A New 3D Segmentation Methodology for Lumbar Vertebral Bodies for the Measurement of BMD and Geometry

TL;DR

This paper introduces a novel multi-step segmentation technique for lumbar vertebral bodies from spiral CT scans, enabling precise measurement of BMD and geometry to aid osteoporosis fracture prediction.

Contribution

The paper presents a new segmentation methodology that improves accuracy and precision in measuring vertebral BMD and geometry from CT scans, with low intra- and inter-operator variability.

Findings

Intra- and inter-operator precision below 1.5%

BMD measurement accuracy errors below 1.5%

Volume measurement errors below 4% in phantom data

Abstract

In this paper a new technique is presented that extracts the geometry of lumbar vertebral bodies from spiral CT scans. Our new multi-step segmentation approach yields highly accurate and precise measurement of the bone mineral density (BMD) in different volumes of interest which are defined relative to a local anatomical coordinate systems. The approach also enables the analysis of the geometry of the relevant vertebrae. Intra- and inter operator precision for segmentation, BMD measurement and position of the coordinate system are below 1.5% in patient data, accuracy errors are below 1.5% for BMD and below 4% for volume in phantom data. The long-term goal of the approach is to improve fracture prediction in osteoporosis.