Learning Population-level Shape Statistics and Anatomy Segmentation From Images: A Joint Deep Learning Model

TL;DR

This paper introduces a deep learning framework that jointly learns population-level shape statistics and anatomy segmentation directly from volumetric images, streamlining traditional shape modeling processes.

Contribution

It presents a novel joint deep learning model that simultaneously captures local and global shape correspondences from images, reducing pre-processing steps in shape analysis.

Findings

Effective shape modeling on two datasets

Direct inference of anatomical surfaces from images

Improved shape analysis without extensive pre-processing

Abstract

Statistical shape modeling is an essential tool for the quantitative analysis of anatomical populations. Point distribution models (PDMs) represent the anatomical surface via a dense set of correspondences, an intuitive and easy-to-use shape representation for subsequent applications. These correspondences are exhibited in two coordinate spaces: the local coordinates describing the geometrical features of each individual anatomical surface and the world coordinates representing the population-level statistical shape information after removing global alignment differences across samples in the given cohort. We propose a deep-learning-based framework that simultaneously learns these two coordinate spaces directly from the volumetric images. The proposed joint model serves a dual purpose; the world correspondences can directly be used for shape analysis applications, circumventing the heavy pre-processing and segmentation involved in traditional PDM models. Additionally, the local correspondences can be used for anatomy segmentation. We demonstrate the efficacy of this joint model for both shape modeling applications on two datasets and its utility in inferring the anatomical surface.