Evaluation of Fragility Fracture Risk Using Deep Learning Based on Ultrasound Radio Frequency Signal

Overview

Journal Endocrine

Specialty Endocrinology

Date 2024 Jul 9

PMID 38982023

Authors

Wenqiang Luo

Jionglin Wu

Zhiwei Chen

Peidong Guo

Qi Zhang

Baiying Lei

Zhong Chen

Shixun Li

Changchuan Li

Haoxian Liu

Teng Ma

Jiang Liu

Xiaoyi Chen

Yue Ding

Affiliations

Soon will be listed here.

Abstract

Background: It was essential to identify individuals at high risk of fragility fracture and prevented them due to the significant morbidity, mortality, and economic burden associated with fragility fracture. The quantitative ultrasound (QUS) showed promise in assessing bone structure characteristics and determining the risk of fragility fracture.

Aims: To evaluate the performance of a multi-channel residual network (MResNet) based on ultrasonic radiofrequency (RF) signal to discriminate fragility fractures retrospectively in postmenopausal women, and compared it with the traditional parameter of QUS, speed of sound (SOS), and bone mineral density (BMD) acquired with dual X-ray absorptiometry (DXA).

Methods: Using QUS, RF signal and SOS were acquired for 246 postmenopausal women. An MResNet was utilized, based on the RF signal, to categorize individuals with an elevated risk of fragility fracture. DXA was employed to obtain BMD at the lumbar, hip, and femoral neck. The fracture history of all adult subjects was gathered. Analyzing the odds ratios (OR) and the area under the receiver operator characteristic curves (AUC) was done to evaluate the effectiveness of various methods in discriminating fragility fracture.

Results: Among the 246 postmenopausal women, 170 belonged to the non-fracture group, 50 to the vertebral group, and 26 to the non-vertebral fracture group. MResNet was competent to discriminate any fragility fracture (OR = 2.64; AUC = 0.74), Vertebral fracture (OR = 3.02; AUC = 0.77), and non-vertebral fracture (OR = 2.01; AUC = 0.69). After being modified by clinical covariates, the efficiency of MResNet was further improved to OR = 3.31-4.08, AUC = 0.81-0.83 among all fracture groups, which significantly surpassed QUS-SOS (OR = 1.32-1.36; AUC = 0.60) and DXA-BMD (OR = 1.23-2.94; AUC = 0.63-0.76).

Conclusions: This pilot cross-sectional study demonstrates that the MResNet model based on the ultrasonic RF signal shows promising performance in discriminating fragility fractures in postmenopausal women. When incorporating clinical covariates, the efficiency of the modified MResNet is further enhanced, surpassing the performance of QUS-SOS and DXA-BMD in terms of OR and AUC. These findings highlight the potential of the MResNet as a promising approach for fracture risk assessment. Future research should focus on larger and more diverse populations to validate these results and explore its clinical applications.

References

Compston J, McClung M, Leslie W . Osteoporosis. Lancet. 2019; 393(10169):364-376. DOI: 10.1016/S0140-6736(18)32112-3. View

Mitchell P, Cooper C, Fujita M, Halbout P, Akesson K, Costa M . Quality Improvement Initiatives in Fragility Fracture Care and Prevention. Curr Osteoporos Rep. 2019; 17(6):510-520. DOI: 10.1007/s11914-019-00544-8. View

Si L, Winzenberg T, Jiang Q, Chen M, Palmer A . Projection of osteoporosis-related fractures and costs in China: 2010-2050. Osteoporos Int. 2015; 26(7):1929-37. DOI: 10.1007/s00198-015-3093-2. View

Borgstrom F, Karlsson L, Ortsater G, Norton N, Halbout P, Cooper C . Fragility fractures in Europe: burden, management and opportunities. Arch Osteoporos. 2020; 15(1):59. PMC: 7166207. DOI: 10.1007/s11657-020-0706-y. View

Clynes M, Harvey N, Curtis E, Fuggle N, Dennison E, Cooper C . The epidemiology of osteoporosis. Br Med Bull. 2020; 133(1):105-117. PMC: 7115830. DOI: 10.1093/bmb/ldaa005. View

Zhang C, Feng J, Wang S, Gao P, Xu L, Zhu J . Incidence of and trends in hip fracture among adults in urban China: A nationwide retrospective cohort study. PLoS Med. 2020; 17(8):e1003180. PMC: 7410202. DOI: 10.1371/journal.pmed.1003180. View

Cauley J . Screening for Osteoporosis. JAMA. 2018; 319(24):2483-2485. DOI: 10.1001/jama.2018.5722. View

Ammann P, Rizzoli R . Bone strength and its determinants. Osteoporos Int. 2003; 14 Suppl 3:S13-8. DOI: 10.1007/s00198-002-1345-4. View

Beattie A, Cournane S, Finucane C, Walsh J, Stassen L . Quantitative Ultrasound of the Mandible as a Novel Screening Approach for Osteoporosis. J Clin Densitom. 2017; 21(1):110-118. DOI: 10.1016/j.jocd.2017.08.001. View

10.

Olszynski W, Adachi J, Hanley D, Davison K, Brown J . Comparison of Speed of Sound Measures Assessed by Multisite Quantitative Ultrasound to Bone Mineral Density Measures Assessed by Dual-Energy X-Ray Absorptiometry in a Large Canadian Cohort: the Canadian Multicentre Osteoporosis Study (CaMos). J Clin Densitom. 2015; 19(2):234-41. DOI: 10.1016/j.jocd.2015.04.004. View

11.

Hans D, Baim S . Quantitative Ultrasound (QUS) in the Management of Osteoporosis and Assessment of Fracture Risk. J Clin Densitom. 2017; 20(3):322-333. DOI: 10.1016/j.jocd.2017.06.018. View

12.

Kilappa V, Moilanen P, Xu L, Nicholson P, Timonen J, Cheng S . Low-frequency axial ultrasound velocity correlates with bone mineral density and cortical thickness in the radius and tibia in pre- and postmenopausal women. Osteoporos Int. 2010; 22(4):1103-13. DOI: 10.1007/s00198-010-1273-7. View

13.

Liu C, Xie L, Kong W, Lu X, Zhang D, Wu M . Prediction of suspicious thyroid nodule using artificial neural network based on radiofrequency ultrasound and conventional ultrasound: A preliminary study. Ultrasonics. 2019; 99:105951. DOI: 10.1016/j.ultras.2019.105951. View

14.

Klimonda Z, Karwat P, Dobruch-Sobczak K, Piotrzkowska-Wroblewska H, Litniewski J . Breast-lesions characterization using Quantitative Ultrasound features of peritumoral tissue. Sci Rep. 2019; 9(1):7963. PMC: 6538710. DOI: 10.1038/s41598-019-44376-z. View

15.

Chen Z, Luo W, Zhang Q, Lei B, Wang T, Chen Z . Osteoporosis Diagnosis Based on Ultrasound Radio Frequency Signal via Multi-channel Convolutional Neural Network. Annu Int Conf IEEE Eng Med Biol Soc. 2021; 2021:832-835. DOI: 10.1109/EMBC46164.2021.9629546. View

16.

Curry S, Krist A, Owens D, Barry M, Caughey A, Davidson K . Screening for Osteoporosis to Prevent Fractures: US Preventive Services Task Force Recommendation Statement. JAMA. 2018; 319(24):2521-2531. DOI: 10.1001/jama.2018.7498. View

17.

Viswanathan M, Reddy S, Berkman N, Cullen K, Middleton J, Nicholson W . Screening to Prevent Osteoporotic Fractures: Updated Evidence Report and Systematic Review for the US Preventive Services Task Force. JAMA. 2018; 319(24):2532-2551. DOI: 10.1001/jama.2018.6537. View

18.

Moilanen P, Maatta M, Kilappa V, Xu L, Nicholson P, Alen M . Discrimination of fractures by low-frequency axial transmission ultrasound in postmenopausal females. Osteoporos Int. 2012; 24(2):723-30. DOI: 10.1007/s00198-012-2022-x. View

19.

Gao C, Song H, Chen B, Zhang Z, Yue H . The Assessment of the Osteoporosis Self-Assessment Tool for Asians and Calcaneal Quantitative Ultrasound in Identifying Osteoporotic Fractures and Falls Among Chinese People. Front Endocrinol (Lausanne). 2021; 12:684334. PMC: 8143027. DOI: 10.3389/fendo.2021.684334. View

20.

Vogl F, Friesenbichler B, Husken L, Kramers-de Quervain I, Taylor W . Can low-frequency guided waves at the tibia paired with machine learning differentiate between healthy and osteopenic/osteoporotic subjects? A pilot study. Ultrasonics. 2019; 94:109-116. DOI: 10.1016/j.ultras.2018.11.012. View