Agata Sularz1, Fulvio Zaccagna1, Dimitri A Kessler1, Fraser Tonnard1, Sonia Benitez1, Thomas Santarius2, Fiona J Gilbert1, Tomasz Matys1, and Joshua D Kaggie1
1Department of Radiology, University of Cambridge, Cambridge, United Kingdom, 2Department of Neurosurgery, University of Cambridge, Cambridge, United Kingdom
Synopsis
We
describe a deep learning method for fully-automated brain meningioma
MRI segmentation. A conditional generative adversarial network (cGAN)
was trained on T1 contrast-enhanced (T1ce) MRI of 37 patients. We
explored the effect of batch size, transfer learning and histogram
equalization on segmentation accuracy. The
highest results for
T1ce images were
achieved for meningioma dataset of
batch size = 1
(DSC
= 0.347).
Histogram
equalization improved segmentation accuracy for
batch size =
1 (DSC
= 0.364) and batch size
= 200. Transfer
learning on a publicly available glioma dataset did not improve
segmentation
results.
Introduction
Meningiomas
are slow-growing tumours arising from arachnoidal cells within
meninges covering the brain and spinal cord. Meningiomas
are most commonly benign and asymptomatic for many years before they
cause
symptoms. Magnetic resonance imaging (MRI) is the preferred modality
for diagnosis due to its
high soft-tissue contrast1.
Specific
measurements (e.g. tumour volume) are useful for monitoring
meningioma
growth and treatment planning1.
This information is obtained through the laborious and often
error-prone process of manual image segmentation. Fully-automated
solutions have been developed to improve segmentation efficiency2,3.
Deep learning approaches such
as convolutional neural
networks have been used in meningioma segmentation4
but are limited by the need to determine an effective loss function.
The use of two competing neural networks (i.e. generative adversarial
networks—GANs) facilitates
this process.
We
investigate the use of a conditional GAN (cGAN) for automated
intracranial
meningioma MRI segmentation, and explore the utility of transferring
weights determined from Multimodal Brain Tumour Segmentation
Challenge (BRATS) 2018
training
for improving this task5,6.Methods
Network
architecture: A cGAN7
was used within PyTorch (Torch v0.5, CUDA v9.0) using an
NVIDIA Quadro P6000 GPU. The cGAN creates
an image through
a generator network, and
a discriminator network determines if it is ‘real’ or ‘fake’.
Images
are generated from
typically random noise and receives additional image information as
input. The “pix2pix”
framework8
(a combined
U-Net generator and Markov Random Field-like
discriminator)
was used to generate
images indistinguishable from a target image (tumour segmentation).
The discriminator performed a patch-wise (64 x 64) classification and
then averaged all patches to create a binary output indicating
whether the generated image was more ‘fake’ or ‘real’ than
noise fed into the generator. To reduce blurring and ensure
low-frequency correctness, the L1 distance is incorporated into the
loss function of the cGAN8.
Datasets:
Meningioma
dataset: Contrast-enhanced T1 brain MR images were obtained from 37
patients on
1.5 and 3.0T MRI systems from
2010 to
2018.
Lesion masks were
segmented manually by trained radiologists.
BRATS 2018 dataset:
Contrast-enhanced T1 brain images with segmentation masks were
obtained from a publicly available database5,6.
MRI for low-grade (n = 75) and high-grade (n = 210) gliomas
were used.
Training:
Each network was trained for 100 epochs. Initially, separate
trainings were run on the meningioma and BRATS datasets. For BRATS
training, networks were trained on low, high and mixed grade MRI.
Patients for the mixed BRATS dataset were randomly selected to
achieve similar number of slices with high-grade and low-grade
gliomas. As batch normalization is
a feature of “pix2pix”9,
the effect of batch size
on cGAN performance was studied. Training
batch sizes of 1, 10, 100 and 200 were compared for
each dataset. Given the
large variation in image quality and contrast within datasets, the
effects of image pre-processing
through histogram equalization was explored. Histogram equalization
was performed in Python 3 using the scikit-image package. For
transfer learning, networks were pre-trained on BRATS-trained
networks (batch
size = 100, low-grade, high-grade and mixed, both original and
histogram equalized) and
network fine-tuning was performed on the meningioma training dataset
(batch
size = 1).
Testing:
Dice-Sorensen coefficient (DSC) and Jaccard Index (JI) were used to
evaluate segmentation accuracy.
Table
1 shows the number of 2D
slices in each training and testing dataset.Results
Table
2 shows DSC and JI training
results. Figure
1 and 2
show selected segmentation images. Without histogram equalization,
the highest
DSC results were achieved for batch size = 1
(DSC
= 0.347 ) in
the meningioma dataset, batch size = 100 for high
grade (DSC = 0.564) and
low-grade (DSC = 0.474), and
batch size = 200 for mixed
(DSC = 0.468) BRATS
datasets. Histogram
equalization improved segmentation accuracy for meningioma (batch
size = 1
and 200), low-grade
BRATS (all batch sizes),
high-grade BRATS (batch size = 1) and mixed BRATS (batch sizes = 1
and
10) training. The
largest
improvement with histogram equalization was seen for low-grade glioma
(batch size = 1, from DSC = 0.285 to DSC = 0.579).Discussion
This
work explored how different characteristics of a 2D cGAN training
affect brain meningioma
automated segmentation accuracy.
We found that both batch size = 1 and batch size = 100 showed best
results for meningioma and BRATS datasets testing, respectively.
Histogram equalization improved learning in meningioma and low and
mixed grade datasets. Network pre-training on glioma BRATS dataset
did not improve meningioma segmentation results. This might be due to
differences between the source images, segmentation objective and
disease pathophysiology. We predict that further work to increase the
number of training masks (local meningioma dataset) as well as image
processing (skull stripping4)
will allow better training and achieve higher segmentation accuracy.
We expect improved results with the application of 3D cGANs, which
have been shown to obtain higher DSCs4,
but also would be
more difficult to apply
to routine MRI that includes 2D imaging.Conclusion
We
found better
brain
meningioma MRI segmentation
accuracy with
1) smaller batch sizes for smaller datasets and 2) image
pre-processing
with histogram equalization. Mixed
trends in our results suggest that specific
parameters
of a network
training
should
be
tailored to the particular
characteristics
of
the target dataset.Acknowledgements
This
work was supported by the National Institute of Health Research
Cambridge Biomedical Research Centre, Addenbrooke’s
Charitable Trust and
GlaxoSmithKline.References
1.
Nowosielski M, Galldiks N, Iglseder S, et al. Diagnostic challenges
in meningioma. Neuro
Oncol
2017; 19: 1588–1598.
2.
Kaus MR, Warfield SK, Nabavi A, et al. Segmentation of meningiomas
and low grade gliomas in MRI. Lect Notes Comput Sci (including
Subser Lect Notes Artif Intell Lect Notes Bioinformatics) 1999;
1679: 1–10.
3.
Kaus MR, Warfield SK, Nabavi A, et al. Automated segmentation of MR
images of brain tumors. Radiology 2001; 218: 586–591.
4.
Laukamp KR, Thiele F, Shakirin G, et al. Fully automated detection
and segmentation of meningiomas using deep learning on routine
multiparametric MRI. Eur Radiol 2019; 29: 124–132.
5.
Crimi
A, Bakas S, Kuijf H, Menze B, Reyes M. Brainlesion: Glioma.
InMultiple Sclerosis, Stroke and Traumatic Brain Injuries. In: Third
International Workshop, BrainLes 2017.
6.
Menze BH, Jakab A, Bauer S, et al. The Multimodal Brain Tumor Image
Segmentation Benchmark (BRATS). IEEE Trans Med Imaging 2015;
34: 1993–2024.
7.
Mirza
M, Osindero S. Conditional generative adversarial nets. arXiv
preprint arXiv:1411.1784. 2014 Nov 6.
8.
Isola P, Zhu JY, Zhou T, et al. Image-to-image translation with
conditional adversarial networks. In: Proceedings - 30th IEEE
Conference on Computer Vision and Pattern Recognition, CVPR 2017.
Institute of Electrical and Electronics Engineers Inc., 2017, pp.
5967–5976.
9.
Ioffe S, Szegedy C. Batch normalization: Accelerating deep network
training by reducing internal covariate shift. 32nd
Int Conf Mach Learn ICML 2015
2015; 1: 448–456.