Anatomically Parameterized Statistical Shape Model: Explaining Morphometry through Statistical Learning

TL;DR

This paper introduces ANAT-SSM, a novel statistical shape model that explicitly links shape coefficients to anatomical measures, enhancing clinical interpretability and utility in morphological analysis and surgical planning.

Contribution

It proposes a new anatomically parameterized SSM that learns a linear mapping between shape coefficients and anatomical parameters, improving interpretability over traditional models.

Findings

Anatomical measures of synthetic shapes showed realistic statistics.

The learned matrices matched the statistical relationships well.

Models predicted anatomical parameters accurately on unseen shapes.

Abstract

Statistical shape models (SSMs) are a popular tool to conduct morphological analysis of anatomical structures which is a crucial step in clinical practices. However, shape representations through SSMs are based on shape coefficients and lack an explicit one-to-one relationship with anatomical measures of clinical relevance. While a shape coefficient embeds a combination of anatomical measures, a formalized approach to find the relationship between them remains elusive in the literature. This limits the use of SSMs to subjective evaluations in clinical practices. We propose a novel SSM controlled by anatomical parameters derived from morphometric analysis. The proposed anatomically parameterized SSM (ANAT-SSM) is based on learning a linear mapping between shape coefficients and selected anatomical parameters. This mapping is learned from a synthetic population generated by the standard SSM. Determining the pseudo-inverse of the mapping allows us to build the ANAT-SSM. We further impose orthogonality constraints to the anatomical parameterization to obtain independent shape variation patterns. The proposed contribution was evaluated on two skeletal databases of femoral and scapular bone shapes using clinically relevant anatomical parameters. Anatomical measures of the synthetically generated shapes exhibited realistic statistics. The learned matrices corroborated well with the obtained statistical relationship, while the two SSMs achieved moderate to excellent performance in predicting anatomical parameters on unseen shapes. This study demonstrates the use of anatomical representation for creating anatomically parameterized SSM and as a result, removes the limited clinical interpretability of standard SSMs. The proposed models could help analyze differences in relevant bone morphometry between populations, and be integrated in patient-specific pre-surgery planning or in-surgery assessment.