14–16 and general segmentation accuracies accounting for
intra- and interreader-variabilities7,8.
Reliable automated meningioma
segmentation as demonstrated in our study should relevantly increase
availability of volumetric data as time consuming manual segmentations could be
omitted. Further, automated segmentation should improve reproducibility of measurements7. Accessibility of volumetric data is clinically
warranted for several reasons. Monitoring of conservatively treated meningioma
could be improved as tumor
growth can be detected with higher sensitivity by a volumetric assessment
compared to conventional diameter methods5,6. Image-based tumor
characterization by quantitative image analysis,
e.g. radiomics-based or (deep) machine learning approaches, heavily rely on
volumetric image segmentations7,17–19. Further, extent of peritumoral edema has a decisive
impact on the clinical outcome as well as intraoperative performance.
Assessment of edema by the total-lesion-volume therefore appears warranted20.
CONCLUSION:
Automated meningioma segmentation by our trained deep learning is highly
accurate and produces reliable results, which are comparable to the interreader-variabilities
from manual readers.Acknowledgements
No acknowledgement found.References
1.
DeAngelis LM. Brain tumors. N. Engl. J. Med. 2001;344:114–123.
2. Schob S, Frydrychowicz C, Gawlitza M, et al.
Signal Intensities in Preoperative MRI Do Not Reflect Proliferative Activity in
Meningioma. Transl. Oncol. 2016;9:274–279.
3. Vernooij MW, Ikram MA, Tanghe HL, et al.
Incidental Findings on Brain MRI in the General Population. N. Engl. J. Med.
2007;357:1821–1828.
4. Spasic M, Pelargos PE, Barnette N, et al.
Incidental Meningiomas. Neurosurg. Clin. N. Am. 2016;27:229–238.
5. Chang V, Narang J, Schultz L, et al.
Computer-aided volumetric analysis as a sensitive tool for the management of
incidental meningiomas. Acta Neurochir. (Wien). 2012;154:589–597.
6. Fountain DM, Soon WC, Matys T, et al. Volumetric
growth rates of meningioma and its correlation with histological diagnosis and
clinical outcome: a systematic review. Acta Neurochir. (Wien).
2017;159:435–445.
7. Akkus Z, Galimzianova A, Hoogi A, et al. Deep
Learning for Brain MRI Segmentation: State of the Art and Future Directions. J.
Digit. Imaging. 2017:1–11.
8. Mazzara GP, Velthuizen RP, Pearlman JL, et al. Brain
tumor target volume determination for radiation treatment planning through
automated MRI segmentation. Int. J. Radiat. Oncol. 2004;59:300–312.
9. Kamnitsas K, Ledig C, Newcombe VFJ, et al.
Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion
Segmentation. Med. Image Anal. 2016;36:61–78.
10. Michael Perkuhn PSFTGSMMDGCKJB. Clinical
Evaluation of a Multiparametric Deep Learning Model for Glioblastoma
Segmentation Using Heterogeneous Magnetic Resonance Imaging Data From Clinical
Routine. Invest. Radiol. 2018;53:647–654.
11. Laukamp KR, Thiele F, Shakirin G, et al. Fully
automated detection and segmentation of meningiomas using deep learning on
routine multiparametric MRI. Eur. Radiol. 2018:1–9.
12. Louis DN, Perry A, Reifenberger G, et al. The
2016 World Health Organization Classification of Tumors of the Central Nervous
System: a summary. Acta Neuropathol. 2016;131:803–820.
13. Crum WR, Camara O, Hill DLG. Generalized overlap
measures for evaluation and validation in medical image analysis. IEEE
Trans. Med. Imaging. 2006;25:1451–61.
14. Havaei M, Davy A, Warde-Farley D, et al. Brain
tumor segmentation with Deep Neural Networks. Med. Image Anal.
2017;35:18–31.
15. Farzaneh N, Soroushmehr SMR, Williamson CA, et
al. Automated subdural hematoma segmentation for traumatic brain injured (TBI)
patients. In: 2017 39th Annual International Conference of the IEEE
Engineering in Medicine and Biology Society (EMBC). IEEE; 2017:3069–3072.
16. Zhuge Y, Krauze A V., Ning H, et al. Brain tumor
segmentation using holistically nested neural networks in MRI images. Med.
Phys. 2017;44:5234–5243.
17. Ma D, Gulani V, Seiberlich N, et al. Magnetic
resonance fingerprinting. Nature. 2013;495:187–192.
18. Badve C, Yu A, Dastmalchian S, et al. MR
Fingerprinting of Adult Brain Tumors: Initial Experience. AJNR. Am. J.
Neuroradiol. 2017;38:492–499.
19. Laukamp K, Shakirin G, Baeßler B, et al. Accuracy
of radiomics-based feature analysis on multiparametric MR images for
non-invasive meningioma grading. World Neurosurg. 2019;Ahead of p.
20. Latini F, Larsson E-M, Ryttlefors M. Rapid and
Accurate MRI Segmentation of Peritumoral Brain Edema in Meningiomas. Clin.
Neuroradiol. 2017;27:145–152.