Development of a system to assess the two- and three-dimensional bone mineral density of the lumbar vertebrae from clinical quantitative CT images

Uemura, Keisuke; Fujimori, Takahito; Otake, Yoshito; Shimomoto, Yuga; Kono, Sotaro; Takashima, Kazuma; Hamada, Hirofumi; Takenaka, Shota; Kaito, Takashi; Sato, Yoshinobu; Sugano, Nobuhiko; Okada, Seiji

doi:10.1007/s11657-023-01216-y

Cited by 5 publications

(4 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This result forms the cornerstone of the analyses of the current article, and it is in agreement with other studies such as the mixed-sex cohort study of Chen et al (Fig. 2B) [20], Lin et al [21], and Uemura et al [22].…”

supporting

confidence: 92%

Quantitative CT lumbar spine BMD cutpoint value for classifying osteoporosis among older Chinese men can be the same as that of older Chinese women, both much lower than the value for Caucasians

Wáng,

Chan,

et al. 2024

Skeletal Radiol

View full text Add to dashboard Cite

For older Caucasian women and men, the QCT (quantitative CT) lumbar spine (LS) bone mineral density (BMD) threshold for classifying osteoporosis is 80 mg/ml. It was recently proposed that, for older East Asian women, the QCT LS BMD value equivalent to the Caucasian women’s threshold of 80 mg/mL is about 45∼50 mg/ml. For a data of 328 cases of Chinese men (age: 73.6 ± 4.4 years) who had QCT LS BMD and DXA LS BMD at the same time and with the DXA BMD value of ≤ 0.613 g/cm2 to classify osteoporosis, the corresponding QCT LS BMD threshold is 53 mg/ml. Osteoporotic-like vertebral fracture sum score (OLVFss) ≤ -2.5 has been proposed to diagnose osteoporosis. For 316 cases of Chinese men (age:73.7±4.5 years), OLVFss ≤ -2.5 defines an osteoporosis prevalence of 4.4%; to achieve this osteoporosis prevalence, the corresponding QCT LS BMD value is < 47.5 mg/ml. In the China Action on Spine and Hip Status study, a Genant grades 2/3 radiographic ‘osteoporotic vertebral fracture’ prevalence was 2.84% for Chinese men (total n = 1267, age: 62.77 ± 9.20 years); to achieve this osteoporosis prevalence, the corresponding BMD value was < 42.5 mg/ml. In a study of 357 Beijing older men, according to the clinical fragility fracture prevalence and femoral neck DXA T-score, the QCT LS BMD value to classify osteoporosis was between 39.45 mg/ml and 51.38 mg/ml. For older Chinese men (≥ 50 years), we recommend the cutpoint for the QCT LS BMD definition of osteoporosis to be 45∼50 mg/ml which is the same as the value for Chinese women.

show abstract

supporting

confidence: 92%

Quantitative CT lumbar spine BMD cutpoint value for classifying osteoporosis among older Chinese men can be the same as that of older Chinese women, both much lower than the value for Caucasians

Wáng,

Chan,

et al. 2024

Skeletal Radiol

View full text Add to dashboard Cite

show abstract

“…For Italian women, DXA LS BMDs of 0.819 and 0.786 g/cm 2 are equivalent to QCT LS BMDs of around 82 and 77.5 mg/mL, respectively ( 48 - 51 ). Based on the data of Lin et al ( 17 ) and Yu et al ( 52 ) and supported by the data of Uemura et al ( 22 ), for Chinese women, a DXA LS BMD of 0.624 g/cm 2 is equivalent to a QCT value of around 45 mg/mL, and 0.589 g/cm 2 is equivalent to less than 45 mg/mL QCT value [see Figure 3 in reference ( 29 )].…”

Section: Older Chinese Women Experience Vertebral Fracture At a Lower...mentioning

confidence: 52%

More evidence to support a lower quantitative computed tomography (QCT) lumbar spine bone mineral density (BMD) cutpoint value for classifying osteoporosis among older East Asian women than for Caucasians

Wáng,

Yu,

Leung

et al. 2024

Quant Imaging Med Surg

View full text Add to dashboard Cite

“…The accuracy of a machine learning model utilizing CT attenuation values from multiple bones in conjunction with clinical and demographic variables exceeded that of models relying on a single bone. Uemura K. et al [120] demonstrated that their model, when limited to sampling just the L1 vertebral region, achieved an AUC of 0.582, significantly lower than when they expanded their sampling to include the L1-L4 vertebrae (AUC = 0.941). Similarly, Sebro R et al [137] showed that using data from multiple bones in the wrist yielded superior accuracy in contrast to relying on CT attenuation values from a single bone.…”

Section: Technical Considerations: Areas Sampledmentioning

confidence: 96%

“…Deep Learning-Based Analysis (e.g., CNNs): CNNs employ deep learning to automatically extract valuable imaging features by learning patterns directly from input images [118]. This enables the detection and processing of distinct diagnostic patterns and imaging features that go beyond what a human reader can accomplish [120], potentially improving BMD classification.…”

mentioning

confidence: 99%

Artificial Intelligence Applications for Osteoporosis Classification Using Computed Tomography

Ong,

Liu,

Makmur

et al. 2023

Bioengineering

View full text Add to dashboard Cite

Osteoporosis, marked by low bone mineral density (BMD) and a high fracture risk, is a major health issue. Recent progress in medical imaging, especially CT scans, offers new ways of diagnosing and assessing osteoporosis. This review examines the use of AI analysis of CT scans to stratify BMD and diagnose osteoporosis. By summarizing the relevant studies, we aimed to assess the effectiveness, constraints, and potential impact of AI-based osteoporosis classification (severity) via CT. A systematic search of electronic databases (PubMed, MEDLINE, Web of Science, ClinicalTrials.gov) was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A total of 39 articles were retrieved from the databases, and the key findings were compiled and summarized, including the regions analyzed, the type of CT imaging, and their efficacy in predicting BMD compared with conventional DXA studies. Important considerations and limitations are also discussed. The overall reported accuracy, sensitivity, and specificity of AI in classifying osteoporosis using CT images ranged from 61.8% to 99.4%, 41.0% to 100.0%, and 31.0% to 100.0% respectively, with areas under the curve (AUCs) ranging from 0.582 to 0.994. While additional research is necessary to validate the clinical efficacy and reproducibility of these AI tools before incorporating them into routine clinical practice, these studies demonstrate the promising potential of using CT to opportunistically predict and classify osteoporosis without the need for DEXA.

show abstract

Development of a system to assess the two- and three-dimensional bone mineral density of the lumbar vertebrae from clinical quantitative CT images

Cited by 5 publications

References 23 publications

Quantitative CT lumbar spine BMD cutpoint value for classifying osteoporosis among older Chinese men can be the same as that of older Chinese women, both much lower than the value for Caucasians

Quantitative CT lumbar spine BMD cutpoint value for classifying osteoporosis among older Chinese men can be the same as that of older Chinese women, both much lower than the value for Caucasians

More evidence to support a lower quantitative computed tomography (QCT) lumbar spine bone mineral density (BMD) cutpoint value for classifying osteoporosis among older East Asian women than for Caucasians

Artificial Intelligence Applications for Osteoporosis Classification Using Computed Tomography

Contact Info

Product

Resources

About