Erythrocytes Morphological Classification Through HMM for Sickle Cell Detection

Delgado-Font, Wilkie Ernesto; González-Hidalgo, Manuel; Herold-García, Silena; Jaume-i-Capó, Antoni; Mir, Arnau

doi:10.1007/978-3-319-41778-3_9

Cited by 4 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All analyses that can be performed on their presence can be used by a specialist to issue a criterion related to the severity of a patient's crisis. For this reason, the cell differentiation into normal, sickle, or other abnormal cells that has been studied by some authors (Wheeless et al, 1994;Fernández et al, 2013;Gonzalez-Hidalgo et al, 2015;Delgado et al, 2016;Gual et al, 2015a) is illustrative for this pathology. However, the analysis of other types of erythrocyte deformations present in blood samples can be of interest, because there are other diseases that can lead to this situation.…”

Section: Unsupervised Clusteringmentioning

confidence: 99%

“…A first group uses elementary descriptors, such as the circularity and elliptical factors, which do not offer the best results due to their simplicity (Wheeless et al, 1994;Fernández et al, 2013). Some other recent approaches propose ellipse fitting (Gonzalez-Hidalgo et al, 2015), Hough transform (Mazalan et al, 2013), circlet transform (Sarrafzadeh et al, 2015), the computation of descriptors using Fourier series (Frejlichowski, 2010;Aziz , 2013), classification via artificial neural networks (Durant et al, 2017;Rahmat et al, 2018;Dalvi and Vernekar , 2016), the analysis of curvature changes (Delgado et al, 2016) and the use of integral geometry-based functions to obtain efficient descriptors of the erythrocyte contour (Gual et al, 2013;2015a). All these approaches make it possible to compare and analyze the shape of erythrocytes in the feature space, but they are not suitable for computing shape statistics, such as mean shapes, or capturing the principal directions of shape variation within a specific class or between the cells in a normal and/or deformed cell class.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Morphological Analysis of Cells by Means of an Elastic Metric in the Shape Space

2020

View full text Add to dashboard Cite

Shape analysis is of great importance in many fields, such as computer vision, medical imaging, and computational biology. This analysis can be performed considering shapes as closed planar curves in the shape space. This approach has been used for the first time to obtain the morphological classification of erythrocytes in digital images of sickle cell disease considering the shape space S1, which has the property of being isometric to an infinite-dimensional Grassmann manifold of two-dimensional subspaces (Younes et al., 2008), without taking advantage of all the features offered by the elastic metric related to the possibility of stretching and bending of the curves. In this paper, we study this deformation in the shape space, S2, which is based on the representation of closed planar curves by means of the square-root velocity function (SRVF) (Srivastava et al., 2011), using the elastic metric of this space to obtain more efficient geodesics and geodesic lengths between planar curves. Supervised classification with this approach achieved an accuracy of 94.3%, classification using templates achieved 94.2% and unsupervised clustering in three groups achieved 94.7%, considering three classes of erythrocytes: normal, sickle, and with other deformations. These results are better than those previously achieved in the morphological analysis of erythrocytes and the method can be used in different applications related to the treatment of sickle cell disease, even in cases where it is necessary to study the process of evolution of the deformation, something that can not be done in a natural way in the feature space.

show abstract