Automatic 3D shape severity quantification and localization for deformational plagiocephaly

Abstract

Recent studies have shown an increase in the occurrence of deformational plagiocephaly and brachycephaly in children. This increase has coincided with the “Back to Sleep” campaign that was introduced to reduce the risk of Sudden Infant Death Syndrome (SIDS). However, there has yet to be an objective quantification of the degree of severity for these two conditions. Most diagnoses are done on subjective factors such as patient history and physician examination. The existence of an objective quantification would help research in areas of diagnosis and intervention measures, as well as provide a tool for finding correlation between the shape severity and cognitive outcome. This paper describes a new shape severity quantification and localization method for deformational plagiocephaly and brachycephaly. Our results show that there is a positive correlation between the new shape severity measure and the scores entered by a human expert.

Analyzing infant head flatness and asymmetry using kernel density estimation of directional surface data from a craniofacial 3D model

“…Med. 2016, 35 4891-4904 4891 V. VUOLLO ET AL.Atmosukarto et al [5,12] took a completely different approach and proposed to use the distribution of head normal vector directions to measure asymmetry and flatness. Flat areas lead to local maxima of the normal vector distribution, which can then be used to quantify head deformation ( Figure 1).…”

“…Flat areas lead to local maxima of the normal vector distribution, which can then be used to quantify head deformation ( Figure 1). The normal vector distribution was represented as a two-dimensional (2D) histogram on the polar coordinate plane with a fixed number of bins and the bin counts were used to define the asymmetry and flatness scores.We also use head normal vectors to measure asymmetry and flatness but propose an approach that improves on the method suggested in [5,12] in several ways. Instead of a fixed-bin histogram defined on the spherical coordinate plane, we use a smooth kernel density estimate of the directional data defined by the normal vectors.…”

“…As an asymmetry score, we propose to use the integral of the squared difference between the density estimate and its reflection across the plane that divides the head into left and right halves.Our example data consist of 3D head images of 3-month-old infants and they were analyzed earlier in [4] using the volume approach of Meyer-Marcotty et al [10]. In addition to the results of that study, we report comparisons with the methods of Atmosukarto et al [5,12], as well as with clinical classification ratings given by two medical doctors.Section 2 describes the kernel density estimation method used, visualization of the estimate, and the proposed flatness and asymmetry scores. Data analysis is presented in Section 3, and the article concludes with a discussion in Section 4.…”

“…We also use head normal vectors to measure asymmetry and flatness but propose an approach that improves on the method suggested in [5,12] in several ways. Instead of a fixed-bin histogram defined on the spherical coordinate plane, we use a smooth kernel density estimate of the directional data defined by the normal vectors.…”

“…Our example data consist of 3D head images of 3-month-old infants and they were analyzed earlier in [4] using the volume approach of Meyer-Marcotty et al [10]. In addition to the results of that study, we report comparisons with the methods of Atmosukarto et al [5,12], as well as with clinical classification ratings given by two medical doctors.…”