TY - JOUR
T1 - Mapping mesoscale axonal projections in the mouse brain using a 3D convolutional network
AU - Friedmann, Drew
AU - Pun, Albert
AU - Adams, Eliza L.
AU - Lui, Jan H.
AU - Kebschull, Justus M.
AU - Grutzner, Sophie M.
AU - Castagnola, Caitlin
AU - Tessier-Lavigne, Marc
AU - Luo, Liqun
N1 - Funding Information:
ACKNOWLEDGMENTS. We thank Ethan Richman for helpful discussions and comments on the manuscript. D.F. was supported by National Institute of Neurological Disorders and Stroke T32 NS007280, J.H.L. by National Institute of Mental Health K01 MH114022, J.M.K. by a Jane
Funding Information:
We thank Ethan Richman for helpful discussions and comments on the manuscript. D.F. was supported by National Institute of Neurological Disorders and Stroke T32 NS007280, J.H.L. by National Institute of Mental Health K01 MH114022, J.M.K. by a Jane Coffin Childs postdoctoral fellowship, and E.L.A. by the Stanford Bio-X Bowes PhD Fellowship. This work was supported by NIH Grants R01 NS104698 and U24 NS109113. L.L. is a Howard Hughes Medical Institute investigator.
Funding Information:
Coffin Childs postdoctoral fellowship, and E.L.A. by the Stanford Bio-X Bowes PhD Fellowship. This work was supported by NIH Grants R01 NS104698 and U24 NS109113. L.L. is a Howard Hughes Medical Institute investigator.
Publisher Copyright:
© 2020 National Academy of Sciences. All rights reserved.
PY - 2020/5/19
Y1 - 2020/5/19
N2 - The projection targets of a neuronal population are a key feature of its anatomical characteristics. Historically, tissue sectioning, confocal microscopy, and manual scoring of specific regions of interest have been used to generate coarse summaries of mesoscale projectomes. We present here TrailMap, a three-dimensional (3D) convolutional network for extracting axonal projections from intact cleared mouse brains imaged by light-sheet microscopy. TrailMap allows region-based quantification of total axon content in large and complex 3D structures after registration to a standard reference atlas. The identification of axonal structures as thin as one voxel benefits from data augmentation but also requires a loss function that tolerates errors in annotation. A network trained with volumes of serotonergic axons in all major brain regions can be generalized to map and quantify axons from thalamocortical, deep cerebellar, and cortical projection neurons, validating transfer learning as a tool to adapt the model to novel categories of axonal morphology. Speed of training, ease of use, and accuracy improve over existing tools without a need for specialized computing hardware. Given the recent emphasis on genetically and functionally defining cell types in neural circuit analysis, TrailMap will facilitate automated extraction and quantification of axons from these specific cell types at the scale of the entire mouse brain, an essential component of deciphering their connectivity.
AB - The projection targets of a neuronal population are a key feature of its anatomical characteristics. Historically, tissue sectioning, confocal microscopy, and manual scoring of specific regions of interest have been used to generate coarse summaries of mesoscale projectomes. We present here TrailMap, a three-dimensional (3D) convolutional network for extracting axonal projections from intact cleared mouse brains imaged by light-sheet microscopy. TrailMap allows region-based quantification of total axon content in large and complex 3D structures after registration to a standard reference atlas. The identification of axonal structures as thin as one voxel benefits from data augmentation but also requires a loss function that tolerates errors in annotation. A network trained with volumes of serotonergic axons in all major brain regions can be generalized to map and quantify axons from thalamocortical, deep cerebellar, and cortical projection neurons, validating transfer learning as a tool to adapt the model to novel categories of axonal morphology. Speed of training, ease of use, and accuracy improve over existing tools without a need for specialized computing hardware. Given the recent emphasis on genetically and functionally defining cell types in neural circuit analysis, TrailMap will facilitate automated extraction and quantification of axons from these specific cell types at the scale of the entire mouse brain, an essential component of deciphering their connectivity.
KW - Axons
KW - Light-sheet microscopy
KW - Neural networks
KW - Tissue clearing
KW - Whole-brain
UR - http://www.scopus.com/inward/record.url?scp=85084962230&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85084962230&partnerID=8YFLogxK
U2 - 10.1073/pnas.1917287117
DO - 10.1073/pnas.1917287117
M3 - Article
C2 - 32358193
AN - SCOPUS:85084962230
SN - 0027-8424
VL - 117
SP - 11068
EP - 11075
JO - Proceedings of the National Academy of Sciences of the United States of America
JF - Proceedings of the National Academy of Sciences of the United States of America
IS - 20
ER -