Cargando…
Opportunistic osteoporosis screening in multi-detector CT images via local classification of textures
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 ide...
Autores principales: | , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Springer London
2019
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6546649/ https://www.ncbi.nlm.nih.gov/pubmed/30830261 http://dx.doi.org/10.1007/s00198-019-04910-1 |
_version_ | 1783423544987746304 |
---|---|
author | Valentinitsch, A. Trebeschi, S. Kaesmacher, J. Lorenz, C. Löffler, M. T. Zimmer, C. Baum, T. Kirschke, J. S. |
author_facet | Valentinitsch, A. Trebeschi, S. Kaesmacher, J. Lorenz, C. Löffler, M. T. Zimmer, C. Baum, T. Kirschke, J. S. |
author_sort | Valentinitsch, A. |
collection | PubMed |
description | 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. ELECTRONIC SUPPLEMENTARY MATERIAL: The online version of this article (10.1007/s00198-019-04910-1) contains supplementary material, which is available to authorized users. |
format | Online Article Text |
id | pubmed-6546649 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2019 |
publisher | Springer London |
record_format | MEDLINE/PubMed |
spelling | pubmed-65466492019-06-19 Opportunistic osteoporosis screening in multi-detector CT images via local classification of textures Valentinitsch, A. Trebeschi, S. Kaesmacher, J. Lorenz, C. Löffler, M. T. Zimmer, C. Baum, T. Kirschke, J. S. Osteoporos Int Original Article 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. ELECTRONIC SUPPLEMENTARY MATERIAL: The online version of this article (10.1007/s00198-019-04910-1) contains supplementary material, which is available to authorized users. Springer London 2019-03-04 2019 /pmc/articles/PMC6546649/ /pubmed/30830261 http://dx.doi.org/10.1007/s00198-019-04910-1 Text en © The Author(s) 2019 OpenAccessThis article is distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. |
spellingShingle | Original Article Valentinitsch, A. Trebeschi, S. Kaesmacher, J. Lorenz, C. Löffler, M. T. Zimmer, C. Baum, T. Kirschke, J. S. Opportunistic osteoporosis screening in multi-detector CT images via local classification of textures |
title | Opportunistic osteoporosis screening in multi-detector CT images via local classification of textures |
title_full | Opportunistic osteoporosis screening in multi-detector CT images via local classification of textures |
title_fullStr | Opportunistic osteoporosis screening in multi-detector CT images via local classification of textures |
title_full_unstemmed | Opportunistic osteoporosis screening in multi-detector CT images via local classification of textures |
title_short | Opportunistic osteoporosis screening in multi-detector CT images via local classification of textures |
title_sort | opportunistic osteoporosis screening in multi-detector ct images via local classification of textures |
topic | Original Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6546649/ https://www.ncbi.nlm.nih.gov/pubmed/30830261 http://dx.doi.org/10.1007/s00198-019-04910-1 |
work_keys_str_mv | AT valentinitscha opportunisticosteoporosisscreeninginmultidetectorctimagesvialocalclassificationoftextures AT trebeschis opportunisticosteoporosisscreeninginmultidetectorctimagesvialocalclassificationoftextures AT kaesmacherj opportunisticosteoporosisscreeninginmultidetectorctimagesvialocalclassificationoftextures AT lorenzc opportunisticosteoporosisscreeninginmultidetectorctimagesvialocalclassificationoftextures AT lofflermt opportunisticosteoporosisscreeninginmultidetectorctimagesvialocalclassificationoftextures AT zimmerc opportunisticosteoporosisscreeninginmultidetectorctimagesvialocalclassificationoftextures AT baumt opportunisticosteoporosisscreeninginmultidetectorctimagesvialocalclassificationoftextures AT kirschkejs opportunisticosteoporosisscreeninginmultidetectorctimagesvialocalclassificationoftextures |