1
|
Dorkenwald S, Li PH, Januszewski M, Berger DR, Maitin-Shepard J, Bodor AL, Collman F, Schneider-Mizell CM, da Costa NM, Lichtman JW, Jain V. Multi-layered maps of neuropil with segmentation-guided contrastive learning. Nat Methods 2023; 20:2011-2020. [PMID: 37985712 PMCID: PMC10703674 DOI: 10.1038/s41592-023-02059-8] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/18/2022] [Accepted: 10/02/2023] [Indexed: 11/22/2023]
Abstract
Maps of the nervous system that identify individual cells along with their type, subcellular components and connectivity have the potential to elucidate fundamental organizational principles of neural circuits. Nanometer-resolution imaging of brain tissue provides the necessary raw data, but inferring cellular and subcellular annotation layers is challenging. We present segmentation-guided contrastive learning of representations (SegCLR), a self-supervised machine learning technique that produces representations of cells directly from 3D imagery and segmentations. When applied to volumes of human and mouse cortex, SegCLR enables accurate classification of cellular subcompartments and achieves performance equivalent to a supervised approach while requiring 400-fold fewer labeled examples. SegCLR also enables inference of cell types from fragments as small as 10 μm, which enhances the utility of volumes in which many neurites are truncated at boundaries. Finally, SegCLR enables exploration of layer 5 pyramidal cell subtypes and automated large-scale analysis of synaptic partners in mouse visual cortex.
Collapse
Affiliation(s)
- Sven Dorkenwald
- Google Research, Mountain View, CA, USA
- Princeton Neuroscience Institute, Princeton University, Princeton, NJ, USA
- Computer Science Department, Princeton University, Princeton, NJ, USA
| | | | | | - Daniel R Berger
- Department of Molecular and Cellular Biology, Center for Brain Science, Harvard, Cambridge, MA, USA
| | | | | | | | | | | | - Jeff W Lichtman
- Department of Molecular and Cellular Biology, Center for Brain Science, Harvard, Cambridge, MA, USA
| | - Viren Jain
- Google Research, Mountain View, CA, USA.
| |
Collapse
|
2
|
Dorkenwald S, Schneider-Mizell CM, Brittain D, Halageri A, Jordan C, Kemnitz N, Castro MA, Silversmith W, Maitin-Shephard J, Troidl J, Pfister H, Gillet V, Xenes D, Bae JA, Bodor AL, Buchanan J, Bumbarger DJ, Elabbady L, Jia Z, Kapner D, Kinn S, Lee K, Li K, Lu R, Macrina T, Mahalingam G, Mitchell E, Mondal SS, Mu S, Nehoran B, Popovych S, Takeno M, Torres R, Turner NL, Wong W, Wu J, Yin W, Yu SC, Reid RC, da Costa NM, Seung HS, Collman F. CAVE: Connectome Annotation Versioning Engine. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2023:2023.07.26.550598. [PMID: 37546753 PMCID: PMC10402030 DOI: 10.1101/2023.07.26.550598] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 08/08/2023]
Abstract
Advances in Electron Microscopy, image segmentation and computational infrastructure have given rise to large-scale and richly annotated connectomic datasets which are increasingly shared across communities. To enable collaboration, users need to be able to concurrently create new annotations and correct errors in the automated segmentation by proofreading. In large datasets, every proofreading edit relabels cell identities of millions of voxels and thousands of annotations like synapses. For analysis, users require immediate and reproducible access to this constantly changing and expanding data landscape. Here, we present the Connectome Annotation Versioning Engine (CAVE), a computational infrastructure for immediate and reproducible connectome analysis in up-to petascale datasets (~1mm3) while proofreading and annotating is ongoing. For segmentation, CAVE provides a distributed proofreading infrastructure for continuous versioning of large reconstructions. Annotations in CAVE are defined by locations such that they can be quickly assigned to the underlying segment which enables fast analysis queries of CAVE's data for arbitrary time points. CAVE supports schematized, extensible annotations, so that researchers can readily design novel annotation types. CAVE is already used for many connectomics datasets, including the largest datasets available to date.
Collapse
Affiliation(s)
- Sven Dorkenwald
- Princeton Neuroscience Institute, Princeton University, Princeton, USA
- Computer Science Department, Princeton University, Princeton, USA
| | | | | | - Akhilesh Halageri
- Princeton Neuroscience Institute, Princeton University, Princeton, USA
| | - Chris Jordan
- Princeton Neuroscience Institute, Princeton University, Princeton, USA
| | - Nico Kemnitz
- Princeton Neuroscience Institute, Princeton University, Princeton, USA
| | - Manual A. Castro
- Princeton Neuroscience Institute, Princeton University, Princeton, USA
| | | | | | - Jakob Troidl
- School of Engineering and Applied Sciences, Harvard University, Boston, USA
| | - Hanspeter Pfister
- School of Engineering and Applied Sciences, Harvard University, Boston, USA
| | - Valentin Gillet
- Lund University, Department of Biology, Lund Vision Group, Lund, Sweden
| | - Daniel Xenes
- Research & Exploratory Development Department, Johns Hopkins University Applied Physics Laboratory, Laurel, United States
| | - J. Alexander Bae
- Princeton Neuroscience Institute, Princeton University, Princeton, USA
- Electrical and Computer Engineering Department, Princeton University, Princeton, USA
| | | | | | | | | | - Zhen Jia
- Princeton Neuroscience Institute, Princeton University, Princeton, USA
- Computer Science Department, Princeton University, Princeton, USA
| | | | - Sam Kinn
- Allen Institute for Brain Science, Seattle, USA
| | - Kisuk Lee
- Princeton Neuroscience Institute, Princeton University, Princeton, USA
- Brain & Cognitive Sciences Department, Massachusetts Institute of Technology, Cambridge, USA
| | - Kai Li
- Computer Science Department, Princeton University, Princeton, USA
| | - Ran Lu
- Princeton Neuroscience Institute, Princeton University, Princeton, USA
| | - Thomas Macrina
- Princeton Neuroscience Institute, Princeton University, Princeton, USA
- Computer Science Department, Princeton University, Princeton, USA
| | | | - Eric Mitchell
- Princeton Neuroscience Institute, Princeton University, Princeton, USA
| | - Shanka Subhra Mondal
- Princeton Neuroscience Institute, Princeton University, Princeton, USA
- Electrical and Computer Engineering Department, Princeton University, Princeton, USA
| | - Shang Mu
- Princeton Neuroscience Institute, Princeton University, Princeton, USA
| | - Barak Nehoran
- Princeton Neuroscience Institute, Princeton University, Princeton, USA
- Computer Science Department, Princeton University, Princeton, USA
| | - Sergiy Popovych
- Princeton Neuroscience Institute, Princeton University, Princeton, USA
- Computer Science Department, Princeton University, Princeton, USA
| | - Marc Takeno
- Allen Institute for Brain Science, Seattle, USA
| | | | - Nicholas L. Turner
- Princeton Neuroscience Institute, Princeton University, Princeton, USA
- Computer Science Department, Princeton University, Princeton, USA
| | - William Wong
- Princeton Neuroscience Institute, Princeton University, Princeton, USA
| | - Jingpeng Wu
- Princeton Neuroscience Institute, Princeton University, Princeton, USA
| | - Wenjing Yin
- Allen Institute for Brain Science, Seattle, USA
| | - Szi-chieh Yu
- Princeton Neuroscience Institute, Princeton University, Princeton, USA
| | | | | | - H. Sebastian Seung
- Princeton Neuroscience Institute, Princeton University, Princeton, USA
- Computer Science Department, Princeton University, Princeton, USA
| | | |
Collapse
|
3
|
Liu Z, Zhang Y, Yu Y, Yixuan, Sun, Wang Y, He Y, Zhao Q, Zheng N, Gong Z, Feng L. High-Speed Automated Reconstruction of Drosophila Larval Brain from Volumetric EM Data. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2023; 2023:1-4. [PMID: 38083640 DOI: 10.1109/embc40787.2023.10340599] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/18/2023]
Abstract
To uncover the relationship between neural activity and behavior, it is essential to reconstruct neural circuits. However, methods typically used for neuron reconstruction from volumetric electron microscopy (EM) dataset are often time-consuming and require extensive manual proofreading, making it difficult to reproduce in a typical laboratory setting. To address this challenge, we have developed a set of acceleration techniques that build upon the Flood Filling Network (FFN), significantly reducing the time required for this task. These techniques can be easily adapted to other similar datasets and laboratory settings. To validate our approach, we tested our pipeline on a dataset of Drosophila larval brain serial section EM images at synaptic-resolution level. Our results demonstrate that our pipeline significantly reduces the inference time compared to the FFN baseline method and greatly reduces the time required for reconstructing the 3D morphology of neurons.
Collapse
|