Multiple Sclerosis Lesion Segmentation from Brain MRI via Fully Convolutional Neural Networks

Multiple Sclerosis (MS) is an autoimmune disease that leads to lesions in the central nervous system. Magnetic resonance (MR) images provide sufficient imaging contrast to visualize and detect lesions, particularly those in the white matter. Quantitative measures based on various features of lesions have been shown to be useful in clinical trials for evaluating therapies. Therefore robust and accurate segmentation of white matter lesions from MR images can provide important information about the disease status and progression. In this paper, we propose a fully convolutional neural network (CNN) based method to segment white matter lesions from multi-contrast MR images. The proposed CNN based method contains two convolutional pathways. The first pathway consists of multiple parallel convolutional filter banks catering to multiple MR modalities. In the second pathway, the outputs of the first one are concatenated and another set of convolutional filters are applied. The output of this last pathway produces a membership function for lesions that may be thresholded to obtain a binary segmentation. The proposed method is evaluated on a dataset of 100 MS patients, as well as the ISBI 2015 challenge data consisting of 14 patients. The comparison is performed against four publicly available MS lesion segmentation methods. Significant improvement in segmentation quality over the competing methods is demonstrated on various metrics, such as Dice and false positive ratio. While evaluating on the ISBI 2015 challenge data, our method produces a score of 90.48, where a score of 90 is considered to be comparable to a human rater.

[1]  A. Oliver,et al.  A toolbox for multiple sclerosis lesion segmentation , 2015, Neuroradiology.

[2]  Haibo He,et al.  Learning from Imbalanced Data , 2009, IEEE Transactions on Knowledge and Data Engineering.

[3]  D. Louis Collins,et al.  Review of automatic segmentation methods of multiple sclerosis white matter lesions on conventional magnetic resonance imaging , 2013, Medical Image Anal..

[4]  Roland G. Henry,et al.  The central vein sign and its clinical evaluation for the diagnosis of multiple sclerosis: a consensus statement from the North American Imaging in Multiple Sclerosis Cooperative , 2016, Nature Reviews Neurology.

[5]  Peter A. Calabresi,et al.  Longitudinal multiple sclerosis lesion segmentation data resource , 2017, Data in brief.

[6]  Christian Barillot,et al.  Adaptive dictionary learning for competitive classification of multiple sclerosis lesions , 2015, 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI).

[7]  Mohammad Havaei,et al.  HeMIS: Hetero-Modal Image Segmentation , 2016, MICCAI.

[8]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Manuel Graña,et al.  Review of Automatic Segmentation Methods of White Matter Lesions on MRI Data , 2016 .

[10]  Sébastien Ourselin,et al.  Bayesian Model Selection for Pathological Neuroimaging Data Applied to White Matter Lesion Segmentation , 2015, IEEE Transactions on Medical Imaging.

[11]  Olivier Clatz,et al.  Spatial Decision Forests for MS Lesion Segmentation in Multi-Channel MR Images , 2010, MICCAI.

[12]  Nick C Fox,et al.  The Alzheimer's disease neuroimaging initiative (ADNI): MRI methods , 2008, Journal of magnetic resonance imaging : JMRI.

[13]  Nico Karssemeijer,et al.  Deep multi-scale location-aware 3D convolutional neural networks for automated detection of lacunes of presumed vascular origin , 2016, NeuroImage: Clinical.

[14]  Roland Opfer,et al.  MRI FLAIR lesion segmentation in multiple sclerosis: Does automated segmentation hold up with manual annotation? , 2016, NeuroImage: Clinical.

[15]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[16]  Paulo Guilherme de Lima Freire,et al.  Automatic iterative segmentation of multiple sclerosis lesions using Student's t mixture models and probabilistic anatomical atlases in FLAIR images , 2016, Comput. Biol. Medicine.

[17]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[18]  M. Viergever,et al.  Automatic Segmentation of MR Brain Images With a Convolutional Neural Network. , 2016, IEEE transactions on medical imaging.

[19]  Koenraad Van Leemput,et al.  Automated segmentation of multiple sclerosis lesions by model outlier detection , 2001, IEEE Transactions on Medical Imaging.

[20]  Peter A. Calabresi,et al.  OASIS is Automated Statistical Inference for Segmentation, with applications to multiple sclerosis lesion segmentation in MRI☆ , 2013, NeuroImage: Clinical.

[21]  Snehashis Roy,et al.  Robust skull stripping using multiple MR image contrasts insensitive to pathology , 2017, NeuroImage.

[22]  Dana Horakova,et al.  Volumetric MRI Markers and Predictors of Disease Activity in Early Multiple Sclerosis: A Longitudinal Cohort Study , 2012, PloS one.

[23]  Bram van Ginneken,et al.  A survey on deep learning in medical image analysis , 2017, Medical Image Anal..

[24]  Grégoire Malandain,et al.  An Automatic Segmentation of T2-FLAIR Multiple Sclerosis Lesions , 2008, The MIDAS Journal.

[25]  Alex Rovira,et al.  Improving automated multiple sclerosis lesion segmentation with a cascaded 3D convolutional neural network approach , 2017, NeuroImage.

[26]  Klaus H. Maier-Hein,et al.  Deep MRI brain extraction: A 3D convolutional neural network for skull stripping , 2016, NeuroImage.

[27]  Amod Jog,et al.  Multi-output decision trees for lesion segmentation in multiple sclerosis , 2015, Medical Imaging.

[28]  Jorge Nocedal,et al.  On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima , 2016, ICLR.

[29]  Peter A. Calabresi,et al.  A topology-preserving approach to the segmentation of brain images with multiple sclerosis lesions , 2010, NeuroImage.

[30]  Sébastien Ourselin,et al.  Bayesian Model Selection for Pathological Data , 2014, MICCAI.

[31]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[32]  Konstantinos Kamnitsas,et al.  Efficient multi‐scale 3D CNN with fully connected CRF for accurate brain lesion segmentation , 2016, Medical Image Anal..

[33]  Saurabh Jain,et al.  Automatic segmentation and volumetry of multiple sclerosis brain lesions from MR images , 2015, NeuroImage: Clinical.

[34]  Lisa Tang,et al.  Deep 3D Convolutional Encoder Networks With Shortcuts for Multiscale Feature Integration Applied to Multiple Sclerosis Lesion Segmentation , 2016, IEEE Transactions on Medical Imaging.

[35]  Snehashis Roy,et al.  Longitudinal Patch-Based Segmentation of Multiple Sclerosis White Matter Lesions , 2015, MLMI.

[36]  Snehashis Roy,et al.  Example based lesion segmentation , 2014, Medical Imaging.

[37]  Shuiwang Ji,et al.  Deep convolutional neural networks for multi-modality isointense infant brain image segmentation , 2015, NeuroImage.

[38]  H. Handels,et al.  Extra Tree forests for sub-acute ischemic stroke lesion segmentation in MR sequences , 2015, Journal of Neuroscience Methods.

[39]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[40]  M. Mohammed Thaha,et al.  Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images , 2019, Journal of Medical Systems.

[41]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[42]  Arno Klein,et al.  A reproducible evaluation of ANTs similarity metric performance in brain image registration , 2011, NeuroImage.

[43]  Hao Chen,et al.  VoxResNet: Deep voxelwise residual networks for brain segmentation from 3D MR images , 2017, NeuroImage.

[44]  Ronald M. Summers,et al.  Deep Learning in Medical Imaging: Overview and Future Promise of an Exciting New Technique , 2016 .

[45]  D. Louis Collins,et al.  Rotation-invariant multi-contrast non-local means for MS lesion segmentation , 2015, NeuroImage: Clinical.

[46]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[47]  Verónica Vilaplana,et al.  3 D Convolutional Networks for Brain Tumor Segmentation , 2016 .

[48]  Snehashis Roy,et al.  Longitudinal multiple sclerosis lesion segmentation: Resource and challenge , 2017, NeuroImage.

[49]  Youngjin Yoo,et al.  Deep Learning of Image Features from Unlabeled Data for Multiple Sclerosis Lesion Segmentation , 2014, MLMI.

[50]  Simon K. Warfield,et al.  A Model of Population and Subject (MOPS) Intensities With Application to Multiple Sclerosis Lesion Segmentation , 2015, IEEE Transactions on Medical Imaging.

[51]  Martin Styner,et al.  Large deep neural networks for MS lesion segmentation , 2017, Medical Imaging.

[52]  Hayit Greenspan,et al.  Longitudinal Multiple Sclerosis Lesion Segmentation Using Multi-view Convolutional Neural Networks , 2016, LABELS/DLMIA@MICCAI.

[53]  Olivier Clatz,et al.  Spatial decision forests for MS lesion segmentation in multi-channel magnetic resonance images , 2011, NeuroImage.

[54]  D. Louis Collins,et al.  Probabilistic Multiple Sclerosis Lesion Classification Based on Modeling Regional Intensity Variability and Local Neighborhood Information , 2015, IEEE Transactions on Biomedical Engineering.

[55]  Brian B. Avants,et al.  N4ITK: Improved N3 Bias Correction , 2010, IEEE Transactions on Medical Imaging.

[56]  D. Louis Collins,et al.  Bayesian MS Lesion Classification Modeling Regional and Local Spatial Information , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[57]  Jian Sun,et al.  Identity Mappings in Deep Residual Networks , 2016, ECCV.

[58]  Arthur W. Toga,et al.  Human brain white matter atlas: Identification and assignment of common anatomical structures in superficial white matter , 2008, NeuroImage.

[59]  Bernhard Hemmer,et al.  An automated tool for detection of FLAIR-hyperintense white-matter lesions in Multiple Sclerosis , 2012, NeuroImage.

[60]  J. Pluim,et al.  Evaluation of a deep learning approach for the segmentation of brain tissues and white matter hyperintensities of presumed vascular origin in MRI , 2017, NeuroImage: Clinical.

[61]  Max A. Viergever,et al.  Deep Learning for Multi-Task Medical Image Segmentation in Multiple Modalities , 2016, MICCAI.

[62]  Thomas Brox,et al.  White Matter MS-Lesion Segmentation Using a Geometric Brain Model , 2016, IEEE Transactions on Medical Imaging.

[63]  Ludovica Griffanti,et al.  BIANCA (Brain Intensity AbNormality Classification Algorithm): A new tool for automated segmentation of white matter hyperintensities , 2016, NeuroImage.

[64]  Christian Wachinger,et al.  DeepNAT: Deep convolutional neural network for segmenting neuroanatomy , 2017, NeuroImage.

[65]  Christos Davatzikos,et al.  Computer-assisted Segmentation of White Matter Lesions in 3d Mr Images Using Support Vector Machine 1 , 2022 .

[66]  Ronald M. Summers,et al.  Improving Computer-Aided Detection Using Convolutional Neural Networks and Random View Aggregation , 2015, IEEE Transactions on Medical Imaging.

[67]  Elena Marchiori,et al.  Location Sensitive Deep Convolutional Neural Networks for Segmentation of White Matter Hyperintensities , 2016, Scientific Reports.

[68]  Aaron Carass,et al.  Simple paradigm for extra-cerebral tissue removal: Algorithm and analysis , 2011, NeuroImage.

[69]  D. Louis Collins,et al.  Trimmed-Likelihood Estimation for Focal Lesions and Tissue Segmentation in Multisequence MRI for Multiple Sclerosis , 2011, IEEE Transactions on Medical Imaging.

[70]  Brian B. Avants,et al.  The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) , 2015, IEEE Transactions on Medical Imaging.

[71]  Daniel S. Reich,et al.  PREVAIL: Predicting Recovery through Estimation and Visualization of Active and Incident Lesions , 2016, NeuroImage: Clinical.

[72]  Snehashis Roy,et al.  Subject Specific Sparse Dictionary Learning for Atlas Based Brain MRI Segmentation , 2014, MLMI.