InShaDe: Invariant Shape Descriptors for visual 2D and 3D cellular and nuclear shape analysis and classification

<p dir="ltr">We present a shape processing framework for visual exploration of cellular nuclear envelopes extracted from microscopic images arising in histology and neuroscience. The framework is based on a novel shape descriptor of closed contours in 2D and 3D. In 2D, it relies on a...

Full description

Saved in:
Bibliographic Details
Main Author: Khaled Al-Thelaya (17302711) (author)
Other Authors: Marco Agus (8032898) (author), Nauman Ullah Gilal (17302714) (author), Yin Yang (35103) (author), Giovanni Pintore (17302717) (author), Enrico Gobbetti (17302720) (author), Corrado Calí (17302723) (author), Pierre J. Magistretti (8032907) (author), William Mifsud (1394) (author), Jens Schneider (16885948) (author)
Published: 2021
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513545453961216
author Khaled Al-Thelaya (17302711)
author2 Marco Agus (8032898)
Nauman Ullah Gilal (17302714)
Yin Yang (35103)
Giovanni Pintore (17302717)
Enrico Gobbetti (17302720)
Corrado Calí (17302723)
Pierre J. Magistretti (8032907)
William Mifsud (1394)
Jens Schneider (16885948)
author2_role author
author
author
author
author
author
author
author
author
author_facet Khaled Al-Thelaya (17302711)
Marco Agus (8032898)
Nauman Ullah Gilal (17302714)
Yin Yang (35103)
Giovanni Pintore (17302717)
Enrico Gobbetti (17302720)
Corrado Calí (17302723)
Pierre J. Magistretti (8032907)
William Mifsud (1394)
Jens Schneider (16885948)
author_role author
dc.creator.none.fl_str_mv Khaled Al-Thelaya (17302711)
Marco Agus (8032898)
Nauman Ullah Gilal (17302714)
Yin Yang (35103)
Giovanni Pintore (17302717)
Enrico Gobbetti (17302720)
Corrado Calí (17302723)
Pierre J. Magistretti (8032907)
William Mifsud (1394)
Jens Schneider (16885948)
dc.date.none.fl_str_mv 2021-08-01T00:00:00Z
dc.identifier.none.fl_str_mv 10.1016/j.cag.2021.04.037
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/InShaDe_Invariant_Shape_Descriptors_for_visual_2D_and_3D_cellular_and_nuclear_shape_analysis_and_classification/24459070
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Biological sciences
Microbiology
Biomedical and clinical sciences
Neurosciences
Engineering
Biomedical engineering
Information and computing sciences
Human-centred computing
Shape analysis
Histopathology
Serial section electron microscopy
Nuclear envelopes
Discrete differential geometry
dc.title.none.fl_str_mv InShaDe: Invariant Shape Descriptors for visual 2D and 3D cellular and nuclear shape analysis and classification
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">We present a shape processing framework for visual exploration of cellular nuclear envelopes extracted from microscopic images arising in histology and neuroscience. The framework is based on a novel shape descriptor of closed contours in 2D and 3D. In 2D, it relies on a geodesically uniform resampling of discrete curves to compute unsigned curvatures at vertices and edges based on discrete differential geometry. Our descriptor is, by design, invariant under translation, rotation, and parameterization. We achieve the latter invariance under parameterization shifts by using elliptic Fourier analysis on the resulting curvature vectors. Uniform scale-invariance is optional and is a result of scaling curvature features to z-scores. We further augment the proposed descriptor with feature coefficients obtained through sparse coding of the extracted cellular structures using K-sparse autoencoders. For the analysis of 3D shapes, we compute mean curvatures based on the Laplace-Beltrami operator on triangular meshes, followed by computing a spherical parameterization through mean curvature flow. Finally, we compute the Spherical Harmonics decomposition to obtain invariant energy coefficients. Our invariant descriptors provide an embedding into a fixed-dimensional feature space that can be used for various applications, e.g., as input features for deep and shallow learning techniques or as input for dimension reduction schemes to provide a visual reference for clustering shape collections. We demonstrate the capabilities of our framework in the context of visual analysis and unsupervised classification of 2D histology images and 3D nuclear envelopes extracted from serial section electron microscopy stacks.</p><h2>Other Information</h2><p dir="ltr">Published in: Computers & Graphics<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.cag.2021.04.037" target="_blank">https://dx.doi.org/10.1016/j.cag.2021.04.037</a></p>
eu_rights_str_mv openAccess
id Manara2_5f9a984c417df42f3075bcb8c4ccfd16
identifier_str_mv 10.1016/j.cag.2021.04.037
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/24459070
publishDate 2021
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling InShaDe: Invariant Shape Descriptors for visual 2D and 3D cellular and nuclear shape analysis and classificationKhaled Al-Thelaya (17302711)Marco Agus (8032898)Nauman Ullah Gilal (17302714)Yin Yang (35103)Giovanni Pintore (17302717)Enrico Gobbetti (17302720)Corrado Calí (17302723)Pierre J. Magistretti (8032907)William Mifsud (1394)Jens Schneider (16885948)Biological sciencesMicrobiologyBiomedical and clinical sciencesNeurosciencesEngineeringBiomedical engineeringInformation and computing sciencesHuman-centred computingShape analysisHistopathologySerial section electron microscopyNuclear envelopesDiscrete differential geometry<p dir="ltr">We present a shape processing framework for visual exploration of cellular nuclear envelopes extracted from microscopic images arising in histology and neuroscience. The framework is based on a novel shape descriptor of closed contours in 2D and 3D. In 2D, it relies on a geodesically uniform resampling of discrete curves to compute unsigned curvatures at vertices and edges based on discrete differential geometry. Our descriptor is, by design, invariant under translation, rotation, and parameterization. We achieve the latter invariance under parameterization shifts by using elliptic Fourier analysis on the resulting curvature vectors. Uniform scale-invariance is optional and is a result of scaling curvature features to z-scores. We further augment the proposed descriptor with feature coefficients obtained through sparse coding of the extracted cellular structures using K-sparse autoencoders. For the analysis of 3D shapes, we compute mean curvatures based on the Laplace-Beltrami operator on triangular meshes, followed by computing a spherical parameterization through mean curvature flow. Finally, we compute the Spherical Harmonics decomposition to obtain invariant energy coefficients. Our invariant descriptors provide an embedding into a fixed-dimensional feature space that can be used for various applications, e.g., as input features for deep and shallow learning techniques or as input for dimension reduction schemes to provide a visual reference for clustering shape collections. We demonstrate the capabilities of our framework in the context of visual analysis and unsupervised classification of 2D histology images and 3D nuclear envelopes extracted from serial section electron microscopy stacks.</p><h2>Other Information</h2><p dir="ltr">Published in: Computers & Graphics<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.cag.2021.04.037" target="_blank">https://dx.doi.org/10.1016/j.cag.2021.04.037</a></p>2021-08-01T00:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1016/j.cag.2021.04.037https://figshare.com/articles/journal_contribution/InShaDe_Invariant_Shape_Descriptors_for_visual_2D_and_3D_cellular_and_nuclear_shape_analysis_and_classification/24459070CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/244590702021-08-01T00:00:00Z
spellingShingle InShaDe: Invariant Shape Descriptors for visual 2D and 3D cellular and nuclear shape analysis and classification
Khaled Al-Thelaya (17302711)
Biological sciences
Microbiology
Biomedical and clinical sciences
Neurosciences
Engineering
Biomedical engineering
Information and computing sciences
Human-centred computing
Shape analysis
Histopathology
Serial section electron microscopy
Nuclear envelopes
Discrete differential geometry
status_str publishedVersion
title InShaDe: Invariant Shape Descriptors for visual 2D and 3D cellular and nuclear shape analysis and classification
title_full InShaDe: Invariant Shape Descriptors for visual 2D and 3D cellular and nuclear shape analysis and classification
title_fullStr InShaDe: Invariant Shape Descriptors for visual 2D and 3D cellular and nuclear shape analysis and classification
title_full_unstemmed InShaDe: Invariant Shape Descriptors for visual 2D and 3D cellular and nuclear shape analysis and classification
title_short InShaDe: Invariant Shape Descriptors for visual 2D and 3D cellular and nuclear shape analysis and classification
title_sort InShaDe: Invariant Shape Descriptors for visual 2D and 3D cellular and nuclear shape analysis and classification
topic Biological sciences
Microbiology
Biomedical and clinical sciences
Neurosciences
Engineering
Biomedical engineering
Information and computing sciences
Human-centred computing
Shape analysis
Histopathology
Serial section electron microscopy
Nuclear envelopes
Discrete differential geometry