1
|
Zhang B, Chen Z, Yan R, Lai B, Wu G, You J, Wu X, Duan J, Zhang S. Development and Validation of a Feature-Based Broad-Learning System for Opportunistic Osteoporosis Screening Using Lumbar Spine Radiographs. Acad Radiol 2024; 31:84-92. [PMID: 37495426 DOI: 10.1016/j.acra.2023.07.002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/10/2023] [Revised: 07/04/2023] [Accepted: 07/05/2023] [Indexed: 07/28/2023]
Abstract
RATIONALE AND OBJECTIVES Osteoporosis is primarily diagnosed using dual-energy X-ray absorptiometry (DXA); yet, DXA is significantly underutilized, causing osteoporosis, an underdiagnosed condition. We aimed to provide an opportunistic approach to screen for osteoporosis using artificial intelligence based on lumbar spine X-ray radiographs. MATERIALS AND METHODS In this institutional review board-approved retrospective study, female patients aged ≥50 years who received both X-ray scans and DXA of the lumbar vertebrae, in three centers, were included. A total of 1180 cases were used for training and 145 cases were used for testing. We proposed a novel broad-learning system (BLS) and then compared the performance of BLS models using radiomic features and deep features as a source of input. The deep features were extracted using ResNet18 and VGG11, respectively. The diagnostic performances of these BLS models were evaluated with the area under the curve (AUC), sensitivity, and specificity. RESULTS The incidence rate of osteoporosis in the training and test sets was 35.9% and 37.9%, respectively. The radiomic feature-based BLS model achieved higher testing AUC (0.802 vs. 0.654 vs. 0.632, both P = .002), sensitivity (78.2% vs. 56.4% vs. 50.9%), and specificity (82.2% vs. 74,4% vs. 75.6%) than the two deep feature-based BLS models. CONCLUSION Our proposed radiomic feature-based BLS model has the potential to expand osteoporosis screening to a broader population by identifying osteoporosis on lumbar spine X-ray radiographs.
Collapse
Affiliation(s)
- Bin Zhang
- Department of Radiology, The First Affiliated Hospital of Jinan University, No. 613 Huangpu West Road, Tianhe District, Guangzhou, Guangdong 510627, China (B.Z., R.Y., J.Y., X.W., S.Z.)
| | - Zhangtianyi Chen
- College of Information Science and Technology, Jinan University, Guangzhou, Guangdong, China (Z.C., B.L., G.W., J.D.)
| | - Ruike Yan
- Department of Radiology, The First Affiliated Hospital of Jinan University, No. 613 Huangpu West Road, Tianhe District, Guangzhou, Guangdong 510627, China (B.Z., R.Y., J.Y., X.W., S.Z.)
| | - Bifan Lai
- College of Information Science and Technology, Jinan University, Guangzhou, Guangdong, China (Z.C., B.L., G.W., J.D.)
| | - Guangheng Wu
- College of Information Science and Technology, Jinan University, Guangzhou, Guangdong, China (Z.C., B.L., G.W., J.D.)
| | - Jingjing You
- Department of Radiology, The First Affiliated Hospital of Jinan University, No. 613 Huangpu West Road, Tianhe District, Guangzhou, Guangdong 510627, China (B.Z., R.Y., J.Y., X.W., S.Z.)
| | - Xuewei Wu
- Department of Radiology, The First Affiliated Hospital of Jinan University, No. 613 Huangpu West Road, Tianhe District, Guangzhou, Guangdong 510627, China (B.Z., R.Y., J.Y., X.W., S.Z.)
| | - Junwei Duan
- College of Information Science and Technology, Jinan University, Guangzhou, Guangdong, China (Z.C., B.L., G.W., J.D.); Guangdong Provincial Key Laboratory of Traditional Chinese Medicine Informatization, Jinan University, Guangzhou, Guangdong, China (J.D.)
| | - Shuixing Zhang
- Department of Radiology, The First Affiliated Hospital of Jinan University, No. 613 Huangpu West Road, Tianhe District, Guangzhou, Guangdong 510627, China (B.Z., R.Y., J.Y., X.W., S.Z.).
| |
Collapse
|
2
|
Carey JJ, Chih-Hsing Wu P, Bergin D. Risk assessment tools for osteoporosis and fractures in 2022. Best Pract Res Clin Rheumatol 2022; 36:101775. [PMID: 36050210 DOI: 10.1016/j.berh.2022.101775] [Citation(s) in RCA: 15] [Impact Index Per Article: 7.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/14/2022]
Abstract
Osteoporosis is one of the frequently encountered non-communicable diseases in the world today. Several hundred million people have osteoporosis, with many more at risk. The clinical feature is a fragility fracture (FF), which results in major reductions in the quality and quantity of life, coupled with a huge financial burden. In recognition of the growing importance, the World Health Organisation established a working group 30 years ago tasked with providing a comprehensive report to understand and assess the risk of osteoporosis in postmenopausal women. Dual-energy X-ray absorptiometry (DXA) is the most widely endorsed technology for assessing the risk of fracture or diagnosing osteoporosis before a fracture occurs, but others are available. In clinical practice, important distinctions are essential to optimise the use of risk assessments. Traditional tools lack specificity and were designed for populations to identify groups at higher risk using a 'one-size-fits-all' approach. Much has changed, though the purpose of risk assessment tools remains the same. In 2022, many tools are available to aid the identification of those most at risk, either likely to have osteoporosis or suffer the clinical consequence. Modern technology, enhanced imaging, proteomics, machine learning, artificial intelligence, and big data science will greatly advance a more personalised risk assessment into the future. Clinicians today need to understand not only which tool is most effective and efficient for use in their practice, but also which tool to use for which patient and for what purpose. A greater understanding of the process of risk assessment, deciding who should be screened, and how to assess fracture risk and prognosis in older men and women more comprehensively will greatly reduce the burden of osteoporosis for patients, society, and healthcare systems worldwide. In this paper, we review the current status of risk assessment, screening and best practice for osteoporosis, summarise areas of uncertainty, and make some suggestions for future developments, including a more personalised approach for individuals.
Collapse
Affiliation(s)
- John J Carey
- National University of Ireland Galway, 1007, Clinical Sciences Institute, Galway, H91 V4AY, Ireland.
| | - Paulo Chih-Hsing Wu
- Institute of Gerontology, College of Medicine, National Cheng Kung University, Taiwan; Department of Family Medicine, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, Director, Obesity/Osteoporosis Special Clinic, 138 Sheng-Li Road, Tainan, 70428, Taiwan
| | - Diane Bergin
- National University of Ireland Galway, 1007, Clinical Sciences Institute, Galway, H91 V4AY, Ireland; Galway University Hospitals, Ireland
| |
Collapse
|
3
|
Pickhardt PJ, Nguyen T, Perez AA, Graffy PM, Jang S, Summers RM, Garrett JW. Improved CT-based Osteoporosis Assessment with a Fully Automated Deep Learning Tool. Radiol Artif Intell 2022; 4:e220042. [PMID: 36204542 PMCID: PMC9530763 DOI: 10.1148/ryai.220042] [Citation(s) in RCA: 9] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/07/2022] [Revised: 08/12/2022] [Accepted: 08/17/2022] [Indexed: 11/11/2022]
Abstract
Purpose To develop, test, and validate a deep learning (DL) tool that improves upon a previous feature-based CT image processing bone mineral density (BMD) algorithm and compare it against the manual reference standard. Materials and Methods This single-center, retrospective, Health Insurance Portability and Accountability Act-compliant study included manual L1 trabecular Hounsfield unit measurements from abdominal CT scans in 11 035 patients (mean age, 58 years ± 12 [SD]; 6311 women) as the reference standard. Automated level selection and L1 trabecular region of interest (ROI) placement were then performed in this CT cohort with both a previously validated feature-based image processing tool and a new DL tool. Overall technical success rates and agreement with the manual reference standard were assessed. Results The overall success rate of the DL tool in this heterogeneous patient cohort was significantly higher than that of the older image processing BMD algorithm (99.3% vs 89.4%, P < .001). Using this DL tool, the closest median Hounsfield unit values for single-, three-, and seven-slice vertebral ROIs were within 5% of the manual reference standard Hounsfield unit values in 35.1%, 56.9%, and 85.8% of scans; within 10% in 56.6%, 75.6%, and 92.9% of scans; and within 25% in 76.5%, 89.3%, and 97.1% of scans, respectively. Trade-offs in sensitivity and specificity for osteoporosis assessment were observed from the single-slice approach (sensitivity, 39.4%; specificity, 98.3%) to the minimum value of the multislice approach (for seven contiguous slices; sensitivity, 71.3% and specificity, 94.6%). Conclusion The new DL BMD tool demonstrated a higher success rate than the older feature-based image processing tool, and its outputs can be targeted for higher specificity or sensitivity for osteoporosis assessment.Keywords: CT, CT-Quantitative, Abdomen/GI, Skeletal-Axial, Spine, Deep Learning, Machine Learning Supplemental material is available for this article. © RSNA, 2022.
Collapse
Affiliation(s)
- Perry J. Pickhardt
- From the Department of Radiology, University of Wisconsin School of Medicine & Public Health, E3/311 Clinical Science Center, 600 Highland Ave, Madison, WI 53792-3252 (P.J.P., T.N., A.A.P., P.M.G., S.J., J.W.G.); and Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Department of Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, Md (R.M.S.)
| | - Thang Nguyen
- From the Department of Radiology, University of Wisconsin School of Medicine & Public Health, E3/311 Clinical Science Center, 600 Highland Ave, Madison, WI 53792-3252 (P.J.P., T.N., A.A.P., P.M.G., S.J., J.W.G.); and Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Department of Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, Md (R.M.S.)
| | - Alberto A. Perez
- From the Department of Radiology, University of Wisconsin School of Medicine & Public Health, E3/311 Clinical Science Center, 600 Highland Ave, Madison, WI 53792-3252 (P.J.P., T.N., A.A.P., P.M.G., S.J., J.W.G.); and Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Department of Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, Md (R.M.S.)
| | - Peter M. Graffy
- From the Department of Radiology, University of Wisconsin School of Medicine & Public Health, E3/311 Clinical Science Center, 600 Highland Ave, Madison, WI 53792-3252 (P.J.P., T.N., A.A.P., P.M.G., S.J., J.W.G.); and Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Department of Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, Md (R.M.S.)
| | - Samuel Jang
- From the Department of Radiology, University of Wisconsin School of Medicine & Public Health, E3/311 Clinical Science Center, 600 Highland Ave, Madison, WI 53792-3252 (P.J.P., T.N., A.A.P., P.M.G., S.J., J.W.G.); and Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Department of Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, Md (R.M.S.)
| | - Ronald M. Summers
- From the Department of Radiology, University of Wisconsin School of Medicine & Public Health, E3/311 Clinical Science Center, 600 Highland Ave, Madison, WI 53792-3252 (P.J.P., T.N., A.A.P., P.M.G., S.J., J.W.G.); and Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Department of Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, Md (R.M.S.)
| | - John W. Garrett
- From the Department of Radiology, University of Wisconsin School of Medicine & Public Health, E3/311 Clinical Science Center, 600 Highland Ave, Madison, WI 53792-3252 (P.J.P., T.N., A.A.P., P.M.G., S.J., J.W.G.); and Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Department of Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, Md (R.M.S.)
| |
Collapse
|
4
|
Zhao C, Herbst M, Weber T, Luckner C, Vogt S, Ritschl L, Kappler S, Siewerdsen JH, Zbijewski W. Slot-scan dual-energy bone densitometry using motorized X-ray systems. Med Phys 2021; 48:6673-6695. [PMID: 34628651 DOI: 10.1002/mp.15272] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/06/2021] [Revised: 08/31/2021] [Accepted: 09/24/2021] [Indexed: 11/12/2022] Open
Abstract
PURPOSE We investigate the feasibility of slot-scan dual-energy (DE) bone densitometry on motorized radiographic equipment. This approach will enable fast quantitative measurements of areal bone mineral density (aBMD) for opportunistic evaluation of osteoporosis. METHODS We investigated DE slot-scan protocols to obtain aBMD measurements at the lumbar spine (L-spine) and hip using a motorized x-ray platform capable of synchronized translation of the x-ray source and flat-panel detector (FPD). The slot dimension was 5 × 20 cm2 . The DE slot views were processed as follows: (1) convolution kernel-based scatter correction, (2) unfiltered backprojection to tile the slots into long-length radiographs, and (3) projection-domain DE decomposition, consisting of an initial adipose-water decomposition in a bone-free region followed by water-CaHA decomposition with adjustment for adipose content. The accuracy and reproducibility of slot-scan aBMD measurements were investigated using a high-fidelity simulator of a robotic x-ray system (Siemens Multitom Rax) in a total of 48 body phantom realizations: four average bone density settings (cortical bone mass fraction: 10-40%), four body sizes (waist circumference, WC = 70-106 cm), and three lateral shifts of the body within the slot field of view (FOV) (centered and ±1 cm off-center). Experimental validations included: (1) x-ray test-bench feasibility study of adipose-water decomposition and (2) initial demonstration of slot-scan DE bone densitometry on the robotic x-ray system using the European Spine Phantom (ESP) with added attenuation (polymethyl methacrylate [PMMA] slabs) ranging 2 to 6 cm thick. RESULTS For the L-spine, the mean aBMD error across all WC settings ranged from 0.08 g/cm2 for phantoms with average cortical bone fraction wcortical = 10% to ∼0.01 g/cm2 for phantoms with wcortical = 40%. The L-spine aBMD measurements were fairly robust to changes in body size and positioning, e.g., coefficient of variation (CV) for L1 with wcortical = 30% was ∼0.034 for various WC and ∼0.02 for an obese patient (WC = 106 cm) changing lateral shift. For the hip, the mean aBMD error across all phantom configurations was about 0.07 g/cm2 for a centered patient. The reproducibility of hip aBMD was slightly worse than in the L-spine (e.g., in the femoral neck, the CV with respect to changing WC was ∼0.13 for phantom realizations with wcortical = 30%) due to more challenging scatter estimation in the presence of an air-tissue interface within the slot FOV. The aBMD of the hip was therefore sensitive to lateral positioning of the patient, especially for obese patients: e.g., the CV with respect to patient lateral shift for femoral neck with WC = 106 cm and wcortical = 30% was 0.14. Empirical evaluations confirmed substantial reduction in aBMD errors with the proposed adipose estimation procedure and demonstrated robust aBMD measurements on the robotic x-ray system, with aBMD errors of ∼0.1 g/cm2 across all three simulated ESP vertebrae and all added PMMA attenuator settings. CONCLUSIONS We demonstrated that accurate aBMD measurements can be obtained on a motorized FPD-based x-ray system using DE slot-scans with kernel-based scatter correction, backprojection-based slot view tiling, and DE decomposition with adipose correction.
Collapse
Affiliation(s)
- Chumin Zhao
- Department of Biomedical Engineering, Johns Hopkins University, Baltimore, Maryland, USA
| | | | | | | | | | | | | | - Jeffrey H Siewerdsen
- Department of Biomedical Engineering, Johns Hopkins University, Baltimore, Maryland, USA.,Department of Radiology, Johns Hopkins University, Baltimore, Maryland, USA
| | - Wojciech Zbijewski
- Department of Biomedical Engineering, Johns Hopkins University, Baltimore, Maryland, USA
| |
Collapse
|