InShaDe: Invariant Shape Descriptors for Visual Analysis of Histology 2D Cellular and Nuclear Shapes

Simple item page
dc.contributor.authorAgus, Marcoen_US
dc.contributor.authorAl-Thelaya, Khaleden_US
dc.contributor.authorCali, Corradoen_US
dc.contributor.authorBoido, Marina M.en_US
dc.contributor.authorYang, Yinen_US
dc.contributor.authorPintore, Giovannien_US
dc.contributor.authorGobbetti, Enricoen_US
dc.contributor.authorSchneider, Jensen_US
dc.contributor.editorKozlíková, Barbora and Krone, Michael and Smit, Noeska and Nieselt, Kay and Raidou, Renata Georgiaen_US
dc.date.accessioned2020-09-28T06:11:50Z
dc.date.available2020-09-28T06:11:50Z
dc.date.issued2020
dc.description.abstractWe present a shape processing framework for visual exploration of cellular nuclear envelopes extracted from histology images. The framework is based on a novel shape descriptor of closed contours relying on a geodesically uniform resampling of discrete curves to allow for discrete differential-geometry-based computation of unsigned curvature at vertices and edges. Our descriptor is, by design, invariant under translation, rotation and parameterization. Moreover, it additionally offers the option for uniform-scale-invariance. The optional scale-invariance is achieved by scaling features to z-scores, while invariance under parameterization shifts is achieved by using elliptic Fourier analysis (EFA) on the resulting curvature vectors. These invariant shape descriptors provide an embedding into a fixed-dimensional feature space that can be utilized for various applications: (i) as input features for deep and shallow learning techniques; (ii) as input for dimension reduction schemes for providing a visual reference for clustering collection of shapes. The capabilities of the proposed framework are demonstrated in the context of visual analysis and unsupervised classification of histology images.en_US
dc.description.sectionheadersJoint Session DAGM GCPR - VMV - VCBM
dc.description.seriesinformationEurographics Workshop on Visual Computing for Biology and Medicine
dc.identifier.doi10.2312/vcbm.20201173
dc.identifier.isbn978-3-03868-109-0
dc.identifier.issn2070-5786
dc.identifier.pages61-70
dc.identifier.urihttps://doi.org/10.2312/vcbm.20201173
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/vcbm20201173
dc.publisherThe Eurographics Associationen_US
dc.subjectApplied computing
dc.subjectImaging
dc.subjectComputing methodologies
dc.subjectShape representations
dc.subjectCluster analysis
dc.titleInShaDe: Invariant Shape Descriptors for Visual Analysis of Histology 2D Cellular and Nuclear Shapesen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
061-070.pdf
Size:
9.2 MB
Format:
Adobe Portable Document Format
Download
Collections
VCBM 2020: Eurographics Workshop on Visual Computing for Biology and Medicine