thumbnail

InShaDe: Invariant Shape Descriptors for visual analysis of histology 2D cellular and nuclear shapes

Marco Agus, Khaled Al-Thelaya, Corrado Calí, Marina Boido, Yin Yang, Giovanni Pintore, Enrico Gobbetti, and Jens Schneider

September 2020

Abstract

We 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.

Reference and download information

Marco Agus, Khaled Al-Thelaya, Corrado Calí, Marina Boido, Yin Yang, Giovanni Pintore, Enrico Gobbetti, and Jens Schneider. InShaDe: Invariant Shape Descriptors for visual analysis of histology 2D cellular and nuclear shapes. In Proc. Eurographics Workshop on Visual Computing for Biology and Medicine (VCBM). Pages 61-70, September 2020. DOI: 10.2312/vcbm.20201173.

Related multimedia productions

Bibtex citation record

@inproceedings{Agus:2020:IIS,
    author = {Marco Agus and Khaled Al-Thelaya and Corrado Cal\'i and Marina Boido and Yin Yang and Giovanni Pintore and Enrico Gobbetti and Jens Schneider},
    title = {{InShaDe}: Invariant Shape Descriptors for visual analysis of histology 2D cellular and nuclear shapes},
    booktitle = {Proc. Eurographics Workshop on Visual Computing for Biology and Medicine (VCBM)},
    pages = {61--70},
    month = {September},
    year = {2020},
    abstract = { We 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. },
    doi = {10.2312/vcbm.20201173},
    url = {http://vic.crs4.it/vic/cgi-bin/bib-page.cgi?id='Agus:2020:IIS'},
}