A deep learning algorithm for 3D cell detection in whole mouse brain image datasets

Understanding the function of the nervous system necessitates mapping the spatial distributions of its constituent cells defined by function, anatomy or gene expression. Recently, developments in tissue preparation and microscopy allow cellular populations to be imaged throughout the entire rodent brain. However, mapping these neurons manually is prone to bias and is often impractically time consuming. Here we present an open-source algorithm for fully automated 3D detection of neuronal somata in mouse whole-brain microscopy images using standard desktop computer hardware. We demonstrate the applicability and power of our approach by mapping the brain-wide locations of large populations of cells labeled with cytoplasmic fluorescent proteins expressed via retrograde trans-synaptic viral infection.

[1]  Sachie K. Ogawa,et al.  Whole-Brain Mapping of Direct Inputs to Midbrain Dopamine Neurons , 2012, Neuron.

[2]  Drew Friedmann,et al.  Mapping mesoscale axonal projections in the mouse brain using a 3D convolutional network , 2019, Proceedings of the National Academy of Sciences.

[3]  Daniel Kirschenbaum,et al.  The mesoSPIM initiative – open-source light-sheet microscopes for imaging cleared tissue , 2019, Nature Methods.

[4]  Knut Conradsen,et al.  Integrated Brain Atlas for Unbiased Mapping of Nervous System Effects Following Liraglutide Treatment , 2018, Scientific Reports.

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

[6]  Asim Iqbal,et al.  DeNeRD: high-throughput detection of neurons for brain-wide analysis with deep learning , 2019, Scientific Reports.

[7]  Rajtarun Madangopal,et al.  SMART: An open source extension of WholeBrain for iDISCO+ LSFM intact mouse brain registration and segmentation , 2019, bioRxiv.

[8]  Karl Deisseroth,et al.  An interactive framework for whole-brain maps at cellular resolution , 2017, Nature Neuroscience.

[9]  Aaron S. Andalman,et al.  Structural and molecular interrogation of intact biological systems , 2013, Nature.

[10]  Cheuk Y. Tang,et al.  Mapping of Brain Activity by Automated Volume Analysis of Immediate Early Genes , 2016, Cell.

[11]  Nicolas Chenouard,et al.  Icy: an open bioimage informatics platform for extended reproducible research , 2012, Nature Methods.

[12]  Johannes E. Schindelin,et al.  Fiji: an open-source platform for biological-image analysis , 2012, Nature Methods.

[13]  L. Ng,et al.  The Allen Mouse Brain Common Coordinate Framework: A 3D Reference Atlas , 2020, Cell.

[14]  M. Scharf,et al.  Rapid evolutionary responses to insecticide resistance management interventions by the German cockroach (Blattella germanica L.) , 2019, Scientific Reports.

[15]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[16]  Liang Gao,et al.  Imaging multicellular specimens with real-time optimized tiling light-sheet selective plane illumination microscopy , 2016, Nature Communications.

[17]  Ian R. Wickersham,et al.  Retrograde neuronal tracing with a deletion-mutant rabies virus , 2007, Nature Methods.

[18]  David J. Anderson,et al.  Ventromedial hypothalamic neurons control a defensive emotion state , 2015, eLife.

[19]  R. Hudson,et al.  A population genetic interpretation of GWAS findings for human quantitative traits , 2018, PLoS biology.

[20]  Amy Strange,et al.  Citizen science, cells and CNNs – deep learning for automatic segmentation of the nuclear envelope in electron microscopy data, trained with volunteer segmentations , 2020, bioRxiv.

[21]  P. Osten,et al.  Mapping brain circuitry with a light microscope , 2013, Nature Methods.

[22]  J. Tiihonen,et al.  Amygdala-orbitofrontal structural and functional connectivity in females with anxiety disorders, with and without a history of conduct disorder , 2018, Scientific Reports.

[23]  Marc Modat,et al.  aMAP is a validated pipeline for registration and segmentation of high-resolution mouse brain data , 2016, Nature Communications.

[24]  Frank Bradke,et al.  Three-dimensional imaging of solvent-cleared organs using 3DISCO , 2012, Nature Protocols.

[25]  Anne E Carpenter,et al.  CellProfiler 3.0: Next-generation image processing for biology , 2018, PLoS biology.

[26]  Fred A. Hamprecht,et al.  ilastik: interactive machine learning for (bio)image analysis , 2019, Nature Methods.

[27]  Srinivas C. Turaga,et al.  Mapping social behavior-induced brain activation at cellular resolution in the mouse. , 2014, Cell reports.

[28]  William Graf,et al.  Deep learning for cellular image analysis , 2019, Nature Methods.

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

[30]  C. Felser,et al.  Negative magnetoresistance without well-defined chirality in the Weyl semimetal TaP , 2015, Nature Communications.

[31]  S. Herculano‐Houzel,et al.  Cellular scaling rules for rodent brains , 2006, Proceedings of the National Academy of Sciences.

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

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

[34]  Sachie K. Ogawa,et al.  Dopamine neurons projecting to the posterior striatum form an anatomically distinct subclass , 2015, eLife.

[35]  E. Susaki,et al.  Whole-Brain Imaging with Single-Cell Resolution Using Chemical Cocktails and Computational Analysis , 2014, Cell.

[36]  Sébastien Ourselin,et al.  Reconstructing a 3D structure from serial histological sections , 2001, Image Vis. Comput..

[37]  A. Schierloh,et al.  Ultramicroscopy: three-dimensional visualization of neuronal networks in the whole mouse brain , 2007, Nature Methods.

[38]  Stephan Saalfeld,et al.  Globally optimal stitching of tiled 3D microscopic image acquisitions , 2009, Bioinform..

[39]  Takeharu Nagai,et al.  High-Speed and Scalable Whole-Brain Imaging in Rodents and Primates , 2017, Neuron.

[40]  Naoshige Uchida,et al.  Organization of monosynaptic inputs to the serotonin and dopamine neuromodulatory systems. , 2014, Cell reports.

[41]  Kwanghun Chung,et al.  Stochastic electrotransport selectively enhances the transport of highly electromobile molecules , 2015, Proceedings of the National Academy of Sciences.

[42]  Mark Mayford,et al.  Localization of a Stable Neural Correlate of Associative Memory , 2007, Science.

[43]  Troy W. Margrie,et al.  BrainGlobe Atlas API: a common interface for neuroanatomical atlases , 2020, J. Open Source Softw..

[44]  Martin K. Schwarz,et al.  Fluorescent-Protein Stabilization and High-Resolution Imaging of Cleared, Intact Mouse Brains , 2015, PloS one.

[45]  F. Claudi,et al.  Brainrender: a python-based software for visualizing anatomically registered data , 2020, bioRxiv.