Brain extraction from normal and pathological images: A joint PCA/Image-Reconstruction approach

ABSTRACT Brain extraction from 3D medical images is a common pre‐processing step. A variety of approaches exist, but they are frequently only designed to perform brain extraction from images without strong pathologies. Extracting the brain from images exhibiting strong pathologies, for example, the presence of a brain tumor or of a traumatic brain injury (TBI), is challenging. In such cases, tissue appearance may substantially deviate from normal tissue appearance and hence violates algorithmic assumptions for standard approaches to brain extraction; consequently, the brain may not be correctly extracted. This paper proposes a brain extraction approach which can explicitly account for pathologies by jointly modeling normal tissue appearance and pathologies. Specifically, our model uses a three‐part image decomposition: (1) normal tissue appearance is captured by principal component analysis (PCA), (2) pathologies are captured via a total variation term, and (3) the skull and surrounding tissue is captured by a sparsity term. Due to its convexity, the resulting decomposition model allows for efficient optimization. Decomposition and image registration steps are alternated to allow statistical modeling of normal tissue appearance in a fixed atlas coordinate system. As a beneficial side effect, the decomposition model allows for the identification of potentially pathological areas and the reconstruction of a quasi‐normal image in atlas space. We demonstrate the effectiveness of our approach on four datasets: the publicly available IBSR and LPBA40 datasets which show normal image appearance, the BRATS dataset containing images with brain tumors, and a dataset containing clinical TBI images. We compare the performance with other popular brain extraction models: ROBEX, BEaST, MASS, BET, BSE and a recently proposed deep learning approach. Our model performs better than these competing approaches on all four datasets. Specifically, our model achieves the best median (97.11) and mean (96.88) Dice scores over all datasets. The two best performing competitors, ROBEX and MASS, achieve scores of 96.23/95.62 and 96.67/94.25 respectively. Hence, our approach is an effective method for high quality brain extraction for a wide variety of images. HIGHLIGHTSBrain extraction on normal and abnormal datasets with high accuracy.Quasi‐normal image estimation and pathology identification in atlas space.Available as open‐source software.

[1]  Y. Benjamini,et al.  Controlling the false discovery rate: a practical and powerful approach to multiple testing , 1995 .

[2]  Richard M. Leahy,et al.  BrainSuite: An Automated Cortical Surface Identification Tool , 2000, MICCAI.

[3]  Nassir Navab,et al.  Guiding multimodal registration with learned optimization updates , 2017, Medical Image Anal..

[4]  Richard L. Van Metter,et al.  Handbook of Medical Imaging , 2009 .

[5]  L. Rudin,et al.  Nonlinear total variation based noise removal algorithms , 1992 .

[6]  Milan Sonka,et al.  "Handbook of Medical Imaging, Volume 2. Medical Image Processing and Analysis " , 2000 .

[7]  John Wright,et al.  Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Matrices via Convex Optimization , 2009, NIPS.

[8]  Sébastien Ourselin,et al.  Global image registration using a symmetric block-matching approach , 2014, Journal of medical imaging.

[9]  Alan C. Evans,et al.  A nonparametric method for automatic correction of intensity nonuniformity in MRI data , 1998, IEEE Transactions on Medical Imaging.

[10]  Paul M. Thompson,et al.  Robust Brain Extraction Across Datasets and Comparison With Publicly Available Methods , 2011, IEEE Transactions on Medical Imaging.

[11]  Xu Han,et al.  Registration of Pathological Images , 2016, SASHIMI@MICCAI.

[12]  Arthur W. Toga,et al.  Construction of a 3D probabilistic atlas of human cortical structures , 2008, NeuroImage.

[13]  Stephen M Smith,et al.  Fast robust automated brain extraction , 2002, Human brain mapping.

[14]  Luis Ibáñez,et al.  The Design of SimpleITK , 2013, Front. Neuroinform..

[15]  Kevin Skadron,et al.  Scalable parallel programming , 2008, 2008 IEEE Hot Chips 20 Symposium (HCS).

[16]  Isaac N. Bankman,et al.  Handbook of medical imaging , 2000 .

[17]  A. M. Dale,et al.  A hybrid approach to the skull stripping problem in MRI , 2004, NeuroImage.

[18]  Bilwaj Gaonkar,et al.  Multi-atlas skull-stripping. , 2013, Academic radiology.

[19]  Mark W. Woolrich,et al.  FSL , 2012, NeuroImage.

[20]  Timothy F. Cootes,et al.  Active Appearance Models , 1998, ECCV.

[21]  Sébastien Ourselin,et al.  Fast free-form deformation using graphics processing units , 2010, Comput. Methods Programs Biomed..

[22]  Chris Rorden,et al.  Spatial Normalization of Brain Images with Focal Lesions Using Cost Function Masking , 2001, NeuroImage.

[23]  C. Almli,et al.  Unbiased nonlinear average age-appropriate brain templates from birth to adulthood , 2009, NeuroImage.

[24]  Xu Han,et al.  Efficient registration of pathological images: A joint PCA/image-reconstruction approach , 2017, 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017).

[26]  R. Leahy,et al.  Magnetic Resonance Image Tissue Classification Using a Partial Volume Model , 2001, NeuroImage.

[27]  R W Cox,et al.  AFNI: software for analysis and visualization of functional magnetic resonance neuroimages. , 1996, Computers and biomedical research, an international journal.

[28]  Irina Voiculescu,et al.  An Overview of Current Evaluation Methods Used in Medical Image Segmentation , 2015 .

[29]  Christos Davatzikos,et al.  Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features , 2017, Scientific Data.

[30]  Ciprian M. Crainiceanu,et al.  Validated automatic brain extraction of head CT images , 2015, NeuroImage.

[31]  D. Louis Collins,et al.  BEaST: Brain extraction based on nonlocal segmentation technique , 2012, NeuroImage.

[32]  Zhuowen Tu,et al.  Robust Skull Stripping of Clinical Glioblastoma Multiforme Data , 2011, MICCAI.

[33]  Anders M. Dale,et al.  A hybrid approach to the Skull Stripping problem in MRI , 2001, NeuroImage.

[34]  W. Nitz,et al.  MP RAGE: a three-dimensional, T1-weighted, gradient-echo sequence--initial experience in the brain. , 1992, Radiology.

[35]  Marc Niethammer,et al.  Low-Rank Atlas Image Analyses in the Presence of Pathologies , 2015, IEEE Transactions on Medical Imaging.

[36]  John G. Csernansky,et al.  Open Access Series of Imaging Studies (OASIS): Cross-sectional MRI Data in Young, Middle Aged, Nondemented, and Demented Older Adults , 2007, Journal of Cognitive Neuroscience.

[37]  Danielle F. Pace,et al.  Geometric Metamorphosis , 2011, MICCAI.

[38]  P. Mahalanobis On the generalized distance in statistics , 1936 .

[39]  Marc Niethammer,et al.  Quicksilver: Fast predictive image registration – A deep learning approach , 2017, NeuroImage.

[40]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

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

[42]  Stephen R. Aylward,et al.  Low-Rank to the Rescue - Atlas-Based Analyses in the Presence of Pathologies , 2014, MICCAI.

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

[44]  Xiaoming Yuan,et al.  Adaptive Primal-Dual Hybrid Gradient Methods for Saddle-Point Problems , 2013, 1305.0546.

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