Skip to main content
main-content

04.03.2019 | Original Article | Ausgabe 6/2019 Open Access

Osteoporosis International 6/2019

Opportunistic osteoporosis screening in multi-detector CT images via local classification of textures

Zeitschrift:
Osteoporosis International > Ausgabe 6/2019
Autoren:
A. Valentinitsch, S. Trebeschi, J. Kaesmacher, C. Lorenz, M. T. Löffler, C. Zimmer, T. Baum, J. S. Kirschke
Wichtige Hinweise

Electronic supplementary material

The online version of this article (https://​doi.​org/​10.​1007/​s00198-019-04910-1) contains supplementary material, which is available to authorized users.

Highlights

• We present an automatic pipeline for opportunistic osteoporosis screening using 3D texture features and regional vBMD.
• A combination of local texture and density features performed better than global vBMD alone to distinguish between patients with and without osteoporotic vertebral fractures.
• All vertebral levels were important to distinguish between patients with and without osteoporotic vertebral fractures.

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Abstract

Summary

Our study proposed an automatic pipeline for opportunistic osteoporosis screening using 3D texture features and regional vBMD using multi-detector CT images. A combination of different local and global texture features outperformed the global vBMD and showed high discriminative power to identify patients with vertebral fractures.

Introduction

Many patients at risk for osteoporosis undergo computed tomography (CT) scans, usable for opportunistic (non-dedicated) screening. We compared the performance of global volumetric bone mineral density (vBMD) with a random forest classifier based on regional vBMD and 3D texture features to separate patients with and without osteoporotic fractures.

Methods

In total, 154 patients (mean age 64 ± 8.5, male; n = 103) were included in this retrospective single-center analysis, who underwent contrast-enhanced CT for other reasons than osteoporosis screening. Patients were dichotomized regarding prevalent vertebral osteoporotic fractures (noFX, n = 101; FX, n = 53). Vertebral bodies were automatically segmented, and trabecular vBMD was calculated with a dedicated phantom. For 3D texture analysis, we extracted gray-level co-occurrence matrix Haralick features (HAR), histogram of gradients (HoG), local binary patterns (LBP), and wavelets (WL). Fractured vertebrae were excluded for texture-feature and vBMD data extraction. The performance to identify patients with prevalent osteoporotic vertebral fractures was evaluated in a fourfold cross-validation.

Results

The random forest classifier showed a high discriminatory power (AUC = 0.88). Parameters of all vertebral levels significantly contributed to this classification. Importantly, the AUC of the proposed algorithm was significantly higher than that of volumetric global BMD alone (AUC = 0.64).

Conclusion

The presented classifier combining 3D texture features and regional vBMD including the complete thoracolumbar spine showed high discriminatory power to identify patients with vertebral fractures and had a better diagnostic performance than vBMD alone.

Unsere Produktempfehlungen

e.Med Interdisziplinär

Kombi-Abonnement

Mit e.Med Interdisziplinär erhalten Sie Zugang zu allen CME-Fortbildungen und Fachzeitschriften auf SpringerMedizin.de.

Jetzt e.Med zum Sonderpreis bestellen!

Sichern Sie sich jetzt Ihr e.Med-Abo und sparen Sie 50 %!

Zusatzmaterial
Literatur
Über diesen Artikel

Weitere Artikel der Ausgabe 6/2019

Osteoporosis International 6/2019 Zur Ausgabe