VESICLE: Volumetric Evaluation of Synaptic Interfaces using Computer vision at Large Scale

Roncal, William Gray; Kaynig-Fittkau, Verena; Kleissas, Dean; Vogelstein, Joshua T.; Pfister, Hanspeter; Burns, Randal; Vogelstein, R. Jacob; Chevillet, Mark A.; Hager, Gregory D.

doi:10.48550/arxiv.1403.3724

Cited by 2 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This distribution may be treated as a Bayesian prior and updated if other information is available; multiple proofreading algorithms can work together. Thus, for example, synapse detection algorithms [29,31] may provide additional evidence for a merge error if synapses of two kinds are found on the same segmented object, but are normally found on different types of neurons. In such a scenario, the probability at the relevant location would be increased from its value computed by MergeNet, according to the confidence of the synapse detection algorithm.…”

Section: Discussionmentioning

confidence: 99%

“…Januszewski et al [11] and Meirovitch et al [22] present approaches for directly segmenting individual neurons from microscope images, without recourse to membrane prediction and agglomeration algorithms. Deep learning techniques have likewise been used to detect synapses between neurons [29,31] and to localize voltage measurements in neural circuits [2] (progress towards a functional connectome). New forms of data are also being leveraged for connectomics [27,34], thanks to advances in biochemical engineering.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Morphological Error Detection in 3D Segmentations

Rolnick,

Meirovitch,

Parag

et al. 2017

Preprint

Self Cite

View full text Add to dashboard Cite

Deep learning algorithms for connectomics rely upon localized classification, rather than overall morphology. This leads to a high incidence of erroneously merged objects. Humans, by contrast, can easily detect such errors by acquiring intuition for the correct morphology of objects. Biological neurons have complicated and variable shapes, which are challenging to learn, and merge errors take a multitude of different forms. We present an algorithm, MergeNet, that shows 3D ConvNets can, in fact, detect merge errors from high-level neuronal morphology. MergeNet follows unsupervised training and operates across datasets. We demonstrate the performance of MergeNet both on a variety of connectomics data and on a dataset created from merged MNIST images.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Morphological Error Detection in 3D Segmentations

Rolnick,

Meirovitch,

Parag

et al. 2017

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Automated synapse detection methods also have seen progress, for instance in [2], automatically identified synapses allow the analysis of different neuron cell types. Most of the proposed methods identify synaptic sites [1,5,10,11,12]. For the overall goal of reconstructing the connectome, however, it is necessary to additionally identify the preand postsynaptic partners.…”

Section: Introductionmentioning

confidence: 99%

Synaptic Partner Prediction from Point Annotations in Insect Brains

Buhmann

Krause

Lentini

et al. 2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

High-throughput electron microscopy allows recording of large stacks of neural tissue with sufficient resolution to extract the wiring diagram of the underlying neural network. Current efforts to automate this process focus mainly on the segmentation of neurons. However, in order to recover a wiring diagram, synaptic partners need to be identified as well. This is especially challenging in insect brains like Drosophila melanogaster, where one presynaptic site is associated with multiple postsynaptic elements. Here we propose a 3D U-Net architecture to directly identify pairs of voxels that are pre-and postsynaptic to each other. To that end, we formulate the problem of synaptic partner identification as a classification problem on long-range edges between voxels to encode both the presence of a synaptic pair and its direction. This formulation allows us to directly learn from synaptic point annotations instead of more expensive voxel-based synaptic cleft or vesicle annotations. We evaluate our method on the MICCAI 2016 CREMI challenge and improve over the current state of the art, producing 3% fewer errors than the next best method.

show abstract

VESICLE: Volumetric Evaluation of Synaptic Interfaces using Computer vision at Large Scale

Cited by 2 publications

References 0 publications

Morphological Error Detection in 3D Segmentations

Morphological Error Detection in 3D Segmentations

Synaptic Partner Prediction from Point Annotations in Insect Brains

Contact Info

Product

Resources

About