Aug 2026· Frontiers in Medicine· Vol 13· 0 citations· 28 references
Medicine
TL;DR
AI-assisted proximal femur BMD assessment on contrast-enhanced abdominal CT showed high agreement and classification concordance with unenhanced CT-derived quantitative computed tomography (QCT), although external validation against DXA or independent QCT remains necessary.
Abstract
Objectives To evaluate the agreement and classification concordance of artificial intelligence (AI)-assisted proximal femur bone mineral density (BMD) assessment using multiphase contrast-enhanced abdominal computed tomography (CT), with unenhanced CT-derived quantitative computed tomography (QCT) serving as the reference standard. Methods This retrospective study included 429 patients (mean age, 60.48 ± 12.30 years) who underwent a standardized five-phase abdominal CT protocol, comprising unenhanced, arterial, portal venous, late venous, and excretory phases. A commercially available AI-based QCT workstation was used for semi-automatic proximal femur segmentation and volumetric BMD (vBMD) and T-score calculation. Repeated-measures ANOVA and Bland-Altman analysis were performed to assess inter-phase differences and agreement. Classification concordance was evaluated using the unenhanced CT-derived QCT results as the reference standard. Results The study cohort comprised 378 osteoporotic patients and 51 non-osteoporotic patients, categorized according to unenhanced CT-derived T-score reference values. Results from repeated-measures ANOVA indicated significant phase-related variations in T-scores and vBMD (both P < 0.001). Subsequent post-hoc comparisons revealed that T-scores and vBMD in the arterial and portal venous phases were consistent with the unenhanced phase, whereas modest yet statistically significant deviations were observed in the late venous and excretory phases. Bland-Altman analyses showed minimal mean bias across arterial, portal venous, and excretory phases; however, the late venous phase exhibited broader limits of agreement (LoA). Classification concordance compared to the unenhanced reference was consistently high across all phases, ranging from 98.14 to 99.53%. Additionally, intraobserver reproducibility remained excellent, with ICC values between 0.964 and 0.996. Conclusion AI-assisted proximal femur BMD assessment on contrast-enhanced abdominal CT showed high agreement and classification concordance with unenhanced CT-derived QCT. The arterial and portal venous phases were particularly suitable for opportunistic osteoporosis screening, although external validation against DXA or independent QCT remains necessary.
Three-dimensional HU represents a novel vBMD assessment methodology that achieves diagnostic parity with QCT using conventional CT scanners without extra radiation exposure or specialized equipment, and demonstrates that precise, universally accessible osteoporosis screening is now achievable.
Rongkun Chang, Jinxin Gu, Yu-Mei Ding et al.· Journal of Neurosurgery : Sp...· 0 citations
VBQ can serve as an opportunistic exploratory screening marker of low BMD and FBQcsf may complement VBQ by identifying early marrow-related changes, although further validation is required.
M. Müller, João Paulo Ferreira, Laura Mulazzani Minuzzi Macedo et al.· Skeletal Radiology· 0 citations
Both HU and VBQ offer useful assessments of vertebral bone quality, but HU provides higher and more stable diagnostic accuracy, demonstrating higher sensitivity, specificity, and accuracy for detecting osteopenia and osteoporosis.
Omar Lubbad, Akram Hagos, Laila Lubbad et al.· European Radiology· 0 citations
Purpose To develop and validate an AI algorithm that enables dual-site (spine and hip) BMD assessment for opportunistic osteoporosis screening using a single kidney-ureter-bladder (KUB) radiograph. Materials and methods In this institutional review board approved prospective study, we developed the SHield pipeline for opportunistic osteoporosis screening. From an initial dataset of 15,175 KUB images, a final cohort of 4,436 patients (mean age 69.0 ± 12.2 years) was included for model development after exclusions for suboptimal quality or incomplete region of interests. The pipeline analyzes both the spine and hip regions on a single KUB to predict site-specific BMD values. Finally, it integrates these dual-site predictions to determine the lowest T-score, mimicking the standard clinical DXA reporting protocol which evaluates both the lumbar spine and proximal femur. Results On the internal test set (628 patients), the hip and spine AI models demonstrated Pearson correlation coefficients of 0.887 and 0.921 and RMSEs of 0.057 and 0.062, respectively, compared to DXA-measured BMD, achieving AUCs of 0.894 and 0.956 for predicting T-scores ≤-2.5. In a subsequent prospective feasibility study (51 patients), we employed a conservative detection threshold of Tm-score ≤-2.8 to minimize false positives and unnecessary referrals. The final AI pipeline achieved a Pearson correlation of 0.959, an AUC of 0.969, 100% PPV, 100% specificity, and 83.8% NPV. Conclusion This paper presents the first AI pipeline that enables gold-standard-aligned, dual-site BMD estimation and opportunistic osteoporosis screening from a single KUB radiograph. Validated prospectively, its high accuracy and specificity confirm its potential to significantly increase early detection rates without overwhelming clinical workflows.
Hsuan-Yin Lin, J. Chai, Qingzong Tseng et al.· Frontiers in Endocrinology· 0 citations
Background/Objectives: This study aimed to evaluate whether artificial intelligence-derived vertebral volumetric bone mineral density (AI-vBMD) and paraspinal intermuscular adipose tissue (IMAT) ratio from routine computed tomography (CT) could identify moderate-to-severe vertebral compression fractures (VCFs) in breast cancer survivors, and whether paraspinal IMAT ratio and routinely available clinical variables improved diagnostic performance. Methods: This retrospective study included 275 women with breast cancer who underwent routine non-contrast CT and lumbar quantitative computed tomography (QCT). Hounsfield unit-derived volumetric bone mineral density (HU-vBMD) was derived using a QCT-referenced HU-to-vBMD conversion equation, whereas AI-vBMD and paraspinal IMAT ratio were extracted using automated software. Moderate-to-severe VCF was defined as Genant grade ≥ 2. Agreement with QCT-vBMD was assessed using correlation, intraclass correlation coefficient (ICC), and Bland–Altman analysis. Model discrimination was evaluated using receiver operating characteristic analysis and DeLong tests. Results: Moderate-to-severe VCF was present in 75 patients (27.3%). HU-vBMD and AI-vBMD showed excellent agreement with QCT-vBMD (ICC, 0.978 and 0.987, respectively). AI-vBMD outperformed HU-vBMD for identifying VCFs (AUC, 0.738 vs. 0.714; p < 0.001). IMAT ratio showed comparable standalone discrimination to AI-vBMD (AUC, 0.760 vs. 0.738; p = 0.604). Adding IMAT ratio to AI-vBMD improved discrimination (AUC, 0.786 vs. 0.738; p = 0.038). The full model incorporating clinical covariates achieved the highest AUC (0.828; 95% CI, 0.778–0.878). Conclusions: AI-vBMD and paraspinal IMAT ratio automatically extracted from routine CT improved the diagnostic assessment of prevalent moderate-to-severe VCFs in breast cancer survivors. This study supports an automated CT-based approach that integrates vertebral bone density and paraspinal muscle–fat information for opportunistic identification of clinically relevant VCFs.
Chen Wan, Lingquan Kong, Jie Hao et al.· Journal of Clinical Medicine· 0 citations
A two-stage decomposition that separates systemic skeletal fragility from within-patient vertebral outlier status produces well-calibrated per-vertebra fracture-risk estimates from routine clinical lumbar spine CT and opportunistic abdominal CT.
K. Riazanovskiy, Dāvids Orlovs, Jekaterina Stepanova et al.· Medicina· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
