Automatic opportunistic osteoporosis screening in routine CT: improved prediction of patients with prevalent vertebral fractures compared to DXA
Open accessAbstract
Objectives: To compare spinal bone measures derived from automatic and manual assessment in routine CT with dual energy X-ray absorptiometry (DXA) in their association with prevalent osteoporotic vertebral fractures using our fully automated framework (https://anduin.bonescreen.de) to assess various bone measures in clinical CT. Methods: We included 192 patients (141 women, 51 men; age 70.2 ± 9.7 years) who had lumbar DXA and CT available (within 1 year). Automatic assessment of spinal bone measures in CT included segmentation of vertebrae using a convolutional neural network (CNN), reduction to the vertebral body, and extraction of bone mineral content (BMC), trabecular and integral volumetric bone mineral density (vBMD), and CT-based areal BMD (aBMD) using asynchronous calibration. Moreover, trabecular bone was manually sampled (manual vBMD). Results: A total of 148 patients (77%) had vertebral fractures and significantly lower values in all bone measures compared to patients without fractures (p ≤ 0.001). Except for BMC, all CT-based measures performed significantly better as predictors for vertebral fractures compared to DXA (e.g., AUC = 0.885 for trabecular vBMD and AUC = 0.86 for integral vBMD vs. AUC = 0.668 for DXA aBMD, respectively; both p < 0.001). Age- and sex-adjusted associations with fracture status were strongest for manual vBMD (OR = 7.3, [95%] CI 3.8–14.3) followed by automatically assessed trabecular vBMD (OR = 6.9, CI 3.5–13.4) and integral vBMD (OR = 4.3, CI 2.5–7.6). Diagnostic cutoffs of integral vBMD for osteoporosis (< 160 mg/cm 3) or low bone mass (160 ≤ BMD < 190 mg/cm 3) had sensitivity (84%/41%) and specificity (78%/95%) similar to trabecular vBMD. Conclusions: Fully automatic osteoporosis screening in routine CT of the spine is feasible. CT-based measures can better identify individuals with reduced bone mass who suffered from vertebral fractures than DXA. Key Points: • Opportunistic osteoporosis screening of spinal bone measures derived from clinical routine CT is feasible in a fully automatic fashion using a deep learning-driven framework (https://anduin.bonescreen.de). • Manually sampled volumetric BMD (vBMD) and automatically assessed trabecular and integral vBMD were the best predictors for prevalent vertebral fractures. • Except for bone mineral content, all CT-based bone measures performed significantly better than DXA-based measures. • We introduce diagnostic thresholds of integral vBMD for osteoporosis (< 160 mg/cm3) and low bone mass (160 ≤ BMD < 190 mg/cm3) with almost equal sensitivity and specificity compared to conventional thresholds of quantitative CT as proposed by the American College of Radiology (osteoporosis < 80 mg/cm3).
AI snapshot
Written from the paper’s full text.
TL;DR
This retrospective study compared fully automatic CT-derived spinal bone measures with DXA for identifying prevalent osteoporotic vertebral fractures in 192 patients. CT-based volumetric measures, especially trabecular and integral vBMD, predicted prevalent fractures better than DXA, and the authors propose integral vBMD thresholds for osteoporosis and low bone mass.
Key findings
- Among 192 patients (141 women, 51 men; mean age 70.2 ± 9.7 years), 148 (77%) had at least one prevalent vertebral fracture; fractured patients were older (72.0 ± 9.3 vs. 64.3 ± 8.6 years, p < 0.001) and had significantly lower values in all bone measures (p ≤ 0.001).
- Except for BMC, all CT-based measures predicted prevalent vertebral fractures significantly better than DXA aBMD: AUC = 0.885 for trabecular vBMD, 0.86 for integral vBMD, and 0.894 for manual vBMD vs. 0.668 for DXA aBMD (p < 0.001 for vBMD comparisons); CT-based BMC was not significantly different from DXA aBMD or T-score.
- Age- and sex-adjusted associations with fracture status were strongest for manual vBMD (OR = 7.3, 95% CI 3.8–14.3), followed by automatically assessed trabecular vBMD (OR = 6.9, CI 3.5–13.4) and integral vBMD (OR = 4.3, CI 2.5–7.6); DXA T-score and aBMD each had OR = 1.9 (CI 1.3–2.8).
- Proposed integral vBMD thresholds were osteoporosis < 160 mg/cm³ and low bone mass 160 ≤ BMD < 190 mg/cm³, with sensitivity/specificity of 84%/78% and 41%/95%, respectively, similar to trabecular vBMD (86%/78% and 41%/98%).
Methods
- Monocentric retrospective study: 360 patients were identified, exclusions left 192 with lumbar DXA and CT available within 1 year; prevalent vertebral fractures were classified using the Genant semiquantitative technique (grade ≥ 1).
- CT bone measures used a fully automatic framework: CNN-based vertebral segmentation, reduction to vertebral bodies, asynchronous HU-to-BMD calibration with contrast correction, and extraction of integral vBMD, trabecular vBMD (eroded by 5 mm), BMC, and CT-based aBMD; manual trabecular vBMD was also sampled.
- Statistical analysis used t tests and chi-squared tests for group comparisons, logistic regression for odds ratios per 1 SD change (unadjusted and age/sex-adjusted), and ROC AUC analysis with DeLong’s test for correlated ROC curves; significance was p < 0.05.
Limitations
- Stated: retrospective selection bias toward elderly, mainly neurosurgical and oncological patients who already had both CT and DXA within 1 year, meaning osteoporosis was already suspected; the study assessed prevalent, not incident, vertebral fractures, so the new integral vBMD thresholds require validation in follow-up fracture-risk studies.
- Evident: the single-center design and high fracture prevalence (77%) may limit generalizability, and the automatic framework and proposed thresholds were not externally validated in this paper.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
8 of 20 cited sources checked · 3 supported · 1 flagged · accuracy not yet measured
- Premisecitation
A framework for fully automatic segmentation of vertebrae in any CT dataset within several seconds was recently introduced.
“We recently introduced a framework for fully automatic segmentation of vertebrae in any CT dataset within several seconds [16, 17].”
Quote in the paperSubstantial claim1 of 2 sources checked- cites [16] Löffler MT, Sekuboyina A, Jacob A et al (2020) A vertebral segmentation dataset with fracture grading. Radiol Artif Intell 2:e190138. https://doi.org/10.1148/ryai.2020190138 source
The Materials and Methods section (Vertebral Segmentation; page unavailable) describes a framework that predicts vertebral segmentations from CT images. It does not establish that the framework works on any CT dataset or completes segmentation within several seconds, and the dataset’s final masks were manually refined. (LLM, conf=0.87)
Experimental — accuracy not yet measured - cites [17] Sekuboyina A, Bayat A, Husseini ME et al (2020) VerSe: a vertebrae labelling and segmentation benchmark. arXiv:200109193 [cs, eess]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Findingown data
All bone measures were statistically significant predictors of prevalent vertebral fractures in AUC analysis.
“AUC analysis showed that all bone measures were statistically significant predictors of prevalent vertebral fractures (Table 3, Fig. 4).”
Quote in the paperNot a substantial claim - Findingown data
CT-based BMC showed no significant difference in discriminatory power compared to DXA-based aBMD or T-score (AUC = 0.735 vs 0.668 or 0.67).
“Only CT-based BMC showed no significant difference in discriminatory power to DXA-based aBMD or T-score (AUC = 0.735 vs. 0.668 or 0.67, respectively).”
Quote in the paperNot a substantial claim - Findingown data
CT-based aBMD slightly underestimated aBMD compared to DXA (bias −0.054 and −0.015 g/cm2 at L2 and L3).
“Bland-Altman plots showed a bias of − 0.054 and − 0.015 g/cm2 at L2 and L3, respectively, for CT-based aBMD (Supplementary Fig. 1). Thus, CT-based assessment seemed to slightly underestimate aBMD compared to DXA.”
Quote in the paperNot a substantial claim - Findingown data
Except for BMC, all CT-based bone measures showed significantly better discriminatory power for the prevalence of vertebral fractures compared to DXA-based measures.
“Except for BMC, all CT-based bone measures showed significantly better discriminatory power for the prevalence of vertebral fractures compared to DXA-based measures.”
Quote in the paperSubstantial claim
- Findingown data
Patients with vertebral fractures were significantly older than those without fractures (72.0 ± 9.3 vs 64.3 ± 8.6 years, p < 0.001).
“Fractured patients (107 women, 41 men; Fig. 2) were significantly older (72.0 ± 9.3 years vs. 64.3 ± 8.6 years, p < 0.001)”
Quote in the paperNot a substantial claim - Findingown data
The finding that trabecular vBMD offers better discriminatory power for prevalent vertebral fractures than aBMD was reproduced on modern scanner hardware.
“Looking 25 years back in time, the insight that trabecular vBMD (QCT; AUC = 0.81) offers better discriminatory power for the prevalence of vertebral fractures than aBMD (DXA; AUC = 0.65) appears familiar [31]. Here, we were able to reproduce these results on modern scanner hardware.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [31] Yu W, Glüer CC, Grampp S et al (1995) Spinal bone mineral assessment in postmenopausal women: a comparison between dual X-ray absorptiometry and quantitative computed tomography. Osteoporos Int 5:433–439 source
- Findingown data
Prevalent vertebral fractures were significantly associated with all DXA- and CT-based bone measures irrespective of adjustment for age and sex.
“Prevalent vertebral fractures were significantly associated with all DXA- and CT-based bone measures irrespective of adjustment for age and sex (Table 2).”
Quote in the paperSubstantial claim - Findingown data
148 patients (77%) had at least one prevalent osteoporotic vertebral fracture.
“This yielded a final study group of 192 patients, with 148 patients (77%) showing at least one prevalent osteoporotic vertebral fracture.”
Quote in the paperNot a substantial claim - Findingown data
Diagnostic cutoffs of integral vBMD for osteoporosis (< 160 mg/cm3) or low bone mass (160 ≤ BMD < 190 mg/cm3) had sensitivity (84%/41%) and specificity (78%/95%) similar to trabecular vBMD.
“Diagnostic cutoffs of integral vBMD for osteoporosis (< 160 mg/cm3) or low bone mass (160 ≤ BMD < 190 mg/cm3) had sensitivity (84%/41%) and specificity (78%/95%) similar to trabecular vBMD.”
Quote in the paperSubstantial claim - Findingown data
CT-based bone measures had stronger associations with prevalent vertebral fractures than DXA-based measures (adjusted ORs ranging from 2.5 for CT-based aBMD to 7.3 for manual vBMD vs 1.9 for DXA-based T-score and aBMD).
“However, there were considerable differences with stronger associations for all CT-based measures (ranging from OR = 2.5, 95% CI 1.7–3.9 for adjusted CT-based aBMD to OR = 7.3, 95% CI 3.8–14.3 for adjusted manual vBMD) compared to DXA-based measures (OR = 1.9, 95% CI 1.3–2.8 each for adjusted DXA-based T-score and aBMD) and for both adjusted and unadjusted ORs (Table 2).”
Quote in the paperSubstantial claim - Interpretationown data
CT-based measures can better identify individuals with reduced bone mass who suffered from vertebral fractures than DXA.
“CT-based measures can better identify individuals with reduced bone mass who suffered from vertebral fractures than DXA.”
Quote in the paperSubstantial claim - Interpretationreasoning
Because BMC is the only non-density measure of bone mass considered, the error introduced by bone mass without structural support for the vertebra's compressive strength (e.g., spondylophytes) is not alleviated.
“Of note, BMC is the only non-density measure of bone mass considered in this study. Therefore, the error introduced by bone mass without structural support for the vertebra’s compressive strength (e.g., spondylophytes) is not alleviated in any way.”
Quote in the paperNot a substantial claim - Study design and conductreasoning
The study has a selection bias of elderly hospital inpatients, mainly neurosurgical and oncological, because patients were required to have received both multidetector CT and DXA within 1 year.
“There are limitations to this retrospective study. As mentioned before, there was a selection bias of elderly and mainly neurosurgical and oncological patients because it was required that they had received both multidetector CT and DXA within 1 year.”
Quote in the paperSubstantial claim - Interpretationnone given
Fully automatic osteoporosis screening in routine CT of the spine is feasible.
“Fully automatic osteoporosis screening in routine CT of the spine is feasible.”
Quote in the paperSubstantial claim - Premisecitation
DXA has inherent inaccuracies.
“emphasizing the inherent inaccuracies of DXA [13]”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [13] Bolotin HH (2007) DXA in vivo BMD methodology: an erroneous and misleading research and clinical gauge of bone mineral status, bone fragility, and bone remodelling. Bone 41:138–154. https://doi.org/10.1016/j.bone.2007.02.022 source
- Premisecitation
Osteoporotic vertebral fractures remain clinically silent with only 15-30% coming to clinical attention.
“Moreover, osteoporotic vertebral fractures remain clinically silent with only 15–30% coming to clinical attention [11].”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [11] Fink HA, Milavetz DL, Palermo L et al (2005) What proportion of incident radiographic vertebral deformities is clinically diagnosed and vice versa? J Bone Miner Res 20:1216–1222. https://doi.org/10.1359/JBMR.050314 source
- Study design and conductown data
CT-based aBMD correlated well with DXA-based aBMD at L2 and L3 (R2 = 0.814 and 0.739) in a sample of 29 patients.
“Good correlation between CT-based and DXA-based aBMD of L2 and L3 (R2 = 0.814 and R2 = 0.739, respectively) could be shown for a sample group of 29 patients (22 women, mean age 61.5 ± 13.6 years; Suppl. Fig. 1).”
Quote in the paperSubstantial claim- The authors state this as an assumption: CT-based aBMD has superior accuracy to DXA because of the 3-dimensional character of CT scans, despite being a monoenergetic technique.
- Classified as probably not a substantial claim. 12
- May combine two claims. 15
- The quote only partly states this claim. 1
Classified as probably not a substantial claim.
PremisecitationPreviously published HU-to-BMD conversion equations were used for all CT scanners in this study.
“Previously published HU-to-BMD conversion equations were used for all CT scanners in this study [22].”
Quote in the paperSubstantial claim1 of 1 sources checked- cites [22] Löffler MT, Jacob A, Valentinitsch A et al (2019) Improved prediction of incident vertebral fractures using opportunistic QCT compared to DXA. Eur Radiol. https://doi.org/10.1007/s00330-019-06018-w source
The Methods (Opportunistic QCT) state that HU-to-BMD conversion equations were calculated by linear regression using phantom measurements for the scanners in this study. Table 4 (Results) lists the resulting scanner-specific equations. The paper does not describe using previously published conversion equations for all scanners; the previously investigated values mentioned in Methods are contrast-enhancement correction offsets. (LLM, conf=0.92)
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measured
Classified as probably not a substantial claim. May combine two claims.
PremisecitationVertebrae were automatically segmented in CT scans using a framework of CNNs that identifies the spine, labels each vertebral body, and creates segmentation masks.
“First, vertebrae were automatically segmented in CT scans using a framework of CNNs that identifies the spine, labels each vertebral body, and creates segmentation masks [16].”
Quote in the paperSubstantial claim1 of 1 sources checked- cites [16] Löffler MT, Sekuboyina A, Jacob A et al (2020) A vertebral segmentation dataset with fracture grading. Radiol Artif Intell 2:e190138. https://doi.org/10.1148/ryai.2020190138 source
Classified as probably not a substantial claim. May combine two claims.
PremisecitationBesides hip fractures, vertebral fractures are the most common and most consequential osteoporotic fractures.
“Besides hip fractures, vertebral fractures are the most common and most consequential osteoporotic fractures [4].”
Quote in the paperSubstantial claim1 of 1 sources checked- cites [4] Ensrud KE (2013) Epidemiology of fracture risk with advancing age. J Gerontol A Biol Sci Med Sci 68:1236–1242. https://doi.org/10.1093/gerona/glt092 source
The Vertebral Fractures section calls vertebral fractures the most common manifestation of osteoporosis and describes associations with pain, disability, mortality, and subsequent fractures. It does not establish that they are the most consequential after hip fractures; it reports that clinical vertebral fractures accounted for only 6% of fracture-related costs in the United States in 2005. (LLM, conf=0.84)
Experimental — accuracy not yet measured
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
InterpretationreasoningDifferences in the study population, focus on prevalent instead of incident fractures, and better sensitivity to detect fractures by using ≤1-mm instead of 2.5-mm axial slices could lead to relatively higher ORs compared to Allaire et al.
“These differences in the study population—paired with the focus on prevalent instead of incident fractures and better sensitivity to detect fractures by using ≤ 1-mm instead of 2.5-mm axial slices [26]—could lead to the relatively higher ORs compared to Allaire et al (OR = 2.7 vs. 1.6 for CT-based aBMD, OR = 4.8 vs. 2.8 for integral vBMD, and OR = 6.8 vs. 2.1 for trabecular vBMD) [27]; though, CT–”
Quote in the paperNot a substantial claim1 of 2 sources checked- cites [26] Bauer JS, Müller D, Ambekar A et al (2006) Detection of osteoporotic vertebral fractures using multidetector CT. Osteoporos Int 17:608–615. https://doi.org/10.1007/s00198-005-0023-8 source
- cites [27] Allaire BT, Lu D, Johannesdottir F et al (2019) Prediction of incident vertebral fracture using CT-based finite element analysis. Osteoporos Int 30:323–331. https://doi.org/10.1007/s00198-018-4716-1 source
The Methods and Results identify Allaire et al.’s study as examining incident vertebral fractures, and the Results report an OR of 1.6 for CT-based aBMD. Our copy says integral and trabecular vBMD were associated with incident fracture, but the passages do not give the specific ORs of 2.8 and 2.1 attributed to Allaire et al. The proposed reasons for the higher ORs are the citing authors’ interpretation; the slice-thickness comparison is attached to a different citation. (LLM, conf=0.82)
Experimental — accuracy not yet measured
May combine two claims.
PremisecitationThere is significant variability in access to DXA services and many fall short of international quality standards.
“Second, there is significant variability in the access to DXA services and many fall short of international quality standards [14].”
Quote in the paperSubstantial claim1 of 1 sources checked- cites [14] Clynes MA, Westbury LD, Dennison EM et al (2020) Bone densitometry worldwide: a global survey by the ISCD and IOF. Osteoporos Int 31:1779–1786. https://doi.org/10.1007/s00198-020-05435-8 source
Classified as probably not a substantial claim.
PremisecitationBias of BMD values due to intravenous injection of contrast medium was corrected for using linear correction equations for arterial and portal/venous contrast phases.
“Bias of BMD values due to intravenous injection of contrast medium was corrected for using linear correction equations for arterial and portal/venous contrast phases [23].”
Quote in the paperSubstantial claim1 of 1 sources checked- cites [23] Kaesmacher J, Liebl H, Baum T, Kirschke JS (2017) Bone mineral density estimations from routine multidetector computed tomography: a comparative study of contrast and calibration effects. J Comput Assist Tomogr 41:217–223. https://doi.org/10.1097/RCT.0000000000000518 source
May combine two claims.
FindingcitationCompared to a study of incident vertebral fractures in the MrOS cohort, the AUCs reported here are higher for trabecular vBMD (0.885 vs 0.79) but lower for DXA-based aBMD (0.668 vs 0.72).
“Compared to a study of incident vertebral fractures in the Osteoporotic Fractures in Men (MrOS) Study cohort of elderly men, the AUCs we report seem considerably higher for trabecular vBMD (AUC = 0.885 vs. 0.79), but lower for DXA-based aBMD (AUC = 0.668 vs. 0.72) [28].”
Quote in the paperNot a substantial claim1 of 1 sources checked- cites [28] Chalhoub D, Orwoll ES, Cawthon PM et al (2016) Areal and volumetric bone mineral density and risk of multiple types of fracture in older men. Bone 92:100–106. https://doi.org/10.1016/j.bone.2016.08.014 source
The Discussion (page unavailable) identifies this as a MrOS study and reports that trabecular spine vBMD predicted spine fractures better than DXA-based spine aBMD. The cited paper passages do not give the specific AUCs of 0.79 and 0.72, so those numerical comparisons are not verified by our copy. (LLM, conf=0.78)
Experimental — accuracy not yet measured
May combine two claims.
Findingown dataAge- and sex-adjusted association with fracture status was strongest for manual vBMD (OR = 7.3, 95% CI 3.8-14.3), followed by automatically assessed trabecular vBMD (OR = 6.9, 95% CI 3.5-13.4) and integral vBMD (OR = 4.3, 95% CI 2.5-7.6).
“Age- and sex-adjusted associations with fracture status were strongest for manual vBMD (OR = 7.3, [95%] CI 3.8–14.3) followed by automatically assessed trabecular vBMD (OR = 6.9, CI 3.5–13.4) and integral vBMD (OR = 4.3, CI 2.5–7.6).”
Quote in the paperSubstantial claimMay combine two claims.
Findingown dataAll automatically assessed CT-based bone measures had a highly significant association with the prevalence of osteoporotic vertebral fractures, with no significant differences between automatic and manual measurements.
“All automatically assessed CT-based bone measures had a highly significant association with the prevalence of osteoporotic vertebral fractures with no significant differences between automatic and manual measurements.”
Quote in the paperSubstantial claimMay combine two claims.
Findingown dataPatients with vertebral fractures had significantly lower values in all bone measures (DXA-based aBMD, CT-based aBMD, manual vBMD, trabecular vBMD, integral vBMD, and BMC, p < 0.001 each; DXA-based T-score, p = 0.001) compared to patients without fractures.
“and showed significantly lower values in all bone measures (DXA-based aBMD, CT-based aBMD, manual vBMD, trabecular vBMD, integral vBMD, and BMC, p < 0.001 each; DXA-based T-score, p = 0.001) compared to patients without fractures”
Quote in the paperSubstantial claimClassified as probably not a substantial claim.
Findingown dataThe study included 192 patients (141 women, 51 men; mean age 70.2 ± 9.7 years) who had lumbar DXA and CT available within 1 year.
“We included 192 patients (141 women, 51 men; age 70.2 ± 9.7 years) who had lumbar DXA and CT available (within 1 year).”
- Also stated in: § Results · plain
“Overall, 192 patients (141 women, 51 men) with a mean age of 70.2 ± 9.7 years were included in this study.”
Quote in the paperSubstantial claim- Also stated in: § Results · plain
May combine two claims. The quote only partly states this claim.
Findingown dataMost CT-based measures performed significantly better than DXA in AUC for predicting prevalent vertebral fractures; e.g., DXA-based aBMD AUC = 0.668 vs integral vBMD 0.860, trabecular vBMD 0.885, manual vBMD 0.894, p < 0.001 each.
“However, most CT-based measures performed significantly better than DXA, e.g., when comparing DXA-based aBMD with intergral, trabecual, or manual vBMD (AUC = 0.668 vs. 0.735, 0.860, or 0.885, respectively, p < 0.001 each; Table 3).”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
InterpretationreasoningThe high prevalence of at least mild (Genant grade 1) osteoporotic vertebral fractures (77%) is not surprising because all patients received DXA scans, implicating that osteoporosis was already suspected.
“We reported on elderly patients that all received DXA scans, thereby implicating that osteoporosis was already suspected; thus, the high prevalence of at least mild (Genant grade 1) osteoporotic vertebral fractures (77%) is not surprising.”
Quote in the paperNot a substantial claimMay combine two claims.
PremisecitationOpportunistic quantitative evaluation of preexisting clinical routine CT entails neither additional costs nor radiation exposure.
“Opportunistic quantitative evaluation of preexisting clinical routing CT entails neither additional costs nor radiation exposure [15].”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [15] Löffler MT, Sollmann N, Mei K et al (2020) X-Ray-based quantitative osteoporosis imaging at the spine. Osteoporos Int 31:233–250. https://doi.org/10.1007/s00198-019-05212-2 source
Classified as probably not a substantial claim.
Study design and conductcitationCT scans were screened for prevalent osteoporotic vertebral fractures using the semi-quantitative technique by Genant.
“CT scans of the remaining 258 patients were screened for prevalent osteoporotic vertebral fractures using the semi-quantitative technique by Genant [18].”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [18] Genant HK, Wu CY, van Kuijk C, Nevitt MC (1993) Vertebral fracture assessment using a semiquantitative technique. J Bone Miner Res 8:1137–1148. https://doi.org/10.1002/jbmr.5650080915 source
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Study design and conductnone givenThe local institutional review board approved the monocentric retrospective study and waived written informed consent.
“The local institutional review board approved this monocentric retrospective study (ethics committee’s reference number 27/19S/SR) and waived written informed consent.”
Quote in the paperNot a substantial claimClassified as probably not a substantial claim.
PremisecitationThe standard screening method includes assessing clinical risk factors and measuring areal bone mineral density (aBMD) using dual-energy X-ray absorptiometry (DXA).
“To date, the standard screening method includes assessing clinical risk factors and measuring areal bone mineral density (aBMD) using dual-energy X-ray absorptiometry (DXA) [1].”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [1] NIH Consensus Development Panel on Osteoporosis Prevention, Diagnosis, and Therapy (2001) Osteoporosis prevention, diagnosis, and therapy. JAMA 285:785–795 source
Classified as probably not a substantial claim.
PremisecitationFor trabecular vBMD, the diagnostic thresholds for osteoporosis (BMD < 80 mg/cm3) and for low bone mass (80 ≤ BMD ≤ 120 mg/cm3) proposed by the American College of Radiology (ACR) were used.
“For trabecular vBMD, we used the diagnostic thresholds for osteoporosis (BMD < 80 mg/cm3) and for low bone mass (80 ≤ BMD ≤ 120 mg/cm3) proposed by the American College of Radiology (ACR) [24].”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [24] American College of Radiology (2018) ACR–SPR–SSR practice parameter for the performance of musculoskeletal quantitative computed tomography (QCT). American College of Radiology, Reston. Available via https://www.acr.org/-/media/ACR/Files/Practice-Parameters/QCT.pdf?la=en. Accessed 7 Nov 2018
Not checked in the free run.
May combine two claims.
PremisecitationLess than half of women (44%) and even fewer men (21%) with osteoporotic fractures exhibited low aBMD in a large observational study.
“First, less than half of women (44%) and even fewer men (21%) with osteoporotic fractures exhibited low aBMD in a large observational study [12]”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [12] Schuit SCE, van der Klift M, Weel AEAM et al (2004) Fracture incidence and association with bone mineral density in elderly men and women: the Rotterdam Study. Bone 34:195–202 source
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Study design and conductcitationDXA scans were performed by trained technologists and quality was assured through evaluation by experienced physicians following current recommendations.
“Scans were performed by trained technologists and quality was assured through evaluation by experienced physicians following current recommendations [19].”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites [19] Shepherd JA, Schousboe JT, Broy SB, Engelke K, Leslie WD (2015) Executive summary of the 2015 ISCD Position Development Conference on Advanced Measures From DXA and QCT: fracture prediction beyond BMD. J Clin Densitom 18:274–286. https://doi.org/10.1016/j.jocd.2015.06.013 source
May combine two claims.
PremisecitationQuantitative computed tomography (QCT) has limited availability, is more expensive, and is associated with a substantially higher radiation dose (>100-fold).
“Yet, other methods of bone densitometry exhibit even more disadvantages: quantitative computed tomography (QCT) has limited availability, is more expensive, and is associated with a substantially higher radiation dose (> 100-fold) [15].”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [15] Löffler MT, Sollmann N, Mei K et al (2020) X-Ray-based quantitative osteoporosis imaging at the spine. Osteoporos Int 31:233–250. https://doi.org/10.1007/s00198-019-05212-2 source
The authors state this as an assumption.
CT-based aBMD has superior accuracy to DXA because of the 3-dimensional character of CT scans, despite being a monoenergetic technique.
“We chose this approach to take advantage of the 3-dimensional character of CT scans compared to DXA, thus postulating its superior accuracy notwithstanding the fact that it is a monoenergetic technique.”
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
AUCs are assigned to the wrong CT measures
MinorThe results assign AUCs of 0.735, 0.860, and 0.885 to integral, trabecular, and manual vBMD, respectively. Table 3 instead reports 0.86, 0.885, and 0.894 for those measures; 0.735 belongs to BMC.
“when comparing DXA-based aBMD with intergral, trabecual, or manual vBMD (AUC = 0.668 vs. 0.735, 0.860, or 0.885, respectively, p < 0.001 each; Table 3).”
“| CT-Based BMC | 0.735 (0.653–0.818) | n.s. | n.s. | | Integral vBMD | 0.86 (0.801–0.92) | p < 0.001 | p < 0.001 | | Trabecular vBMD | 0.885 (0.833–0.938) | p < 0.001 | p < 0.001 | | Manual vBMD | 0.894 (0.841–0.947) | p < 0.001 | p = 0.003 |”
A T-score of −2.5 is classified as both low bone mass and osteoporosis
MinorThe methods define osteoporosis as T ≤ −2.5 SD, but the Fig. 2 caption calls a T-score of −2.5 SD low bone mass.
“DXA reported T-score of − 2.5 SD still in the range of low bone mass (not shown).”
“Osteoporosis was defined as T ≤ − 2.5 SD and low bone mass as − 2.5 < T ≤ − 1 SD [21].”
Cites
pROC: an open-source package for R and S+ to analyze and compare ROC curves
Robin, X., Turck, N., Hainard, A., Tiberti, N., Lisacek, F., Sanchez, J.-C., & Müller, M. (2011) · BMC Bioinformatics · doi:10.1186/1471-2105-12-77 · Cited by 13,697 · cited 1× · see citing works
“ROC curves were compared with DeLong’s test for two correlated ROC curves using the pROC package [25].”
MethodOsteoporosis Prevention, Diagnosis, and Therapy
NIH Consensus Development Panel on Osteoporosis Prevention, D. (2001) · JAMA: The Journal of the American Medical Association · doi:10.1001/jama.285.6.785 · Cited by 5,529 · see citing works
An estimate of the worldwide prevalence and disability associated with osteoporotic fractures
Johnell, O., & Kanis, J. (2006) · Osteoporosis International · doi:10.1007/s00198-006-0172-4 · Cited by 4,770 · cited 1× · see citing works
“Osteoporosis affects the population worldwide, particularly the elderly in developed countries [2].”
BackgroundVertebral fracture assessment using a semiquantitative technique
Genant, H. K., Wu, C. Y., van Kuijk, C., & Nevitt, M. C. (1993) · Journal of Bone and Mineral Research · doi:10.1002/jbmr.5650080915 · Cited by 3,691 · cited 3× · see citing works
“the semi-quantitative technique by Genant [18].”
InfluentialOsteoporosis in the European Union: medical management, epidemiology and economic burden
Hernlund, E., Svedbom, A., Ivergård, M., Compston, J., Cooper, C. C., Stenmark, J., McCloskey, E. V., Jönsson, B., & Kanis, J. A. (2013) · Archives of Osteoporosis · doi:10.1007/s11657-013-0136-1 · Cited by 2,674 · cited 1× · see citing works
“In the European Union, the economic burden of osteoporotic fractures has been estimated at 37 billion euros per year and is expected to increase by 25% in 2025 [3].”
BackgroundCompston, J. E., McClung, M. R., & Leslie, W. D. (2019) · The Lancet · doi:10.1016/s0140-6736(18)32112-3 · Cited by 2,449 · see citing works
Bliuc, D. (2009) · JAMA · doi:10.1001/jama.2009.50 · Cited by 1,695 · cited 1× · see citing works
“Vertebral fractures have dramatic consequences that include a reduced quality of life [6], a 2-fold increase in age-adjusted mortality risk [7], and a 3-fold increase in the risk of additional fractures compared to the normal population, respectively [8].”
BackgroundSchuit, S. C. E., van der Klift, M., Weel, A. E. A. M., de Laet, C. E. D. H., Burger, H., Seeman, E., Hofman, A., Uitterlinden, A. G., van Leeuwen, J. P. T. M., & Pols, H. A. P. (2004) · Bone · doi:10.1016/j.bone.2003.10.001 · Cited by 1,651 · cited 1× · see citing works
“First, less than half of women (44%) and even fewer men (21%) with osteoporotic fractures exhibited low aBMD in a large observational study [12], emphasiz-”
BackgroundVertebral Fractures Predict Subsequent Fractures
Melton, L. J., Atkinson, E. J., Cooper, C. C., O’Fallon, W. M., & Riggs, B. L. (1999) · Osteoporosis International · doi:10.1007/s001980050218 · Cited by 496 · cited 1× · see citing works
“Vertebral fractures have dramatic consequences that include a reduced quality of life [6], a 2-fold increase in age-adjusted mortality risk [7], and a 3-fold increase in the risk of additional fractures compared to the normal population, respectively [8].”
BackgroundWorldwide prevalence and incidence of osteoporotic vertebral fractures
Ballane, G. T., Cauley, J. A., Luckey, M. M., & Fuleihan, G. E. (2017) · Osteoporosis International · doi:10.1007/s00198-017-3909-3 · Cited by 491 · cited 1× · see citing works
“Their prevalence among Europeans older than 50 years ranges between 18 and 26% [5].”
BackgroundEpidemiology of fracture risk with advancing age
Ensrud, K. E. (2013) · The Journals of Gerontology Series A: Biological Sciences and Medical Sciences · doi:10.1093/gerona/glt092 · Cited by 456 · cited 1× · see citing works
“Besides hip fractures, vertebral fractures are the most common and most consequential osteoporotic fractures [4].”
BackgroundVerSe: A Vertebrae labelling and segmentation benchmark for multi-detector CT images
Sekuboyina, A., Husseini, M. E., Bayat, A., Löffler, M. T., Liebl, H., Li, H., Tetteh, G., Kukačka, J., Payer, C., Štern, D., et al. (2021) · Medical Image Analysis · doi:10.1016/j.media.2021.102166 · Cited by 391 · see citing works
Self-citationFink, H. A., Milavetz, D. L., Palermo, L., Nevitt, M. C., Cauley, J. A., Genant, H. K., Black, D. M., & Ensrud, K. E. (2005) · Journal of Bone and Mineral Research · doi:10.1359/jbmr.050314 · Cited by 365 · cited 1× · see citing works
“Moreover, osteoporotic vertebral fractures remain clinically silent with only 15–30% coming to clinical attention [11].”
BackgroundJang, S., Graffy, P. M., Ziemlewicz, T. J., Lee, S., Summers, R. M., & Pickhardt, P. J. (2019) · Radiology · doi:10.1148/radiol.2019181648 · Cited by 364 · cited 1× · see citing works
“Some automatic tools use HU as a proxy for BMD [34], which is a method that is expected to produce inaccuracies due to its lack of scanner-specific calibration to bone [35] as well as high variations due to presence of contrast material [15, 36, 37].”
MethodOsteoporosis Due to Cancer Treatment: Pathogenesis and Management
Pfeilschifter, J., & Diel, I. (2000) · Journal of Clinical Oncology · doi:10.1200/jco.2000.18.7.1570 · Cited by 363 · cited 1× · see citing works
“larly benefit from opportunistic screening because osteoporosis may occur as a side effect of cancer treatment [39].”
BackgroundLewiecki, E. M., Binkley, N., Morgan, S. L., Shuhart, C., Camargos, B. M., CAREY, J. J., Gordon, C. M., Jankowski, L. G., Lee, J. K., & Leslie, W. D. (2016) · Journal of Clinical Densitometry · doi:10.1016/j.jocd.2016.03.003 · Cited by 338 · see citing works
Shepherd, J. A., Schousboe, J. T., Broy, S. B., Engelke, K., & Leslie, W. D. (2015) · Journal of Clinical Densitometry · doi:10.1016/j.jocd.2015.06.013 · Cited by 281 · cited 1× · see citing works
“Scans were performed by trained technologists and quality was assured through evaluation by experienced physicians following current recommendations [19].”
MethodBolotin, H. H. (2007) · Bone · doi:10.1016/j.bone.2007.02.022 · Cited by 274 · see citing works
Compston Juliet, E., McClung Michael, R., & Leslie William, D. (2019) · The Lancet · Cited by 261 · see citing works
Wang, X., Sanyal, A., Cawthon, P. M., Palermo, L., Jekir, M. G., Christensen, J., Ensrud, K. E., Cummings, S. R., ORWOLL, E. S., Black, D. M., et al. (2011) · Journal of Bone and Mineral Research · doi:10.1002/jbmr.1539 · Cited by 212 · see citing works
Improved prediction of incident vertebral fractures using opportunistic QCT compared to DXA
Löffler, M. T., Jacob, A., Valentinitsch, A., Rienmüller, A., Zimmer, C., Ryang, Y.-M., Baum, T., & Kirschke, J. S. (2019) · European Radiology · doi:10.1007/s00330-019-06018-w · Cited by 197 · cited 2× · see citing works
“Previously published HU-to-BMD conversion equations were used for all CT scanners in this study [22].”
MethodSelf-citationA Vertebral Segmentation Dataset with Fracture Grading
Löffler, M. T., Sekuboyina, A., Jacob, A., Grau, A.-L., Scharr, A., El Husseini, M., Kallweit, M., Zimmer, C., Baum, T., & Kirschke, J. S. (2020) · Radiology: Artificial Intelligence · doi:10.1148/ryai.2020190138 · Cited by 181 · cited 3× · see citing works
“We recently introduced a framework for fully automatic segmentation of vertebrae in any CT dataset within several seconds [16, 17].”
MethodSelf-citationYu, W., Glüer, C., Grampp, S., Jergas, M., Fuerst, T., Wu, C. Y., Lu, Y., Fan, B., & Genant, H. K. (1995) · Osteoporosis International · doi:10.1007/bf01626604 · Cited by 170 · see citing works
Influence of degenerative joint disease on spinal bone mineral measurements in postmenopausal women
Yu, W., Gl�er, C. C., Fuerst, T., Grampp, S., Li, J., Lu, Y., & Genant, H. K. (1995) · Calcified Tissue International · doi:10.1007/bf00310253 · Cited by 154 · cited 1× · see citing works
“In contrast to a community-dwelling population like the MrOS cohort, our study group has a selection bias of elderly hospital inpatients, mainly neurosurgical and oncological and exhibiting severe spinal degeneration that render areal density measures inaccurate [30].”
ResultYasaka, K., Akai, H., Kunimatsu, A., Kiryu, S., & Abe, O. (2020) · European Radiology · doi:10.1007/s00330-020-06677-0 · Cited by 151 · cited 1× · see citing works
“In this regard, a recently presented approach to directly estimate aBMD from CT scans using CNNs trained on DXA and CT data is questionable because it propagates the inaccuracies of DXA to CT measures [32].”
BackgroundBuckens, C. F. M., Dijkhuis, G. R., de Keizer, B., et al. (2015) · European Radiology · doi:10.1007/s00330-014-3584-0 · Cited by 148 · cited 1× · see citing works
“Some automatic tools use HU as a proxy for BMD [34], which is a method that is expected to produce inaccuracies due to its lack of scanner-specific calibration to bone [35] as well as high variations due to presence of contrast material [15, 36, 37].”
MethodDual-energy X-ray Absorptiometry
Jain, R. K., & Vokes, T. (2017) · Journal of Clinical Densitometry · doi:10.1016/j.jocd.2017.06.014 · Cited by 148 · see citing works
Pickhardt, P. J., Graffy, P. M., Zea, R. D., Lee, S., Liu, J., Sandfort, V., & Summers, R. M. (2020) · Radiology · doi:10.1148/radiol.2020200466 · Cited by 134 · cited 1× · see citing works
“Of note, automatic assessment of other CT-derived biomarkers such as muscle attenuation has shown potential to predict fragility fractures [38].”
BackgroundX-ray-based quantitative osteoporosis imaging at the spine
Löffler, M. T., Sollmann, N., Mei, K., Valentinitsch, A., Noël, P. B., Kirschke, J. S., & Baum, T. (2020) · Osteoporosis International · doi:10.1007/s00198-019-05212-2 · Cited by 114 · cited 4× · see citing works
“Some automatic tools use HU as a proxy for BMD [34], which is a method that is expected to produce inaccuracies due to its lack of scanner-specific calibration to bone [35] as well as high variations due to presence of contrast material [15, 36, 37].”
BackgroundMethodInfluentialSelf-citationHealth-related quality of life after vertebral or hip fracture: a seven-year follow-up study
Hallberg, I., Bachrach‐Lindström, M., Hammerby, S., Toss, G., & Ek, A. (2009) · BMC Musculoskeletal Disorders · doi:10.1186/1471-2474-10-135 · Cited by 102 · cited 1× · see citing works
“Vertebral fractures have dramatic consequences that include a reduced quality of life [6], a 2-fold increase in age-adjusted mortality risk [7], and a 3-fold increase in the risk of additional fractures compared to the normal population, respectively [8].”
BackgroundPrediction of incident vertebral fracture using CT-based finite element analysis
Allaire, B. T., Lu, D., Johannesdottir, F., Kopperdahl, D., Keaveny, T. M., Jarraya, M., Guermazi, A., Bredella, M. A., Samelson, E. J., Kiel, D. P., et al. (2019) · Osteoporosis International · doi:10.1007/s00198-018-4716-1 · Cited by 95 · cited 2× · see citing works
“that has been previously proposed [27].”
BackgroundPickhardt, P. J., Lee, S., Liu, J., et al. (2018) · British Journal of Radiology · doi:10.1259/bjr.20180726 · Cited by 95 · cited 1× · see citing works
“Previously, efforts to automatically assess BMD in CT data have been undertaken [33].”
BackgroundIntravenous contrast injection significantly affects bone mineral density measured on CT
Pompe, E., Willemink, M. J., Dijkhuis, G. R., Verhaar, H. J. J., Hoesein, F. A. A. M., & de Jong, P. A. (2014) · European Radiology · doi:10.1007/s00330-014-3408-2 · Cited by 90 · cited 1× · see citing works
“Some automatic tools use HU as a proxy for BMD [34], which is a method that is expected to produce inaccuracies due to its lack of scanner-specific calibration to bone [35] as well as high variations due to presence of contrast material [15, 36, 37].”
MethodJacqueline R. Center (2017) · Current Osteoporosis Reports · doi:10.1007/s11914-017-0352-5 · Cited by 78 · cited 1× · see citing works
“All types of osteoporotic fractures in the elderly foreshadow a high risk of poor outcomes, so that early medical intervention is strongly advised [9].”
BackgroundDetection of osteoporotic vertebral fractures using multidetector CT
Bauer, J. S., Müller, D., Ambekar, A., Dobritz, M., Matsuura, M., Eckstein, F., Rummeny, E. J., & Link, T. M. (2006) · Osteoporosis International · doi:10.1007/s00198-005-0023-8 · Cited by 66 · cited 1× · see citing works
“5mm axial slices [26]—could lead to the relatively higher ORs compared to Allaire et al (OR = 2.”
ResultBone densitometry worldwide: a global survey by the ISCD and IOF
on behalf of the International Society for Clinical Densitometry (ISCD) and the International Osteoporosis Foundation (IOF), Clynes, M. A., Westbury, L. D., Dennison, E. M., Kanis, J. A., Javaid, M. K., Harvey, N. C., Fujita, M., Cooper, C., Leslie, W. D., et al. (2020) · Osteoporosis International · doi:10.1007/s00198-020-05435-8 · Cited by 64 · cited 1× · see citing works
“Second, there is significant variability in the access to DXA services and many fall short of international quality standards [14].”
BackgroundAreal and volumetric bone mineral density and risk of multiple types of fracture in older men
Chalhoub, D., Orwoll, E. S., Cawthon, P. M., Ensrud, K. E., Boudreau, R., Greenspan, S., Newman, A. B., Zmuda, J., Bauer, D., Cummings, S., et al. (2016) · Bone · doi:10.1016/j.bone.2016.08.014 · Cited by 54 · see citing works
Kaesmacher, J., Liebl, H., Baum, T., & Kirschke, J. S. (2017) · Journal of Computer Assisted Tomography · doi:10.1097/rct.0000000000000518 · Cited by 50 · cited 1× · see citing works
“Bias of BMD values due to intravenous injection of contrast medium was corrected for using linear correction equations for arterial and portal/venous contrast phases [23].”
MethodSelf-citationLöffler, M. T., Sollmann, N., Burian, E., et al. (2021) · Frontiers in Endocrinology · doi:10.3389/fendo.2020.552719 · Cited by 47 · cited 1× · see citing works
“Using an earlier version of this automatic framework we were able to predict screw loosening after lumbar spinal instrumentation in patients with osteoporotic trabecular vBMD [40].”
MethodSelf-citationVerSe: A Vertebrae Labelling and Segmentation BenchmarkPreprint
Sekuboyina, A., Bayat, A., Husseini, M. E., et al. (2020) · arXiv (Cornell University) · Cited by 26 · see citing works
Self-citationEngelke, K., & Keaveny, T. M. (2019) · British Journal of Radiology · doi:10.1259/bjr.20190115 · Cited by 6 · see citing works
Interrelationships of Vero cytotoxin producing Escherichia coli infections of humans and animals.
Cr, D. (1988) · PubMed · Cited by 5 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Value-added Opportunistic CT Screening: State of the Art
Pickhardt, P. J. (2022) · Radiology · doi:10.1148/radiol.211561 · Cited by 247 · see citing works
Deshpande, N., Hadi, M. S., Lillard, J. C., et al. (2023) · Journal of Neurosurgery Spine · doi:10.3171/2022.11.spine22875 · Cited by 130 · see citing works
Sollmann, N., Löffler, M. T., Husseini, M. E., et al. (2020) · Journal of Bone and Mineral Research · doi:10.1002/jbmr.4575 · Cited by 65 · see citing works
“1A-D and 2A-D).((19)) Any patient cases with segmentation masks generated by the CNN-based approach that did not entirely and correctly enclose the trabecular component of vertebral bodies (eg, due to Schmorl nodes,”
BackgroundMethodResultInfluentialSelf-citationDevelopment of a Spine X-Ray-Based Fracture Prediction Model Using a Deep Learning Algorithm
Kong, S. H., Lee, J.-W., Bae, B., Sung, J. K., Jung, K. H., Kim, J. H., & Shin, C. S. (2022) · Endocrinology and Metabolism · doi:10.3803/enm.2022.1461 · Cited by 59 · see citing works
“In several cross-sectional studies, CNN algorithms using X-rays and CT images have been applied to assess bone mineral density (BMD) or detect fractures [16-19].”
Current development and prospects of deep learning in spine image analysis: a literature review
Qu, B., Cao, J., Qian, C., et al. (2022) · Quantitative Imaging in Medicine and Surgery · doi:10.21037/qims-21-939 · Cited by 54 · see citing works
Dong, Q., Luo, G., Lane, N. E., et al. (2022) · Academic Radiology · doi:10.1016/j.acra.2022.02.020 · Cited by 50 · see citing works
“[17] Löffler MT, Jacob A, Scharr A, Sollmann N, Burian E, El Husseini M, Sekuboyina A, Tetteh G, Zimmer C, Gempt J, Baum T.”
BackgroundMethodFan, Z., Yan, X., Li, B., et al. (2023) · PLoS ONE · doi:10.1371/journal.pone.0286110 · Cited by 49 · see citing works
“Whether the CT scan for osteoporosis is better than DXA has also not been proven and needs further investigation [59, 60].”
BackgroundArtificial Intelligence Applications for Osteoporosis Classification Using Computed Tomography
Ong, W., Liu, R. W., Makmur, A., Low, X. Z., Sng, W. J., Tan, J. H., Kumar, N., & Hallinan, J. T. P. D. (2023) · Bioengineering · doi:10.3390/bioengineering10121364 · Cited by 52 · see citing works
Deep learning in the radiologic diagnosis of osteoporosis: a literature review
He, Y., Lin, J., Zhu, S., et al. (2024) · Journal of International Medical Research · doi:10.1177/03000605241244754 · Cited by 47 · see citing works
Lin, W., He, C., Xie, F., Chen, T., Zheng, G., Yin, H., Chen, H., & Wang, Z. (2023) · BMC Geriatrics · doi:10.1186/s12877-023-03963-6 · Cited by 46 · see citing works
Prijs, J., Liao, Z., To, M., Verjans, J. W. H., Jutte, P. C., Stirler, V. M. A., Olczak, J., Gordon, M., Guss, D., DiGiovanni, C. W., et al. (2022) · European Journal of Trauma and Emergency Surgery · doi:10.1007/s00068-022-02136-1 · Cited by 42 · see citing works
“The next level of CNN studies in our field report detailed segmentation by a CNN of the second intact metacarpal [21] on plain radiographs, vertebrae on computed tomography (CT) [22], and femora on magnetic resonance imaging (MRI) [23, 24].”
BackgroundRühling, S., Navarro, F., Sekuboyina, A., et al. (2021) · European Radiology · doi:10.1007/s00330-021-08284-z · Cited by 41 · see citing works
“BMD values were automatically extracted from the segmentations masks of the trabecular compartment of vertebral bodies, and scanner-specific HU-to-BMD conversion equations previously calculated with density reference phantoms (QRM)were applied [28].”
MethodSelf-citationLöffler, M. T., Kallweit, M., Niederreiter, E., Baum, T. H., Makowski, M. R., Zimmer, C., & Kirschke, J. S. (2021) · Osteoporosis International · doi:10.1007/s00198-021-06169-x · Cited by 43 · see citing works
Self-citationGassert, F. T., Gassert, F. T., Kufner, A., et al. (2021) · Osteoporosis International · doi:10.1007/s00198-021-06147-3 · Cited by 39 · see citing works
Self-citationDieckmeyer, M., Löffler, M. T., Husseini, M. E., et al. (2022) · Frontiers in Endocrinology · doi:10.3389/fendo.2022.882163 · Cited by 36 · see citing works
Self-citationRühling, S., Scharr, A., Sollmann, N., et al. (2022) · European Radiology · doi:10.1007/s00330-022-08721-7 · Cited by 35 · see citing works
Self-citationPraveen, A. D., Sollmann, N., Baum, T. H., Ferguson, S. J., & Helgason, B. (2024) · Osteoporosis International · doi:10.1007/s00198-024-07029-0 · Cited by 29 · see citing works
“SI1) [13, 40, 43, 45, 58, 66, 67, 70, 72, 75, 76].”
BackgroundSelf-citationRühling, S., Schwarting, J., Froelich, M. F., Löffler, M. T., Bodden, J. H., Petzsche, M. R. H., Baum, T. H., Wostrack, M., Aftahy, A. K., Seifert‐Klauss, V., et al. (2023) · Frontiers in Endocrinology · doi:10.3389/fendo.2023.1222041 · Cited by 28 · see citing works
“Frontiers in Endocrinology 09 still evolving, a fully automated pipeline for opportunistic BMD measurements has recently been shown to outperform DXA in the prediction of prevalent and incident VFs (21, 22).”
BackgroundSelf-citationWang, M., Chen, X., Chen, X., et al. (2022) · The Journal of Clinical Endocrinology & Metabolism · doi:10.1210/clinem/dgac722 · Cited by 27 · see citing works
Özmen, E., Biçer, O., Meriç, E., et al. (2023) · European Spine Journal · doi:10.1007/s00586-023-07912-0 · Cited by 26 · see citing works
“This might be advantageous, as DEXA scores are known for their shortcomings in predicting these fractures [8, 14–16].”
BackgroundLu, S., Fuggle, N. R., Westbury, L. D., Breasail, M. Ó., Bevilacqua, G., Ward, K. A., Dennison, E. M., Mahmoodi, S., Niranjan, M., & Cooper, C. C. (2022) · Bone · doi:10.1016/j.bone.2022.116653 · Cited by 23 · see citing works
Opportunistic Screening for Low Bone Density Using Abdominopelvic CT Scans
Tariq, A., Patel, B. N., Sensakovic, W. F., Fahrenholtz, S. J., & Banerjee, I. (2022) · Medical Physics · doi:10.1002/mp.16230 · Cited by 22 · see citing works
Constant, C., Aubin, C., Kremers, H. M., Vera-Garcia, D. V., Wyles, C. C., Rouzrokh, P., & Larson, A. N. (2023) · North American Spine Society Journal (NASSJ) · doi:10.1016/j.xnsj.2023.100236 · Cited by 23 · see citing works
Efficacy of two opportunistic methods for screening osteoporosis in lumbar spine surgery patients
Xu, T., Huang, X., & Jiang, Y.-W. (2023) · European Spine Journal · doi:10.1007/s00586-023-07938-4 · Cited by 23 · see citing works
Sollmann, N., Becherucci, E. A., Boehm, C., et al. (2022) · Frontiers in Endocrinology · doi:10.3389/fendo.2021.778537 · Cited by 22 · see citing works
Self-citationSollmann, N., Kirschke, J. S., Kronthaler, S., et al. (2022) · RöFo - Fortschritte auf dem Gebiet der Röntgenstrahlen und der bildgebenden Verfahren · doi:10.1055/a-1770-4626 · Cited by 21 · see citing works
Self-citationDong, Q., Luo, G., Lane, N. E., et al. (2023) · Academic Radiology · doi:10.1016/j.acra.2023.04.023 · Cited by 21 · see citing works
Naghavi, M., Atlas, K. C., Jaberzadeh, A., et al. (2023) · Journal of the American College of Radiology · doi:10.1016/j.jacr.2023.05.006 · Cited by 19 · see citing works
Li, Y., Liang, Z., Li, Y., Cao, Y., Zhang, H., & Dong, B. (2024) · European Journal of Radiology · doi:10.1016/j.ejrad.2024.111714 · Cited by 16 · see citing works
Feng, C., Zhou, X., Wang, H., et al. (2022) · Frontiers in Public Health · doi:10.3389/fpubh.2022.949366 · Cited by 16 · see citing works
“used conventional CT combined with deep learning to predict osteoporosis (52).”
MethodBodden, J. H., Prucker, P., Sekuboyina, A., et al. (2024) · European Radiology Experimental · doi:10.1186/s41747-024-00483-9 · Cited by 14 · see citing works
“The conversion of asynchronous CT-based density values measured in HU into vBMD and corrections for the intravenous contrast media phase can be performed automatically [11 – 13].”
MethodSelf-citationRe-tear after arthroscopic rotator cuff repair can be predicted using deep learning algorithm
Zhang, Z., Ke, C., Zhang, Z., et al. (2024) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2024.1331853 · Cited by 14 · see citing works
Utilizing artificial intelligence to determine bone mineral density using spectral CT
Li, Y., Jin, D., Zhang, Y., Li, W., Jiang, C., Ni, M., Liao, N., & Yuan, H. (2024) · Bone · doi:10.1016/j.bone.2024.117321 · Cited by 14 · see citing works
Mohammadi-Sadr, M., Cheki, M., Moslehi, M., Zarasvandnia, M., & Salamat, M. R. (2024) · Academic Radiology · doi:10.1016/j.acra.2024.10.049 · Cited by 13 · see citing works
Kim, Y., Kim, C., Lee, E., et al. (2023) · Skeletal Radiology · doi:10.1007/s00256-023-04525-y · Cited by 11 · see citing works
“Moreover, recent studies suggested that CT numbers measured at the trabecular bone of the vertebrae could predict osteoporotic compression fractures [9, 10].”
Deep Learning to Differentiate Benign and Malignant Vertebral Fractures at Multidetector CT
Foreman, S. C., Schinz, D., Husseini, M. E., et al. (2024) · Radiology · doi:10.1148/radiol.231429 · Cited by 11 · see citing works
Self-citationBrance, M. L., Saraví, F. D., Henríquez, M. M., et al. (2024) · Journal of Bone Metabolism · doi:10.11005/jbm.24.765 · Cited by 11 · see citing works
Petraikin, A. V., Pickhardt, P. J., Belyaev, M., Belaya, Z. E., Pisov, M., Bukharaev, A., Zakharov, A., Kudryavtsev, N. D., Bobrovskaya, T., Семенов, Д. С., et al. (2025) · Asian Spine Journal · doi:10.31616/asj.2024.0314 · Cited by 12 · see citing works
“Additionally, indirect BMD assessment using HU values [6,11], fully automated bone mineral densitometry following an asynchronous calibration [12], and automated BMD assessment with texture analysis [13] are used.”
InfluentialDağ, N., Ulubaba, H. E., Taşolar, S., Candur, M., & Akbulut, S. (2025) · Diagnostics · doi:10.3390/diagnostics16010029 · Cited by 10 · see citing works
Rühling, S., Dittmann, J., Müller, T., Husseini, M. E., Bodden, J. H., Petzsche, M. R. H., Löffler, M. T., Sollmann, N., Baum, T. H., Seifert‐Klauss, V., et al. (2024) · Frontiers in Endocrinology · doi:10.3389/fendo.2024.1352048 · Cited by 10 · see citing works
Self-citationGuenoun, D., Quemeneur, M., Ayobi, A., et al. (2025) · Clinical Radiology · doi:10.1016/j.crad.2025.106831 · Cited by 10 · see citing works
Rayudu, N. M., Subburaj, K., Elara, M. R., Sollmann, N., Dieckmeyer, M., Kirschke, J. S., & Baum, T. H. (2022) · Biomedicines · doi:10.3390/biomedicines10071567 · Cited by 10 · see citing works
Self-citationBodden, J. H., Dieckmeyer, M., Sollmann, N., et al. (2023) · Frontiers in Endocrinology · doi:10.3389/fendo.2023.1207949 · Cited by 9 · see citing works
Self-citationZhang, K., Lin, P.-C., Pan, J., Shao, R., Pei-xia, X., Cao, R., Wu, C., Crookes, D., Hua, L., & Wang, L. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.107916 · Cited by 9 · see citing works
Opportunistic Screening of Bone Fragility Using Computed Tomography
Acevedo, J. B. H., Lenchik, L., Weaver, A. A., et al. (2024) · Seminars in Musculoskeletal Radiology · doi:10.1055/s-0044-1788816 · Cited by 9 · see citing works
Goller, S. S., Foreman, S. C., Rischewski, J., et al. (2023) · European Spine Journal · doi:10.1007/s00586-023-07838-7 · Cited by 9 · see citing works
“A fully automated framework (https:// anduin. bones creen. de), which enables an instant segmentation of vertebrae in any CT data set, has recently been introduced, particularly for opportunistic osteoporosis screening and related applications [9, 14–18].”
MethodSelf-citationGreve, T., Rayudu, N. M., Dieckmeyer, M., Boehm, C., Ruschke, S., Burian, E., Kloth, C., Kirschke, J. S., Karampinos, D. C., Baum, T. H., et al. (2022) · Frontiers in Endocrinology · doi:10.3389/fendo.2022.900356 · Cited by 8 · see citing works
Self-citationOpportunistic Computed Tomography Screening for Osteoporosis and Fracture
Guenoun, D., & Champsaur, P. (2023) · Seminars in Musculoskeletal Radiology · doi:10.1055/s-0043-1771037 · Cited by 8 · see citing works
Jiang, X.-Y., Tang, Z.-Y., Liu, B.-W., et al. (2024) · Experimental Gerontology · doi:10.1016/j.exger.2024.112654 · Cited by 8 · see citing works
“The diagnostic thresholds for bone density in osteoporosis and low bone mass were BMD 80 mg/cm 3 and 80 ≤ BMD ≤ 120 mg/cm 3 , respectively (L ¨ offler et al., 2021).”
Paukovitsch, M., Fechner, T., Felbel, D., et al. (2025) · Archives of Osteoporosis · doi:10.1007/s11657-025-01579-4 · Cited by 8 · see citing works
“…in image processing and artificial intelligence (AI), CT scans obtained during clinical routine may, however, be used for determining BMD, thus allowing opportunistic screening for osteoporosis in clinical routine CT scans specifically obtained for indications other than assessing BMD [16–19].”
InfluentialSelf-citationAutomatic bone marrow segmentation for precise [ 177 Lu]Lu‐PSMA‐617 dosimetry
Lu, Z., Hu, J., Chen, G., Jiang, H., Shih, C., Afshar‐Oromieh, A., Rominger, A., Shi, K., & Mok, G. S. P. (2025) · Medical Physics · doi:10.1002/mp.17684 · Cited by 7 · see citing works
“An open source artificial intelligence (AI)-based automatic bone segmentation software ANDUIN, 14,15 was first used to segment out L1–L5, followed by the smoothing of a bilateral filter ( σ d = 2.5 mm) for noise suppression and edge preservation.”
InfluentialAutomated Fast Prediction of Bone Mineral Density From Low-dose Computed Tomography
Zhou, K., Xin, E., Yang, S., Luo, X., Zhu, Y., Zeng, Y., Fu, J., Ruan, Z., Wang, R., Geng, D., et al. (2025) · Academic Radiology · doi:10.1016/j.acra.2025.02.041 · Cited by 7 · see citing works
Quantitative Computed Tomography, modern data. Review
Petraikin, A. V., & Skripnikova, I. A. (2021) · Medical Visualization · doi:10.24835/1607-0763-1049 · Cited by 7 · see citing works
Anatomy-Aware Inference of the 3D Standing Spine Posture from 2D Radiographs
Bayat, A., Pace, D. F., Sekuboyina, A., Payer, C., Štern, D., Urschler, M., Kirschke, J. S., & Menze, B. H. (2022) · Tomography · doi:10.3390/tomography8010039 · Cited by 7 · see citing works
“As crucial spatial information is lost when projecting a 3D object in only two 2D planes [5], a random object cannot reliably be reconstructed from two orthogonal projections.”
BackgroundSelf-citationHanly, A., Gyftopoulos, S., Pelzl, C. E., He, W., & Chang, C. Y. (2025) · Skeletal Radiology · doi:10.1007/s00256-025-04892-8 · Cited by 6 · see citing works
“As machine learning technologies improve and are adopted, it is feasible that this method could also be automated by software [13, 28–30].”
Goller, S. S., Rischewski, J., Liebig, T., et al. (2023) · Diagnostics · doi:10.3390/diagnostics13122119 · Cited by 6 · see citing works
“This highlights a major problem of DXA, measuring areal but not volumetric BMD, which is easily contaminated by intraand extra-osseous soft tissue effects [13].”
BackgroundMethodResultInfluentialSelf-citationHowlett, D. C., Drinkwater, K. J., Mahmood, N., Salman, L., Griffin, J., Javaid, M. K., Retnasingam, G., Marzoug, A., Greenhalgh, R., Barrett, A., et al. (2023) · Clinical Radiology · doi:10.1016/j.crad.2023.09.004 · Cited by 6 · see citing works
The low bone mass density in adults with hypertension: A meta-analysis
Gao, Y., Tian, X., Zhang, G., Yu, J., & Zhang, L. (2024) · Journal of Orthopaedics · doi:10.1016/j.jor.2024.10.041 · Cited by 6 · see citing works
Nachef, C., Bousson, V., Belmatoug, N., Cohen-Solal, M., Vilgrain, V., Roux, O., Francoz, C., Durand, F., & Funck-Brentano, T. (2024) · American Journal of Gastroenterology · doi:10.14309/ajg.0000000000002507 · Cited by 5 · see citing works
“Furthermore, the performance of DXA in predicting fractures is questionable in patients with cirrhosis (2).”
BackgroundInfluentialJacob, A., Heumann, M., Zderic, I., et al. (2024) · European Spine Journal · doi:10.1007/s00586-024-08391-7 · Cited by 5 · see citing works
“In clinical application, this emphasizes the importance of preoperative BMD assessment and osteoporosis screening as bone quality is crucial for risk assessment, indication setting, and surgery planning [30, 31].”
Self-citationHammel, J., Birnbacher, L., Campbell, G. M., Coulon, P., Ushakov, L., Pfeiffer, F., Makowski, M. R., Kirschke, J. S., & Pfeiffer, D. (2023) · European Radiology Experimental · doi:10.1186/s41747-023-00356-7 · Cited by 5 · see citing works
Self-citationEvaluation of Bone Mineral Density in Lung Transplant Recipients by Chest Computed Tomography
Mori, R., Handa, T., Ohsumi, A., Ikezoe, K., Tanizawa, K., Uozumi, R., Tanabe, N., Oguma, T., Sakamoto, R., Hamaji, M., et al. (2023) · Respiration · doi:10.1159/000535269 · Cited by 5 · see citing works
“CT-derived BMD has been reported to be superior to DEXA-derived BMD in predicting osteoporotic fractures [30, 31].”
BackgroundOsteoporosis classification using VGG-16 and logistic regression: A radiograph and BMD data approach
Salunke, D., Joshi, G., Inamdar, S., et al. (2024) · Intelligent Decision Technologies · doi:10.3233/idt-240227 · Cited by 4 · see citing works
“Maximilian T. Löffler et al. [1] described the relation between osteoporotic fractures and spinal bone measurements.”
Huang, C., Li, E., Hu, J., et al. (2025) · Spine · doi:10.1097/brs.0000000000005438 · Cited by 4 · see citing works
Jin, Q., Jia, Q., Zhou, X., Jin, D., Song, X., Xie, Z., Alimujiang, A., Li, Y., Huang, J., & Ma, C. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3597467 · Cited by 4 · see citing works
“Due to the hidden nature of the disease, it is easy to progress to fragility fractures, which can seriously affect quality of life and increase mortality risk, and is known as the “silent epidemic” [3].”
Doussière, M., Aboud, A., Dequen, G., & Goëb, V. (2026) · Journal of Clinical Medicine · doi:10.3390/jcm15020491 · Cited by 4 · see citing works
“CT-based measures have shown superiority over DXA in identifying patients with reduced bone mass who sustained vertebral fractures [98].”
Artyukova, Z. R., Kudryavtsev, N. D., Petraikin, A. V., et al. (2023) · Medical Visualization · doi:10.24835/1607-0763-1257 · Cited by 4 · see citing works
Imaging of Metabolic Bone Diseases: The Spine View, Part II
Gómez, M. P. A., Isaac, A., Dalili, D., Fotiadou, A. N., Kariki, E. P., Kirschke, J. S., Krestan, C. R., Messina, C., Oei, E. H. G., Phan, C. M., et al. (2022) · Seminars in Musculoskeletal Radiology · doi:10.1055/s-0042-1754341 · Cited by 4 · see citing works
Self-citationPetragallo, R., Bertram, P., Halvorsen, P. H., Iftimia, I. N., Low, D. A., Morin, O., Narayanasamy, G., Saenz, D. L., Sukumar, K. N., Valdés, G., et al. (2023) · Medical Physics · doi:10.1002/mp.16359 · Cited by 4 · see citing works
Bodden, J. H., Dieckmeyer, M., Sollmann, N., et al. (2023) · Quantitative Imaging in Medicine and Surgery · doi:10.21037/qims-23-19 · Cited by 4 · see citing works
“Using the sagittal reformations, automated vertebral body segmentation was performed for T5–L5 using a CNN-based pipeline ( Figure 1 ) (https://anduin.bonescreen. de) (12,13,15,18).”
InfluentialSelf-citationAdams, H., Salman, L., Drinkwater, K. J., Griffin, J., Rowntree, S., & Howlett, D. C. (2025) · Osteoporosis International · doi:10.1007/s00198-025-07488-z · Cited by 3 · see citing works
“AI is well recognised within the field of radiology, and it is becoming increasingly apparent that AI will be incorporated into multiple facets of radiology reporting over the coming years [34–36].”
Zhu, L., Song, B., Xu, Y., Zhu, Y.-L., Hua, L., Nian, N., Zhang, L., Sun, Q., Xue, B.-C., Xu, Y., et al. (2025) · Orphanet Journal of Rare Diseases · doi:10.1186/s13023-025-03910-1 · Cited by 3 · see citing works
“The reasons for this are that the present study used more reasonable testing methods [8, 9] and selected the lumbar spine as the more recommended component of the test [13, 14].”
Mniai, E. M., Laletin, V., Tselikas, L., et al. (2025) · La radiologia medica · doi:10.1007/s11547-025-02058-z · Cited by 3 · see citing works
“Additionally, CT has proven to be an optimal modality for automated osteoporosis screening, which is particularly relevant for applications detecting VCFs [34, 36, 37].”
Serpa, A. S., Takahashi, M. S., Farina, E. M. J. D. M., et al. (2025) · Abdominal Radiology · doi:10.1007/s00261-025-05213-2 · Cited by 3 · see citing works
Atthipatla, J., & Senthil kumar, S. (2022) · Journal of Pharmaceutical Negative Results · doi:10.47750/pnr.2022.13.s04.219 · Cited by 3 · see citing works
Ha, T. J., Kim, H. S., Hwang, D. H., et al. (2023) · Research Square · doi:10.21203/rs.3.rs-3440051/v1 · Cited by 3 · see citing works
Jiang, W., Huang, J., Wu, N., Liu, J., Liang, J., Li, S., Ye, Z., & Wang, J. (2025) · Frontiers in Endocrinology · doi:10.3389/fendo.2025.1672551 · Cited by 3 · see citing works
Ramschütz, C., Kloth, C., Vogele, D., Baum, T. H., Rühling, S., Beer, M., Jansen, J. U., Schlager, B., Wilke, H., Kirschke, J. S., et al. (2025) · European Spine Journal · doi:10.1007/s00586-025-09146-8 · Cited by 3 · see citing works
“The feasibility of a phantom-free opportunistic approach using convolutional neural network (CNN)-based algorithms for assessing vBMD has been demonstrated in previous retrospective studies [ 12 , 13 ].”
Self-citationStangelmaier, V., Salzlechner, C., Götz, C., et al. (2025) · Osteologie/Osteology · doi:10.1055/a-2673-6204 · Cited by 2 · see citing works
中野渡滉希, Watanabe, K., Mori, K., et al. (2021) · Journal of Orthopaedic Science · doi:10.1016/j.jos.2021.03.004 · Cited by 2 · see citing works
Sollmann, N., Mei, K., Löffler, M. T., et al. (2025) · Osteoporosis International · doi:10.1007/s00198-025-07467-4 · Cited by 1 · see citing works
Self-citationArtificial intelligence in spine surgery
Zhang, C., Liu, S., Shi, J., Zhou, X., Passias, P. G., Xu, N., & Li, W. (2025) · Spine Research · doi:10.1097/br9.0000000000000005 · Cited by 1 · see citing works
Opportunistic screening for osteoporosis using artificial intelligence services
Artyukova, Z. R., Kudryavtsev, N. D., Petraikin, A. V., et al. (2025) · N N Priorov Journal of Traumatology and Orthopedics · doi:10.17816/vto634918 · Cited by 1 · see citing works
Yang, H. J., Li, J., Zheng, X., et al. (2025) · Clinical Interventions in Aging · doi:10.2147/cia.s538123 · Cited by 1 · see citing works
“8 In contrast, quantitative computed tomography (QCT) offers a 3D BMD assessment, enabling separate measurement of trabecular and cortical bone without interference from surrounding structures.”
Liu, C., Tong, Y., Pan, M., Li, Y., Yang, X., Wang, Y., & Xing, L. (2025) · Frontiers in Nutrition · doi:10.3389/fnut.2025.1660080 · Cited by 1 · see citing works
Current Status of AI-Assisted Screening for Opportunistic Osteoporosis
Zheng, X., Dai, Z., & Fang, K. (2026) · Current Osteoporosis Reports · doi:10.1007/s11914-026-00950-9 · Cited by 1 · see citing works
“Some scholars have used convolutional neural network-based automatic segmentation techniques to automatically segment vertebral bodies and extract the trabecular bone within them for bone density calculation, achieving an AUC of 0.885 in osteo - porosis screening [80].”
InfluentialClinical Implementation of Opportunistic Screening for Osteoporosis
Dogra, S., Bussey, O., Dane, B. R., et al. (2026) · American Journal of Roentgenology · doi:10.2214/ajr.26.34956 · Cited by 1 · see citing works
Lee, J., Park, C.-M., Cho, M., et al. (2024) · SPIE Medical Imaging: Image Processing · doi:10.1117/12.3006168 · Cited by 1 · see citing works
“1-3].”
Jörger, A.-K., Butenschoen, V. M., Feihl, S., et al. (2024) · Brain and Spine · doi:10.1016/j.bas.2024.104152 · Cited by 1 · see citing works
Self-citationKim, Y., Lee, S., Lee, E., et al. (2025) · Acta Radiologica · doi:10.1177/02841851251322928 · Cited by 1 · see citing works
“Automatic ROI placement would be helpful in future studies to reduce observer variability (35).”
Messtechnische Verfahren im Kontext der DVO Leitlinie – neue Entwicklungen
Engelke, K., Müller, D., Buehring, B., et al. (2023) · Osteologie/Osteology · doi:10.1055/a-2045-7222 · Cited by 1 · see citing works
“[30] Loffler MT, Jacob A, Scharr A et al.”
BackgroundGlüer, C., Krekiehn, N. R., Yilmaz, E. B., & Both, M. (2022) · Osteologie/Osteology · doi:10.1055/a-1717-0955
“Erste Studien zeigen, dass bereits heute KI Modelle den Fraktursta-tus abschätzen können [42, 43].”
BackgroundOsteoporosis Screening: A Review
ÖZBİLGEÇ, S. (2022) · MAS Journal of Applied Sciences · doi:10.52520/masjaps.v7i2id173
A Deep Spiking Convolutional Conversion Scheme for Robust Vertebrae Segmentation & Identification
Litman, E. (2022) · IEEE MIT Undergraduate Research Technology Conference (URTC) · doi:10.1109/urtc56832.2022.10002217
“Following the free available research tool Anduin [15] that”
MethodBadoghaish, W., Mirghani, H. O., Djeradi, L., & Aljammaz, H. M. (2023) · Medical Science · doi:10.54905/disssi/v27i133/e139ms2935
Beeri, Y., Ben‐Arie, G., Shelef, I., Ofri, M., Abeles, O. D., Novack, V., Fisher, D. L., & Fraenkel, M. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4813440
Setting the Stage for Preventive Radiology
Maerkisch, L., Schneider, B., & Wiedemeyer, C. (2024) · Applied Radiology · doi:10.37549/ar2980
Spine X-Ray-Based Osteoporosis Detection Using Deep Learning Techniques
Maddu, S., Muppana, J., Korasapati, P., et al. (2025) · International Conference on Data Science, Agents & Artificial Intelligence (ICDSAAI) · doi:10.1109/icdsaai65575.2025.11011781
Sollmann, N., & Ramschütz, C. (2025) · European Spine Journal · doi:10.1007/s00586-025-09355-1
Self-citationZHANG, D., Shu, C. U. I., Wang, Q., et al. (2025) · Research Square · doi:10.21203/rs.3.rs-7575231/v1
- Authors
- Löffler, M. T., Jacob, A., Scharr, A., Sollmann, N., Burian, E., El Husseini, M., Sekuboyina, A., Tetteh, G., Zimmer, C., Gempt, J., Baum, T., & Kirschke, J. S.
- Affiliations
- University of Freiburg (DE)
- TUM Klinikum (DE)
- Technical University of Munich (DE)
- Corresponding author
- Löffler, Maximilian T.
- ORCID
- Venue
- European Radiology
- Published
- 2021-01-28
- Volume
- 31
- Issue
- 8
- Pages
- 6069-6077
- ISSN
- 0938-7994 (ISSN-L)
- 1432-1084
- PMC
- PMC8270840
- OpenAlex
- W3121936649
- Semantic Scholar
- b602a08ba27601fdcc1b4a1bbf3d057825bf73ee
- Cited by
- 120
- References
- 42
- Citations by year
- 2026: 15 · 2025: 27 · 2024: 20 · 2023: 32 · 2022: 20 · 2021: 5 · 2020: 1
- FWCI
- 16.99
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Locations
- European Radiology (publishedVersion, cc-by)
- PubMed (publishedVersion)
- PubMed Central (submittedVersion, cc-by)
- Informationszentrum Lebenswissenschaften (ZB MED) (submittedVersion, cc-by)
- mediaTUM – the media and publications repository of the Technical University Munich (Technical University Munich) (submittedVersion, other-oa)
- mediaTUM – the media and publications repository of the Technical University Munich (Technical University Munich) (submittedVersion)
- OPen Access Repositorium der Universität Ulm (OPARU) (Ulm University) (submittedVersion, cc-by)
- Universität Ulm, Kommunikations- und Informationszentrum (kiz) (cc-by)
- Funders
- European Research Council (637164)
- Deutsche Forschungsgemeinschaft (432290010)
- Topics
- Health Sciences › Medicine › Orthopedics and Sports Medicine › Bone health and osteoporosis research
- Physical Sciences › Engineering › Biomedical Engineering › Medical Imaging and Analysis
- Health Sciences › Medicine › Surgery › Scoliosis diagnosis and treatment
- Keywords
- osteoporosis screening, vertebral fractures, dual-energy X-ray absorptiometry, volumetric bone mineral density, trabecular bone, bone mineral content, vertebral segmentation, convolutional neural networks, osteopenia, fracture prediction, low-dose CT, diagnostic accuracy
- MeSH terms
- Aged, Female, Humans, Lumbar Vertebrae, Male, Middle Aged, Osteoporosis, Tomography, X-Ray Computed, Absorptiometry, Photon, Bone Density, Spinal Fractures
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Claims read by deepseek-v4.1-flash under definition version 3 (extract-v3) on 2026-10-27.
Classified by jev-1.13-20260917 (gold-guideline-v0.2) on 2026-10-27.
Cited sources are checked by gpt-6-sol.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
