Brain tissues have single-voxel signatures in multi-spectral MRI

Since the seminal works by Brodmann and contemporaries, it is well-known that different brain regions exhibit unique cytoarchitectonic and myeloarchitectonic features. Transferring the approach of classifying brain tissues - and other tissues - based on their intrinsic features to the realm of magnetic resonance (MR) is a longstanding endeavor. In the 1990s, atlas-based segmentation replaced earlier multi-spectral classification approaches because of the large overlap between the class distributions. Here, we explored the feasibility of performing global brain classification based on intrinsic MR features, and used several technological advances: Ultra-high field MRI, q-space trajectory diffusion imaging revealing voxel-intrinsic diffusion properties, chemical exchange saturation transfer and semi-solid magnetization transfer imaging as a marker of myelination and neurochemistry, and current neural network architectures to analyze the data. In particular, we used the raw image data as well to increase the number of input features. We found that a global brain classification of roughly 97 brain regions was feasible with gross classification accuracy of 60%; and that mapping from voxel-intrinsic MR data to the brain region to which the data belongs is possible. This indicates the presence of unique MR signals of different brain regions, similar to their cytoarchitectonic and myeloarchitectonic fingerprints.

[1]  Yan Kang,et al.  STrategically Acquired Gradient Echo (STAGE) imaging, part I: Creating enhanced T1 contrast and standardized susceptibility weighted imaging and quantitative susceptibility mapping. , 2018, Magnetic resonance imaging.

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

[3]  M. Jacobs,et al.  Multiparametric radiomics methods for breast cancer tissue characterization using radiological imaging , 2020, Breast Cancer Research and Treatment.

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

[5]  Mert R. Sabuncu,et al.  Multi-atlas segmentation of biomedical images: A survey , 2014, Medical Image Anal..

[6]  Dosik Hwang,et al.  Susceptibility map‐weighted imaging (SMWI) for neuroimaging , 2014, Magnetic resonance in medicine.

[7]  Weifu Chen,et al.  A self-tuned graph-based framework for localization and grading prostate cancer lesions: An initial evaluation based on multiparametric magnetic resonance imaging , 2018, Comput. Biol. Medicine.

[8]  Peter Bachert,et al.  CEST Signals of Lipids , 2017 .

[9]  Max A. Viergever,et al.  elastix: A Toolbox for Intensity-Based Medical Image Registration , 2010, IEEE Transactions on Medical Imaging.

[10]  Berkman Sahiner,et al.  Deep learning in medical imaging and radiation therapy. , 2018, Medical physics.

[11]  Bernhard Schölkopf,et al.  A 32‐channel multi‐coil setup optimized for human brain shimming at 9.4T , 2020, Magnetic resonance in medicine.

[12]  Klaus H. Maier-Hein,et al.  Automated brain extraction of multisequence MRI using artificial neural networks , 2019, Human Brain Mapping.

[13]  Klaus Scheffler,et al.  Snapshot‐CEST: Optimizing spiral‐centric‐reordered gradient echo acquisition for fast and robust 3D CEST MRI at 9.4 T , 2018, NMR in biomedicine.

[14]  Bruce Fischl,et al.  FreeSurfer , 2012, NeuroImage.

[15]  M. Uder,et al.  Sample size estimation: Current practice and considerations for original investigations in MRI technical development studies , 2020, Magnetic resonance in medicine.

[16]  A. Evans,et al.  Prostate cancer detection with multi‐parametric MRI: Logistic regression analysis of quantitative T2, diffusion‐weighted imaging, and dynamic contrast‐enhanced MRI , 2009, Journal of magnetic resonance imaging : JMRI.

[17]  M. Uder,et al.  Fast online‐customized (FOCUS) parallel transmission pulses: A combination of universal pulses and individual optimization , 2021, Magnetic resonance in medicine.

[18]  A. Toga,et al.  Detection and mapping of abnormal brain structure with a probabilistic atlas of cortical surfaces. , 1997, Journal of computer assisted tomography.

[19]  Oliver Speck,et al.  Pros and cons of ultra-high-field MRI/MRS for human application. , 2018, Progress in nuclear magnetic resonance spectroscopy.

[20]  V. Abeler,et al.  Multispectral analysis of uterine corpus tumors in magnetic resonance imaging , 1992, Magnetic resonance in medicine.

[21]  Daniel Paech,et al.  Correction of B1‐inhomogeneities for relaxation‐compensated CEST imaging at 7 T , 2015, NMR in biomedicine.

[22]  Christian Riess,et al.  A Gentle Introduction to Deep Learning in Medical Image Processing , 2018, Zeitschrift fur medizinische Physik.

[23]  I. S. Yetik,et al.  Prostate cancer segmentation with multispectral MRI using cost-sensitive Conditional Random Fields , 2009, 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[24]  D. V. van Essen,et al.  Mapping Human Cortical Areas In Vivo Based on Myelin Content as Revealed by T1- and T2-Weighted MRI , 2011, The Journal of Neuroscience.

[25]  B. Stieltjes,et al.  [Introduction to the basic principles and techniques of diffusion-weighted imaging]. , 2011, Der Radiologe.

[26]  Klaus Scheffler,et al.  Adaptive denoising for chemical exchange saturation transfer MR imaging , 2019, NMR in biomedicine.

[27]  Bernhard Preim,et al.  A cytoarchitecture-driven myelin model reveals area-specific signatures in human primary and secondary areas using ultra-high resolution in-vivo brain MRI , 2015, NeuroImage.

[28]  Mark E Ladd,et al.  RF excitation using time interleaved acquisition of modes (TIAMO) to address B1 inhomogeneity in high‐field MRI , 2010, Magnetic resonance in medicine.

[29]  Ben Jeurissen,et al.  The role of whole‐brain diffusion MRI as a tool for studying human in vivo cortical segregation based on a measure of neurite density , 2018, Magnetic resonance in medicine.

[30]  Arthur W. Toga,et al.  A Probabilistic Atlas of the Human Brain: Theory and Rationale for Its Development The International Consortium for Brain Mapping (ICBM) , 1995, NeuroImage.

[31]  M. Uder,et al.  Multiple interleaved mode saturation (MIMOSA) for B1+ inhomogeneity mitigation in chemical exchange saturation transfer , 2018, Magnetic resonance in medicine.

[32]  Klaus Scheffler,et al.  DeepCEST 3T: Robust MRI parameter determination and uncertainty quantification with neural networks—application to CEST imaging of the human brain at 3T , 2019, Magnetic resonance in medicine.

[33]  L Axel,et al.  Noise performance of surface coils for magnetic resonance imaging at 1.5 T. , 1985, Medical physics.

[34]  James C. Bezdek,et al.  A comparison of neural network and fuzzy clustering techniques in segmenting magnetic resonance images of the brain , 1992, IEEE Trans. Neural Networks.

[35]  Peter F. Neher,et al.  TractSeg - Fast and accurate white matter tract segmentation , 2018, NeuroImage.

[36]  Cem M Deniz,et al.  Parallel Transmission for Ultrahigh Field MRI. , 2019, Topics in magnetic resonance imaging : TMRI.

[37]  K. Scheffler,et al.  DeepCEST: 9.4 T Chemical exchange saturation transfer MRI contrast predicted from 3 T data – a proof of concept study , 2019, Magnetic resonance in medicine.

[38]  H. Aerts,et al.  Applications and limitations of radiomics , 2016, Physics in medicine and biology.

[39]  R. Damadian Tumor Detection by Nuclear Magnetic Resonance , 1971, Science.

[40]  Markus Nilsson,et al.  Imaging brain tumour microstructure , 2018, NeuroImage.

[41]  Jinyuan Zhou,et al.  Using the amide proton signals of intracellular proteins and peptides to detect pH effects in MRI , 2003, Nature Medicine.

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

[43]  Stephen M. Smith,et al.  Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm , 2001, IEEE Transactions on Medical Imaging.

[44]  Massimo Bellomi,et al.  Radiomics: the facts and the challenges of image analysis , 2018, European Radiology Experimental.

[45]  K S Cheng,et al.  Segmentation of multispectral magnetic resonance image using penalized fuzzy competitive learning network. , 1996, Computers and biomedical research, an international journal.

[46]  K. Herz,et al.  AI boosted molecular MRI for apoptosis detection in oncolytic virotherapy , 2020, bioRxiv.

[47]  G. Lindstrom,et al.  Some preliminary observations on the proton magnetic resonance in biologic samples. , 1955, Acta radiologica.

[48]  M. Uder,et al.  Contrast-to-noise ratio analysis of microscopic diffusion anisotropy indices in q-space trajectory imaging. , 2020, Zeitschrift fur medizinische Physik.

[49]  B. Fischl,et al.  FastSurfer - A fast and accurate deep learning based neuroimaging pipeline , 2019, NeuroImage.

[50]  Julien Cohen-Adad,et al.  T2* mapping and B0 orientation-dependence at 7T reveal cyto- and myeloarchitecture organization of the human cortex , 2012, NeuroImage.

[51]  G. C. Levy,et al.  Characterization of normal brain tissue using seven calculated MRI parameters and a statistical analysis system , 1989, Magnetic resonance in medicine.

[52]  Jesper Andersson,et al.  A multi-modal parcellation of human cerebral cortex , 2016, Nature.

[53]  Peter Bachert,et al.  Signature of protein unfolding in chemical exchange saturation transfer imaging , 2015, NMR in biomedicine.

[54]  Stefan Skare,et al.  How to correct susceptibility distortions in spin-echo echo-planar images: application to diffusion tensor imaging , 2003, NeuroImage.

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

[56]  Lawrence L. Wald,et al.  Surface based analysis of diffusion orientation for identifying architectonic domains in the in vivo human cortex , 2013, NeuroImage.

[57]  R. Turner,et al.  Layer-Specific Intracortical Connectivity Revealed with Diffusion MRI , 2012, Cerebral cortex.

[58]  M. Lythgoe,et al.  Deep learning diffusion fingerprinting to detect brain tumour response to chemotherapy , 2017, bioRxiv.

[59]  T. Mikkelsen,et al.  Feature space analysis of MRI , 1998, Magnetic resonance in medicine.

[60]  Yongyi Yang,et al.  Supervised and unsupervised methods for prostate cancer segmentation with multispectral MRI. , 2010, Medical physics.

[61]  E. Formisano,et al.  Reproducibility and Reliability of Quantitative and Weighted T1 and T2∗ Mapping for Myelin-Based Cortical Parcellation at 7 Tesla , 2016, Front. Neuroanat..

[62]  L. H. Bennett,et al.  Recognition of Cancer in vivo by Nuclear Magnetic Resonance , 1972, Science.

[63]  Jianrong Xu,et al.  Streaking artifact reduction for quantitative susceptibility mapping of sources with large dynamic range , 2015, NMR in biomedicine.

[64]  David L. Thomas,et al.  Using High Angular Resolution Diffusion Imaging Data to Discriminate Cortical Regions , 2013, PloS one.

[65]  Steen Moeller,et al.  High‐resolution whole‐brain diffusion MRI at 7T using radiofrequency parallel transmission , 2018, Magnetic resonance in medicine.

[66]  G. Mangeat,et al.  Multivariate combination of magnetization transfer, T2* and B0 orientation to study the myelo-architecture of the in vivo human cortex , 2015, NeuroImage.

[67]  Douglas L. Rickman,et al.  Validation of magnetic resonance imaging (MRI) multispectral tissue classification , 1988, [1988 Proceedings] 9th International Conference on Pattern Recognition.

[68]  J. Duerk,et al.  Magnetic Resonance Fingerprinting , 2013, Nature.

[69]  William Wells,et al.  Detection of prostate cancer by integration of line-scan diffusion, T2-mapping and T2-weighted magnetic resonance imaging; a multichannel statistical classifier. , 2003, Medical physics.

[70]  H Soltanian-Zadeh,et al.  Brain tumor segmentation and characterization by pattern analysis of multispectral NMR images , 1998, NMR in biomedicine.

[71]  M W Vannier,et al.  Multispectral analysis of MR images of the breast. , 1987, Radiology.

[72]  Jelliffe Vergleichende Lokalisationslehre der Grosshirnrinde , 1910 .

[73]  M Quarantelli,et al.  Unsupervised, automated segmentation of the normal brain using a multispectral relaxometric magnetic resonance approach , 1997, Magnetic resonance in medicine.

[74]  Bruce Fischl,et al.  Regional white matter volume differences in nondemented aging and Alzheimer's disease , 2009, NeuroImage.

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

[76]  David G. Norris,et al.  Diffusion tensor characteristics of gyrencephaly using high resolution diffusion MRI in vivo at 7T , 2015, NeuroImage.

[77]  Brian B. Avants,et al.  An Open Source Multivariate Framework for n-Tissue Segmentation with Evaluation on Public Data , 2011, Neuroinformatics.

[78]  A Zavaljevski,et al.  Multi-level adaptive segmentation of multi-parameter MR brain images. , 2000, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[79]  John A. Detre,et al.  Magnetic Resonance Imaging of Glutamate , 2011, Nature Medicine.

[80]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[81]  Imam Samil Yetik,et al.  Prostate Cancer Localization Using Multiparametric MRI based on Semisupervised Techniques With Automated Seed Initialization , 2012, IEEE Transactions on Information Technology in Biomedicine.

[82]  P. V. van Zijl,et al.  In vivo imaging of phosphocreatine with artificial neural networks , 2020, Nature Communications.

[83]  Wiro J. Niessen,et al.  Neuro4Neuro: A neural network approach for neural tract segmentation using large-scale population-based diffusion imaging , 2020, NeuroImage.

[84]  Arvid Lundervold,et al.  Multispectral analysis of the brain using magnetic resonance imaging , 1994, IEEE Trans. Medical Imaging.

[85]  A. Schleicher,et al.  Architectonics of the human cerebral cortex and transmitter receptor fingerprints: reconciling functional neuroanatomy and neurochemistry , 2002, European Neuropsychopharmacology.

[86]  P. Lauterbur,et al.  Image Formation by Induced Local Interactions: Examples Employing Nuclear Magnetic Resonance , 1973, Nature.

[87]  R. L. Butterfield,et al.  Multispectral analysis of magnetic resonance images. , 1985, Radiology.

[88]  Zhengrong Liang,et al.  Parameter estimation and tissue segmentation from multispectral MR images , 1994, IEEE Trans. Medical Imaging.

[89]  Carl-Fredrik Westin,et al.  Q-space trajectory imaging for multidimensional diffusion MRI of the human brain , 2016, NeuroImage.

[90]  Benoit M. Dawant,et al.  Neural-network-based segmentation of multi-modal medical images: a comparative and prospective study , 1993, IEEE Trans. Medical Imaging.

[91]  Wolfgang Bogner,et al.  Computationally Efficient Combination of Multi‐channel Phase Data From Multi‐echo Acquisitions (ASPIRE) , 2018, Magnetic resonance in medicine.

[92]  Chunlei Liu,et al.  Whole brain susceptibility mapping using compressed sensing , 2012, Magnetic resonance in medicine.

[93]  Klaus Scheffler,et al.  Chemical exchange saturation transfer MRI contrast in the human brain at 9.4 T , 2018, NeuroImage.

[94]  F. Szczepankiewicz,et al.  Extrapolation-Based References Improve Motion and Eddy-Current Correction of High B-Value DWI Data: Application in Parkinson’s Disease Dementia , 2015, PloS one.

[95]  Thomas K. Pilgram,et al.  Validation of magnetic resonance imaging (MRI) multispectral tissue classification. , 1991, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[96]  Susumu Mori,et al.  Probing region-specific microstructure of human cortical areas using high angular and spatial resolution diffusion MRI , 2015, NeuroImage.

[97]  C. Hazlewood,et al.  Spin Echo Studies on Cellular Water , 1972, Nature.

[98]  Neural Networks Used to Interpret Pulsed-Gradient Restricted-Diffusion Data , 1994 .

[99]  D. Collins,et al.  Automatic 3D Intersubject Registration of MR Volumetric Data in Standardized Talairach Space , 1994, Journal of computer assisted tomography.

[100]  Richard A. E. Edden,et al.  Nuclear Overhauser enhancement (NOE) imaging in the human brain at 7T , 2013, NeuroImage.

[101]  L M Fletcher,et al.  A multispectral analysis of brain tissues , 1993, Magnetic resonance in medicine.

[102]  N. Fujii,et al.  Spin echo nuclear magnetic resonance in cancerous tissue. , 1972, Physiological chemistry and physics.

[103]  Yoshiyasu Takefuji,et al.  Optimization neural networks for the segmentation of magnetic resonance images , 1992, IEEE Trans. Medical Imaging.

[104]  Xue Xiao,et al.  Integrated Laplacian‐based phase unwrapping and background phase removal for quantitative susceptibility mapping , 2014, NMR in biomedicine.

[105]  Cornelis H. Slump,et al.  Layer-specific diffusion weighted imaging in human primary visual cortex in vitro , 2013, Cortex.