A deep learning toolbox for automatic segmentation of subcortical limbic structures from MRI images

A tool was developed to automatically segment several subcortical limbic structures (nucleus accumbens, basal forebrain, septal nuclei, hypothalamus without mammillary bodies, the mammillary bodies, and fornix) using only a T1-weighted MRI as input. This tool fills an unmet need as there are few, if any, publicly available tools to segment these clinically relevant structures. A U-Net with spatial, intensity, contrast, and noise augmentation was trained using 39 manually labeled MRI data sets. In general, the Dice scores, true positive rates, false discovery rates, and manual-automatic volume correlation were very good relative to comparable tools for other structures. A diverse data set of 698 subjects were segmented using the tool; evaluation of the resulting labelings showed that the tool failed in less than 1% of cases. Test-retest reliability of the tool was excellent. The automatically segmented volume of all structures except mammillary bodies showed effectiveness at detecting either clinical AD effects, age effects, or both. This tool will be publicly released with FreeSurfer (surfer.nmr.mgh.harvard.edu/fswiki/ScLimbic). Together with the other cortical and subcortical limbic segmentations, this tool will allow FreeSurfer to provide a comprehensive view of the limbic system in an automated way.

[1]  Carlos Ortiz-de-Solorzano,et al.  Combination Strategies in Multi-Atlas Image Segmentation: Application to Brain MR Data , 2009, IEEE Transactions on Medical Imaging.

[2]  Amod Jog,et al.  PSACNN: Pulse sequence adaptive fast whole brain segmentation , 2019, NeuroImage.

[3]  Andrew J. Saykin,et al.  The fornix and mammillary bodies in older adults with Alzheimer's disease, mild cognitive impairment, and cognitive complaints: A volumetric MRI study , 2006, Psychiatry Research: Neuroimaging.

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

[5]  E. Halgren,et al.  Volume of the Human Septal Forebrain Region Is a Predictor of Source Memory Accuracy , 2011, Journal of the International Neuropsychological Society.

[6]  Jens Petersen,et al.  nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation , 2020, Nature Methods.

[7]  G. V. Van Hoesen,et al.  Alzheimer's disease: cell-specific pathology isolates the hippocampal formation. , 1984, Science.

[8]  C. Geula,et al.  Systematic regional variations in the loss of cortical cholinergic fibers in Alzheimer's disease. , 1996, Cerebral cortex.

[9]  Koenraad Van Leemput,et al.  A computational atlas of the hippocampal formation using ex vivo, ultra-high resolution MRI: Application to adaptive segmentation of in vivo MRI , 2015, NeuroImage.

[10]  J. Whitwell,et al.  Alzheimer's disease neuroimaging , 2018, Current opinion in neurology.

[11]  Joseph E LeDoux.  Rethinking the Emotional Brain , 2012, Neuron.

[12]  R Kötter,et al.  Useless or Helpful? The "Limbic System" Concept , 1997, Reviews in the neurosciences.

[13]  Robert L. Ruff.  Neuroanatomy An Atlas of Structures, Sections, and Systems, 4th Ed. , 1995 .

[14]  F. Vogel,et al.  The limbic system in Alzheimer's disease. A neuropathologic investigation. , 1976, The American journal of pathology.

[15]  Keith A. Johnson,et al.  Synergistic effect of β-amyloid and neurodegeneration on cognitive decline in clinically normal individuals. , 2014, JAMA neurology.

[16]  Sébastien Ourselin,et al.  MIRIAD—Public release of a multiple time point Alzheimer's MR imaging dataset , 2013, NeuroImage.

[17]  M M Mesulam,et al.  The systems-level organization of cholinergic innervation in the human cerebral cortex and its alterations in Alzheimer's disease. , 1996, Progress in brain research.

[18]  H. Braak,et al.  Where, when, and in what form does sporadic Alzheimer's disease begin? , 2012, Current opinion in neurology.

[19]  Tobias Kober,et al.  MP2RAGE, a self bias-field corrected sequence for improved segmentation and T1-mapping at high field , 2010, NeuroImage.

[20]  Abraham Z. Snyder,et al.  A unified approach for morphometric and functional data analysis in young, old, and demented adults using automated atlas-based head size normalization: reliability and validation against manual measurement of total intracranial volume , 2004, NeuroImage.

[21]  D. Selkoe.  Alzheimer's disease. , 2011, Cold Spring Harbor perspectives in biology.

[22]  M. Leon,et al.  Basal forebrain septal nuclei are enlarged in healthy subjects prior to the development of Alzheimer's disease , 2018, Neurobiology of Aging.

[23]  Stephen M. Smith,et al.  A Bayesian model of shape and appearance for subcortical brain segmentation , 2011, NeuroImage.

[24]  H. Braak,et al.  Neuropathological stageing of Alzheimer-related changes , 2004, Acta Neuropathologica.

[25]  Ben Glocker,et al.  Automated quality control in image segmentation: application to the UK Biobank cardiovascular magnetic resonance imaging study , 2019, Journal of Cardiovascular Magnetic Resonance.

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

[27]  Z. M. Saygina,et al.  High-resolution magnetic resonance imaging reveals nuclei of the human amygdala : manual segmentation to automatic atlas , 2017 .

[28]  Leticia Rittner,et al.  Hypothalamus fully automatic segmentation from MR images using a U-Net based architecture , 2020, Symposium on Medical Information Processing and Analysis.

[29]  J C Adair,et al.  Is it Alzheimer's? , 1998, Hospital practice.

[30]  Harald Hampel,et al.  Revisiting the Cholinergic Hypothesis in Alzheimer’s Disease: Emerging Evidence from Translational and Clinical Research , 2018, The Journal of Prevention of Alzheimer's Disease.

[31]  L. Heimer,et al.  The limbic lobe and its output channels: Implications for emotional functions and adaptive behavior , 2006, Neuroscience & Biobehavioral Reviews.

[32]  Jochen Peters,et al.  Rapid fully automatic segmentation of subcortical brain structures by shape‐constrained surface adaptation , 2018, Medical Image Anal..

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

[34]  Allan R. Jones,et al.  Comprehensive cellular‐resolution atlas of the adult human brain , 2016, The Journal of comparative neurology.

[35]  A. Dale,et al.  Thinning of the cerebral cortex in aging. , 2004, Cerebral cortex.

[36]  A. Nappi,et al.  Alzheimer ' s Disease : Cell-Specific Pathology Isolates the Hippocampal Formation , 2022 .

[37]  Adrian V. Dalca,et al.  A Learning Strategy for Contrast-agnostic MRI Segmentation , 2020, MIDL.

[38]  Lucas Wexler.  Principles Of Behavioral Neurology , 2016 .

[39]  J. Fleiss,et al.  Intraclass correlations: uses in assessing rater reliability. , 1979, Psychological bulletin.

[40]  J Bohl,et al.  Staging of Alzheimer-Related Cortical Destruction , 1997, International Psychogeriatrics.

[41]  Stefan Teipel,et al.  Cholinergic basal forebrain atrophy predicts amyloid burden in Alzheimer's disease , 2014, Neurobiology of Aging.

[42]  André J. W. van der Kouwe,et al.  Brain morphometry with multiecho MPRAGE , 2008, NeuroImage.

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

[44]  Wilfried Philips,et al.  MRI Segmentation of the Human Brain: Challenges, Methods, and Applications , 2015, Comput. Math. Methods Medicine.

[45]  H. Möller,et al.  The septum pellucidum and its variants. An MRI study. , 2004, European archives of psychiatry and clinical neuroscience.

[46]  Paul M. Thompson,et al.  Automated multi-atlas labeling of the fornix and its integrity in alzheimer's disease , 2015, 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI).

[47]  H. Braak,et al.  Staging of Alzheimer-related cortical destruction. , 1997, International psychogeriatrics.

[48]  D. McCandless.  Neuroanatomy: an atlas of structures, sections and systems , 1994, Metabolic Brain Disease.

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

[50]  P. Maclean.  Psychosomatic Disease and the "Visceral Brain": Recent Developments Bearing on the Papez Theory of Emotion , 1949, Psychosomatic medicine.

[51]  H. Möller,et al.  The septum pellucidum and its variants , 2004, European Archives of Psychiatry and Clinical Neuroscience.

[52]  R. Terry,et al.  Senile dementia of the Alzheimer type , 1983, Annals of neurology.

[53]  Paul M. Thompson,et al.  A Focus on Structural Brain Imaging in the Alzheimer’s Disease Neuroimaging Initiative , 2014, Biological Psychiatry.

[54]  Chi‐Jen Chen,et al.  Prevalence of cavum septum pellucidum and/or cavum Vergae in brain computed tomographies of Taiwanese. , 2014, Acta neurologica Taiwanica.

[55]  Yi Li,et al.  Comparison of human septal nuclei MRI measurements using automated segmentation and a new manual protocol based on histology , 2014, NeuroImage.

[56]  D. S. Zahm,et al.  Anatomy of Neuropsychiatry: The New Anatomy of the Basal Forebrain and Its Implications for Neuropsychiatric Illness , 2007 .

[57]  Mark E. Schmidt,et al.  The Alzheimer's Disease Neuroimaging Initiative: Progress report and future plans , 2010, Alzheimer's & Dementia.

[58]  Martina Bocchetta,et al.  Automated segmentation of the hypothalamus and associated subunits in brain MRI , 2020, NeuroImage.

[59]  K. Yanagisawa.  [Senile dementia of Alzheimer type]. , 1999, Ryoikibetsu shokogun shirizu.

[60]  Ciprian Catana,et al.  Different partial volume correction methods lead to different conclusions: An 18F-FDG-PET study of aging , 2016, NeuroImage.

[61]  J. Morris,et al.  Recent publications from the Alzheimer's Disease Neuroimaging Initiative: Reviewing progress toward improved AD clinical trials , 2017, Alzheimer's & Dementia.

[62]  Koenraad Van Leemput,et al.  Fast and sequence-adaptive whole-brain segmentation using parametric Bayesian modeling , 2016, NeuroImage.

[63]  Olivier Rouaud,et al.  Reduced basal forebrain atrophy progression in a randomized Donepezil trial in prodromal Alzheimer’s disease , 2017, Scientific Reports.

[64]  Mert R. Sabuncu,et al.  Anatomical Priors in Convolutional Networks for Unsupervised Biomedical Segmentation , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[65]  J. Hort,et al.  Subregional Structural Alterations in Hippocampus and Nucleus Accumbens Correlate with the Clinical Impairment in Patients with Alzheimer’s Disease Clinical Spectrum: Parallel Combining Volume and Vertex-Based Approach , 2017, Front. Neurol..

[66]  B Fischl,et al.  High-resolution magnetic resonance imaging reveals nuclei of the human amygdala: manual segmentation to automatic atlas , 2017, NeuroImage.

[67]  Cheuk Y. Tang,et al.  Multimodal Characterization of the Late Effects of Traumatic Brain Injury: A Methodological Overview of the Late Effects of Traumatic Brain Injury Project. , 2018, Journal of neurotrauma.

[68]  Konstantinos Kamnitsas,et al.  Reverse Classification Accuracy: Predicting Segmentation Performance in the Absence of Ground Truth , 2017, IEEE Transactions on Medical Imaging.

[69]  Nikos Makris,et al.  Automatically parcellating the human cerebral cortex. , 2004, Cerebral cortex.

[70]  M. Ananth,et al.  Basal Forebrain Cholinergic Circuits and Signaling in Cognition and Cognitive Decline , 2016, Neuron.