3D Spine Shape Estimation from Single 2D DXA

TL;DR

This paper introduces an automated framework to estimate 3D spine shape from single 2D DXA scans by predicting the sagittal view and combining it with the coronal view, aiding in better scoliosis assessment.

Contribution

The novel approach predicts the sagittal spine view from DXA scans to reconstruct 3D spine shape, utilizing a large dataset of paired DXA and MRI images.

Findings

High accuracy in 3D spine shape estimation

Effective use of paired DXA and MRI data

Potential to improve scoliosis diagnosis

Abstract

Scoliosis is traditionally assessed based solely on 2D lateral deviations, but recent studies have also revealed the importance of other imaging planes in understanding the deformation of the spine. Consequently, extracting the spinal geometry in 3D would help quantify these spinal deformations and aid diagnosis. In this study, we propose an automated general framework to estimate the 3D spine shape from 2D DXA scans. We achieve this by explicitly predicting the sagittal view of the spine from the DXA scan. Using these two orthogonal projections of the spine (coronal in DXA, and sagittal from the prediction), we are able to describe the 3D shape of the spine. The prediction is learnt from over 30k paired images of DXA and MRI scans. We assess the performance of the method on a held out test set, and achieve high accuracy.