DEEPMIR: A DEEP convolutional neural network for differential detection of cerebral Microbleeds and IRon deposits in MRI

Background: Cerebral microbleeds (CMBs) and non-hemorrhage iron deposits in the basal ganglia have been associated with brain aging, vascular disease and neurodegenerative disorders. Recent advances using quantitative susceptibility mapping (QSM) make it possible to differentiate iron content from mineralization in-vivo using magnetic resonance imaging (MRI). However, automated detection of such lesions is still challenging, making quantification in large cohort bases studies rather limited. Purpose: Development of a fully automated method using deep learning for detecting CMBs and basal ganglia iron deposits using multimodal MRI. Materials and Methods: We included a convenience sample of 24 participants from the MESA cohort and used T2-weighted images, susceptibility weighted imaging (SWI), and QSM to segment the lesions. We developed a protocol for simultaneous manual annotation of CMBs and non-hemorrhage iron deposits in the basal ganglia, which resulted in defining the gold standard. This gold standard was then used to train a deep convolution neural network (CNN) model. Specifically, we adapted the U-Net model with a higher number of resolution layers to be able to detect small lesions such as CMBs from standard resolution MRI which are used in cohort-based studies. The detection performance was then evaluated using the cross-validation principle in order to ensure generalization of the results. Results: With multi-class CNN models, we achieved an average sensitivity and precision of about 0.8 and 0.6, respectively for detecting CMBs. The same framework detected non-hemorrhage iron deposits reaching an average sensitivity and precision of about 0.8. Conclusions: Our results showed that deep learning could automate the detection of small vessel disease lesions and including multimodal MR data such as QSM can improve the detection of CMB and non-hemorrhage iron deposits.

[1]  Susan M. Chang,et al.  Computer-aided detection of radiation-induced cerebral microbleeds on susceptibility-weighted MR images☆ , 2013, NeuroImage: Clinical.

[2]  Steven Warach,et al.  Cerebral Microbleeds : A Field Guide to their Detection and Interpretation , 2012 .

[3]  J. Reichenbach,et al.  Differentiation between diamagnetic and paramagnetic cerebral lesions based on magnetic susceptibility mapping. , 2010, Medical physics.

[4]  Simon Andermatt,et al.  Standardized Assessment of Automatic Segmentation of White Matter Hyperintensities and Results of the WMH Segmentation Challenge , 2019, IEEE Transactions on Medical Imaging.

[5]  Seung-Hoon Lee,et al.  Cerebral microbleeds in patients with hypertensive stroke , 2004, Journal of Neurology.

[6]  Stephen M. Smith,et al.  A global optimisation method for robust affine registration of brain images , 2001, Medical Image Anal..

[7]  M A Weinstein,et al.  Calcification of the basal ganglia as visualized by computed tomography. , 1980, Radiology.

[8]  Hao Chen,et al.  Automatic Detection of Cerebral Microbleeds From MR Images via 3D Convolutional Neural Networks , 2016, IEEE Transactions on Medical Imaging.

[9]  Taghi M. Khoshgoftaar,et al.  Experimental perspectives on learning from imbalanced data , 2007, ICML '07.

[10]  Christos Davatzikos,et al.  White matter hyperintensities and imaging patterns of brain ageing in the general population. , 2016, Brain : a journal of neurology.

[11]  Yi Wang,et al.  Quantitative susceptibility map reconstruction from MR phase data using bayesian regularization: Validation and application to brain imaging , 2010, Magnetic resonance in medicine.

[12]  Yu-Chung N. Cheng,et al.  Susceptibility weighted imaging (SWI) , 2004, Zeitschrift fur medizinische Physik.

[13]  Jim Mintz,et al.  Brain ferritin iron may influence age- and gender-related risks of neurodegeneration , 2007, Neurobiology of Aging.

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

[15]  E. Haacke,et al.  Susceptibility-Weighted Imaging: Technical Aspects and Clinical Applications, Part 1 , 2008, American Journal of Neuroradiology.

[16]  J. Babb,et al.  Age-related total gray matter and white matter changes in normal adult brain. Part I: volumetric MR imaging analysis. , 2002, AJNR. American journal of neuroradiology.

[17]  Z. Wu,et al.  Susceptibility-Weighted Imaging: Technical Aspects and Clinical Applications, Part 2 , 2008, American Journal of Neuroradiology.

[18]  M. Seghier,et al.  Microbleed Detection Using Automated Segmentation (MIDAS): A New Method Applicable to Standard Clinical MR Images , 2011, PloS one.

[19]  Julio Acosta-Cabronero,et al.  In Vivo MRI Mapping of Brain Iron Deposition across the Adult Lifespan , 2016, The Journal of Neuroscience.

[20]  Yi Wang,et al.  Morphology enabled dipole inversion for quantitative susceptibility mapping using structural consistency between the magnitude image and the susceptibility map , 2012, NeuroImage.

[21]  Karl J. Friston,et al.  Unified segmentation , 2005, NeuroImage.

[22]  D. Werring,et al.  The Microbleed Anatomical Rating Scale (MARS) , 2009, Neurology.

[23]  R. Kronmal,et al.  Multi-Ethnic Study of Atherosclerosis: objectives and design. , 2002, American journal of epidemiology.

[24]  Sven Haller,et al.  Cerebral Microbleeds: Imaging and Clinical Significance. , 2018, Radiology.

[25]  Nathan D. Wong,et al.  The Multiethnic Study of Atherosclerosis. , 2016, Global heart.

[26]  M. Modic,et al.  Calcification of the choroid plexus visualized by computed tomography. , 1980, Radiology.

[27]  R. Martins,et al.  Quantitative MR imaging R2 relaxometry in elderly participants reporting memory loss. , 2006, AJNR. American journal of neuroradiology.

[28]  Saifeng Liu,et al.  Cerebral microbleed detection using Susceptibility Weighted Imaging and deep learning , 2019, NeuroImage.

[29]  Joanna M Wardlaw,et al.  Improving Interrater Agreement About Brain Microbleeds: Development of the Brain Observer MicroBleed Scale (BOMBS) , 2009, Stroke.

[30]  J S Thornton,et al.  Choice of echo time on GRE T2*-weighted MRI influences the classification of brain microbleeds. , 2010, Clinical radiology.

[31]  Hao Chen,et al.  Automatic cerebral microbleeds detection from MR images via Independent Subspace Analysis based hierarchical features , 2015, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[32]  Wiesje M van der Flier,et al.  Brain microbleeds and Alzheimer's disease: innocent observation or key player? , 2011, Brain : a journal of neurology.

[33]  Amir Alansary,et al.  MRBrainS Challenge: Online Evaluation Framework for Brain Image Segmentation in 3T MRI Scans , 2015, Comput. Intell. Neurosci..

[34]  Snehashis Roy,et al.  Cerebral microbleed segmentation from susceptibility weighted images , 2015, Medical Imaging.

[35]  Bruce Fischl,et al.  Accurate and robust brain image alignment using boundary-based registration , 2009, NeuroImage.

[36]  Christos Davatzikos,et al.  MUSE: MUlti-atlas region Segmentation utilizing Ensembles of registration algorithms and parameters, and locally optimal atlas selection , 2016, NeuroImage.

[37]  Jeff H Duyn,et al.  The role of iron in brain ageing and neurodegenerative disorders , 2014, The Lancet Neurology.

[38]  Thomas Brox,et al.  3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation , 2016, MICCAI.

[39]  D. Werring,et al.  Cerebral microbleed detection and mapping: Principles, methodological aspects and rationale in vascular dementia , 2012, Experimental Gerontology.

[40]  Michael Brady,et al.  Improved Optimization for the Robust and Accurate Linear Registration and Motion Correction of Brain Images , 2002, NeuroImage.

[41]  Janine M. Lupo,et al.  Toward Automatic Detection of Radiation-Induced Cerebral Microbleeds Using a 3D Deep Residual Network , 2018, Journal of Digital Imaging.

[42]  Nick C Fox,et al.  A longitudinal study of brain volume changes in normal aging using serial registered magnetic resonance imaging. , 2003, Archives of neurology.

[43]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[44]  Bruce M Psaty,et al.  Yield and consistency of arrhythmia detection with patch electrocardiographic monitoring: The Multi-Ethnic Study of Atherosclerosis. , 2018, Journal of electrocardiology.

[45]  Pascal Spincemaille,et al.  Cerebral microbleeds: burden assessment by using quantitative susceptibility mapping. , 2012, Radiology.

[46]  Sven Haller,et al.  Cerebral microhemorrhage and iron deposition in mild cognitive impairment: susceptibility-weighted MR imaging assessment. , 2010, Radiology.

[47]  Max A. Viergever,et al.  Efficient detection of cerebral microbleeds on 7.0T MR images using the radial symmetry transform , 2012, NeuroImage.

[48]  Sudha Seshadri,et al.  Association of MRI Markers of Vascular Brain Injury With Incident Stroke, Mild Cognitive Impairment, Dementia, and Mortality: The Framingham Offspring Study , 2010, Stroke.

[49]  E Mark Haacke,et al.  Imaging cerebral microbleeds using susceptibility weighted imaging: One step toward detecting vascular dementia , 2010, Journal of magnetic resonance imaging : JMRI.

[50]  J. Wardlaw,et al.  Spontaneous brain microbleeds: systematic review, subgroup analyses and standards for study design and reporting. , 2007, Brain : a journal of neurology.

[51]  Eric E. Smith,et al.  MR Imaging Detection of Cerebral Microbleeds: Effect of Susceptibility-Weighted Imaging, Section Thickness, and Field Strength , 2008, American Journal of Neuroradiology.