eCommons

 

Data from: Deep convolutional neural networks for segmenting 3D in vivo multiphoton images of vasculature in Alzheimer disease mouse models

dc.contributor.authorHaft-Javaherian, Mohammad
dc.contributor.authorFang, Linjing
dc.contributor.authorMuse, Victorine
dc.contributor.authorSchaffer, Chris B
dc.contributor.authorNishimura, Nozomi
dc.contributor.authorSabuncu, Mert R
dc.date.accessioned2018-10-15T21:44:57Z
dc.date.available2018-10-15T21:44:57Z
dc.date.issued2018
dc.description.abstractThe health and function of tissue rely on its vasculature network to provide reliable blood perfusion. Volumetric imaging approaches, such as multiphoton microscopy, are able to generate detailed 3D images of blood vessels that could contribute to our understanding of the role of vascular structure in normal physiology and in disease mechanisms. The segmentation of vessels, a core image analysis problem, is a bottleneck that has prevented the systematic comparison of 3D vascular architecture across experimental populations. We explored the use of convolutional neural networks to segment 3D vessels within volumetric in vivo images acquired by multiphoton microscopy. We evaluated different network architectures and machine learning techniques in the context of this segmentation problem. We show that our optimized convolutional neural network architecture, which we call DeepVess, yielded a segmentation accuracy that was better than both the current state-of-the-art and a trained human annotator, while also being orders of magnitude faster. To explore the effects of aging and Alzheimer's disease on capillaries, we applied DeepVess to 3D images of cortical blood vessels in young and old mouse models of Alzheimer's disease and wild type littermates. We found little difference in the distribution of capillary diameter or tortuosity between these groups, but did note a decrease in the number of longer capillary segments (>75μm) in aged animals as compared to young, in both wild type and Alzheimer's disease mouse models. These data support these findings.en_US
dc.description.sponsorshipThis work was supported by the European Research Council grant 615102 (NN), the National Institutes of Health grant AG049952 (CS), the National Institutes of Health grants R01LM012719 and R01AG053949 (MS), and the National Science Foundation Cornell NeuroNex Hub grant (1707312, MS and CS).en_US
dc.identifier.doihttps://doi.org/10.7298/X4FJ2F1D
dc.identifier.urihttps://hdl.handle.net/1813/59221
dc.language.isoen_USen_US
dc.relation.isreferencedbyHaft-Javaherian, M., Fang, L., Muse, V., Schaffer, C. B., Nishimura, N., & Sabuncu, M. R. (2018). Deep convolutional neural networks for segmenting 3D in vivo multiphoton images of vasculature in Alzheimer disease mouse models. arXiv preprint arXiv:1801.00880.
dc.relation.isreferencedbyHaft-Javaherian, M., Fang, L., Muse, V., Schaffer, C. B., Nishimuraa, N., & Sabuncu, M. R. (2018). DeepVess Github repository. https://github.com/mhaft/DeepVess. Downloaded 2018-10-16.
dc.relation.isreferencedbyurihttps://arxiv.org/abs/1801.00880
dc.relation.isreferencedbyurihttps://github.com/mhaft/DeepVess
dc.rightsAttribution 4.0 International*
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/*
dc.subjectVessel segmentationen_US
dc.subjectVascular segmentationen_US
dc.subjectIn vivo multiphoton microscopyen_US
dc.subjectConvolutional neural networken_US
dc.subjectDeep neural networken_US
dc.subjectCenterline extractionen_US
dc.subjectAgingen_US
dc.subjectAlzheimer’s diseaseen_US
dc.titleData from: Deep convolutional neural networks for segmenting 3D in vivo multiphoton images of vasculature in Alzheimer disease mouse modelsen_US
dc.typedataseten_US

Files

Original bundle
Now showing 1 - 3 of 3
No Thumbnail Available
Name:
HaftJavaherian_DeepVess2018_Images.zip
Size:
1.41 GB
Format:
Data Compression Utility
Description:
No Thumbnail Available
Name:
HaftJavaherian_DeepVess2018_GithubArchive.zip
Size:
18.88 MB
Format:
Data Compression Utility
Description:
No Thumbnail Available
Name:
HaftJavaherian_DeepVess2018_ReadMe.txt
Size:
3.97 KB
Format:
Plain Text
Description: