Incidental vertebral fracture prediction using neuronal network-based automatic spine segmentation and volumetric bone mineral density extraction from routine clinical CT scans
ObjectivesTo investigate vertebral osteoporotic fracture (VF) prediction by automatically extracted trabecular volumetric bone mineral density (vBMD) from routine CT, and to compare the model with fracture prevalence-based prediction models.MethodsThis single-center retrospective study included pati...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-07-01
|
| Series: | Frontiers in Endocrinology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fendo.2023.1207949/full |
| _version_ | 1797777910112714752 |
|---|---|
| author | Jannis Bodden Michael Dieckmeyer Michael Dieckmeyer Nico Sollmann Nico Sollmann Nico Sollmann Egon Burian Sebastian Rühling Maximilian T. Löffler Maximilian T. Löffler Anjany Sekuboyina Anjany Sekuboyina Anjany Sekuboyina Malek El Husseini Malek El Husseini Claus Zimmer Claus Zimmer Jan S. Kirschke Jan S. Kirschke Thomas Baum |
| author_facet | Jannis Bodden Michael Dieckmeyer Michael Dieckmeyer Nico Sollmann Nico Sollmann Nico Sollmann Egon Burian Sebastian Rühling Maximilian T. Löffler Maximilian T. Löffler Anjany Sekuboyina Anjany Sekuboyina Anjany Sekuboyina Malek El Husseini Malek El Husseini Claus Zimmer Claus Zimmer Jan S. Kirschke Jan S. Kirschke Thomas Baum |
| author_sort | Jannis Bodden |
| collection | DOAJ |
| description | ObjectivesTo investigate vertebral osteoporotic fracture (VF) prediction by automatically extracted trabecular volumetric bone mineral density (vBMD) from routine CT, and to compare the model with fracture prevalence-based prediction models.MethodsThis single-center retrospective study included patients who underwent two thoraco-abdominal CT scans during clinical routine with an average inter-scan interval of 21.7 ± 13.1 months (range 5–52 months). Automatic spine segmentation and vBMD extraction was performed by a convolutional neural network framework (anduin.bonescreen.de). Mean vBMD was calculated for levels T5-8, T9-12, and L1-5. VFs were identified by an expert in spine imaging. Odds ratios (ORs) for prevalent and incident VFs were calculated for vBMD (per standard deviation decrease) at each level, for baseline VF prevalence (yes/no), and for baseline VF count (n) using logistic regression models, adjusted for age and sex. Models were compared using Akaike’s and Bayesian information criteria (AIC & BIC).Results420 patients (mean age, 63 years ± 9, 276 males) were included in this study. 40 (25 female) had prevalent and 24 (13 female) had incident VFs. Individuals with lower vBMD at any spine level had higher odds for VFs (L1-5, prevalent VF: OR,95%-CI,p: 2.2, 1.4–3.5,p=0.001; incident VF: 3.5, 1.8–6.9,p<0.001). In contrast, VF status (2.15, 0.72–6.43,p=0.170) and count (1.38, 0.89–2.12,p=0.147) performed worse in incident VF prediction. Information criteria revealed best fit for vBMD-based models (AIC vBMD=165.2; VF status=181.0; count=180.7).ConclusionsVF prediction based on automatically extracted vBMD from routine clinical MDCT outperforms prediction models based on VF status and count. These findings underline the importance of opportunistic quantitative osteoporosis screening in clinical routine MDCT data. |
| first_indexed | 2024-03-12T23:11:17Z |
| format | Article |
| id | doaj.art-25cba528f3c04178b3a00e66a34a0115 |
| institution | Directory Open Access Journal |
| issn | 1664-2392 |
| language | English |
| last_indexed | 2024-03-12T23:11:17Z |
| publishDate | 2023-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Endocrinology |
| spelling | doaj.art-25cba528f3c04178b3a00e66a34a01152023-07-18T03:30:36ZengFrontiers Media S.A.Frontiers in Endocrinology1664-23922023-07-011410.3389/fendo.2023.12079491207949Incidental vertebral fracture prediction using neuronal network-based automatic spine segmentation and volumetric bone mineral density extraction from routine clinical CT scansJannis Bodden0Michael Dieckmeyer1Michael Dieckmeyer2Nico Sollmann3Nico Sollmann4Nico Sollmann5Egon Burian6Sebastian Rühling7Maximilian T. Löffler8Maximilian T. Löffler9Anjany Sekuboyina10Anjany Sekuboyina11Anjany Sekuboyina12Malek El Husseini13Malek El Husseini14Claus Zimmer15Claus Zimmer16Jan S. Kirschke17Jan S. Kirschke18Thomas Baum19Department of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, GermanyDepartment of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, GermanyDepartment of Diagnostic and Interventional Neuroradiology, University of Bern, Bern, SwitzerlandDepartment of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, GermanyTUM-Neuroimaging Center, Klinikum rechts der Isar, Technical University of Munich, Munich, GermanyDepartment of Diagnostic and Interventional Radiology, University Hospital Ulm, Ulm, GermanyDepartment of Diagnostic and Interventional Radiology, School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, GermanyDepartment of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, GermanyDepartment of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, GermanyDepartment of Diagnostic and Interventional Radiology, University Medical Center Freiburg, Freiburg im Breisgau, GermanyDepartment of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, GermanyDepartment of Informatics, Technical University of Munich, Munich, GermanyMunich School of BioEngineering, Technical University of Munich, Munich, GermanyDepartment of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, GermanyDepartment of Informatics, Technical University of Munich, Munich, GermanyDepartment of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, GermanyTUM-Neuroimaging Center, Klinikum rechts der Isar, Technical University of Munich, Munich, GermanyDepartment of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, GermanyTUM-Neuroimaging Center, Klinikum rechts der Isar, Technical University of Munich, Munich, GermanyDepartment of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, GermanyObjectivesTo investigate vertebral osteoporotic fracture (VF) prediction by automatically extracted trabecular volumetric bone mineral density (vBMD) from routine CT, and to compare the model with fracture prevalence-based prediction models.MethodsThis single-center retrospective study included patients who underwent two thoraco-abdominal CT scans during clinical routine with an average inter-scan interval of 21.7 ± 13.1 months (range 5–52 months). Automatic spine segmentation and vBMD extraction was performed by a convolutional neural network framework (anduin.bonescreen.de). Mean vBMD was calculated for levels T5-8, T9-12, and L1-5. VFs were identified by an expert in spine imaging. Odds ratios (ORs) for prevalent and incident VFs were calculated for vBMD (per standard deviation decrease) at each level, for baseline VF prevalence (yes/no), and for baseline VF count (n) using logistic regression models, adjusted for age and sex. Models were compared using Akaike’s and Bayesian information criteria (AIC & BIC).Results420 patients (mean age, 63 years ± 9, 276 males) were included in this study. 40 (25 female) had prevalent and 24 (13 female) had incident VFs. Individuals with lower vBMD at any spine level had higher odds for VFs (L1-5, prevalent VF: OR,95%-CI,p: 2.2, 1.4–3.5,p=0.001; incident VF: 3.5, 1.8–6.9,p<0.001). In contrast, VF status (2.15, 0.72–6.43,p=0.170) and count (1.38, 0.89–2.12,p=0.147) performed worse in incident VF prediction. Information criteria revealed best fit for vBMD-based models (AIC vBMD=165.2; VF status=181.0; count=180.7).ConclusionsVF prediction based on automatically extracted vBMD from routine clinical MDCT outperforms prediction models based on VF status and count. These findings underline the importance of opportunistic quantitative osteoporosis screening in clinical routine MDCT data.https://www.frontiersin.org/articles/10.3389/fendo.2023.1207949/fullosteoporosisosteoporotic fracturesbone densitytomographyx-ray computedartificial intelligence |
| spellingShingle | Jannis Bodden Michael Dieckmeyer Michael Dieckmeyer Nico Sollmann Nico Sollmann Nico Sollmann Egon Burian Sebastian Rühling Maximilian T. Löffler Maximilian T. Löffler Anjany Sekuboyina Anjany Sekuboyina Anjany Sekuboyina Malek El Husseini Malek El Husseini Claus Zimmer Claus Zimmer Jan S. Kirschke Jan S. Kirschke Thomas Baum Incidental vertebral fracture prediction using neuronal network-based automatic spine segmentation and volumetric bone mineral density extraction from routine clinical CT scans Frontiers in Endocrinology osteoporosis osteoporotic fractures bone density tomography x-ray computed artificial intelligence |
| title | Incidental vertebral fracture prediction using neuronal network-based automatic spine segmentation and volumetric bone mineral density extraction from routine clinical CT scans |
| title_full | Incidental vertebral fracture prediction using neuronal network-based automatic spine segmentation and volumetric bone mineral density extraction from routine clinical CT scans |
| title_fullStr | Incidental vertebral fracture prediction using neuronal network-based automatic spine segmentation and volumetric bone mineral density extraction from routine clinical CT scans |
| title_full_unstemmed | Incidental vertebral fracture prediction using neuronal network-based automatic spine segmentation and volumetric bone mineral density extraction from routine clinical CT scans |
| title_short | Incidental vertebral fracture prediction using neuronal network-based automatic spine segmentation and volumetric bone mineral density extraction from routine clinical CT scans |
| title_sort | incidental vertebral fracture prediction using neuronal network based automatic spine segmentation and volumetric bone mineral density extraction from routine clinical ct scans |
| topic | osteoporosis osteoporotic fractures bone density tomography x-ray computed artificial intelligence |
| url | https://www.frontiersin.org/articles/10.3389/fendo.2023.1207949/full |
| work_keys_str_mv | AT jannisbodden incidentalvertebralfracturepredictionusingneuronalnetworkbasedautomaticspinesegmentationandvolumetricbonemineraldensityextractionfromroutineclinicalctscans AT michaeldieckmeyer incidentalvertebralfracturepredictionusingneuronalnetworkbasedautomaticspinesegmentationandvolumetricbonemineraldensityextractionfromroutineclinicalctscans AT michaeldieckmeyer incidentalvertebralfracturepredictionusingneuronalnetworkbasedautomaticspinesegmentationandvolumetricbonemineraldensityextractionfromroutineclinicalctscans AT nicosollmann incidentalvertebralfracturepredictionusingneuronalnetworkbasedautomaticspinesegmentationandvolumetricbonemineraldensityextractionfromroutineclinicalctscans AT nicosollmann incidentalvertebralfracturepredictionusingneuronalnetworkbasedautomaticspinesegmentationandvolumetricbonemineraldensityextractionfromroutineclinicalctscans AT nicosollmann incidentalvertebralfracturepredictionusingneuronalnetworkbasedautomaticspinesegmentationandvolumetricbonemineraldensityextractionfromroutineclinicalctscans AT egonburian incidentalvertebralfracturepredictionusingneuronalnetworkbasedautomaticspinesegmentationandvolumetricbonemineraldensityextractionfromroutineclinicalctscans AT sebastianruhling incidentalvertebralfracturepredictionusingneuronalnetworkbasedautomaticspinesegmentationandvolumetricbonemineraldensityextractionfromroutineclinicalctscans AT maximiliantloffler incidentalvertebralfracturepredictionusingneuronalnetworkbasedautomaticspinesegmentationandvolumetricbonemineraldensityextractionfromroutineclinicalctscans AT maximiliantloffler incidentalvertebralfracturepredictionusingneuronalnetworkbasedautomaticspinesegmentationandvolumetricbonemineraldensityextractionfromroutineclinicalctscans AT anjanysekuboyina incidentalvertebralfracturepredictionusingneuronalnetworkbasedautomaticspinesegmentationandvolumetricbonemineraldensityextractionfromroutineclinicalctscans AT anjanysekuboyina incidentalvertebralfracturepredictionusingneuronalnetworkbasedautomaticspinesegmentationandvolumetricbonemineraldensityextractionfromroutineclinicalctscans AT anjanysekuboyina incidentalvertebralfracturepredictionusingneuronalnetworkbasedautomaticspinesegmentationandvolumetricbonemineraldensityextractionfromroutineclinicalctscans AT malekelhusseini incidentalvertebralfracturepredictionusingneuronalnetworkbasedautomaticspinesegmentationandvolumetricbonemineraldensityextractionfromroutineclinicalctscans AT malekelhusseini incidentalvertebralfracturepredictionusingneuronalnetworkbasedautomaticspinesegmentationandvolumetricbonemineraldensityextractionfromroutineclinicalctscans AT clauszimmer incidentalvertebralfracturepredictionusingneuronalnetworkbasedautomaticspinesegmentationandvolumetricbonemineraldensityextractionfromroutineclinicalctscans AT clauszimmer incidentalvertebralfracturepredictionusingneuronalnetworkbasedautomaticspinesegmentationandvolumetricbonemineraldensityextractionfromroutineclinicalctscans AT janskirschke incidentalvertebralfracturepredictionusingneuronalnetworkbasedautomaticspinesegmentationandvolumetricbonemineraldensityextractionfromroutineclinicalctscans AT janskirschke incidentalvertebralfracturepredictionusingneuronalnetworkbasedautomaticspinesegmentationandvolumetricbonemineraldensityextractionfromroutineclinicalctscans AT thomasbaum incidentalvertebralfracturepredictionusingneuronalnetworkbasedautomaticspinesegmentationandvolumetricbonemineraldensityextractionfromroutineclinicalctscans |