1
|
Naghavi M, De Oliveira I, Mao SS, Jaberzadeh A, Montoya J, Zhang C, Atlas K, Manubolu V, Montes M, Li D, Atlas T, Reeves A, Henschke C, Yankelevitz D, Budoff M. Opportunistic AI-enabled automated bone mineral density measurements in lung cancer screening and coronary calcium scoring CT scans are equivalent. Eur J Radiol Open 2023; 10:100492. [PMID: 37214544 PMCID: PMC10196960 DOI: 10.1016/j.ejro.2023.100492] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/24/2023] Open
Abstract
Rationale and objectives We previously reported a novel manual method for measuring bone mineral density (BMD) in coronary artery calcium (CAC) scans and validated our method against Dual X-Ray Absorptiometry (DEXA). Furthermore, we have developed and validated an artificial intelligence (AI) based automated BMD (AutoBMD) measurement as an opportunistic add-on to CAC scans that recently received FDA approval. In this report, we present evidence of equivalency between AutoBMD measurements in cardiac vs lung CT scans. Materials and methods AI models were trained using 132 cases with 7649 (3 mm) slices for CAC, and 37 cases with 21918 (0.5 mm) slices for lung scans. To validate AutoBMD against manual measurements, we used 6776 cases of BMD measured manually on CAC scans in the Multi-Ethnic Study of Atherosclerosis (MESA). We then used 165 additional cases from Harbor UCLA Lundquist Institute to compare AutoBMD in patients who underwent both cardiac and lung scans on the same day. Results Mean±SD for age was 69 ± 9.4 years with 52.4% male. AutoBMD in lung and cardiac scans, and manual BMD in cardiac scans were 153.7 ± 43.9, 155.1 ± 44.4, and 163.6 ± 45.3 g/cm3, respectively (p = 0.09). Bland-Altman agreement analysis between AutoBMD lung and cardiac scans resulted in 1.37 g/cm3 mean differences. Pearson correlation coefficient between lung and cardiac AutoBMD was R2 = 0.95 (p < 0.0001). Conclusion Opportunistic BMD measurement using AutoBMD in CAC and lung cancer screening scans is promising and yields similar results. No extra radiation plus the high prevalence of asymptomatic osteoporosis makes AutoBMD an ideal screening tool for osteopenia and osteoporosis in CT scans done for other reasons.
Collapse
Affiliation(s)
- Morteza Naghavi
- HeartLung AI Technologies, TMC Innovation, 2450 Holcomb Blvd, Houston, TX 77021
| | - Isabel De Oliveira
- HeartLung AI Technologies, TMC Innovation, 2450 Holcomb Blvd, Houston, TX 77021
| | - Song Shou Mao
- Lundquist Institute, Harbor UCLA Medical Center, 1124 W Carson St, Torrance, CA 90502, USA
| | | | - Juan Montoya
- HeartLung AI Technologies, TMC Innovation, 2450 Holcomb Blvd, Houston, TX 77021
| | - Chenyu Zhang
- HeartLung AI Technologies, TMC Innovation, 2450 Holcomb Blvd, Houston, TX 77021
| | - Kyle Atlas
- HeartLung AI Technologies, TMC Innovation, 2450 Holcomb Blvd, Houston, TX 77021
| | - Venkat Manubolu
- Lundquist Institute, Harbor UCLA Medical Center, 1124 W Carson St, Torrance, CA 90502, USA
| | - Marlon Montes
- HeartLung AI Technologies, TMC Innovation, 2450 Holcomb Blvd, Houston, TX 77021
| | - Dong Li
- Emory University, 201 Dowman Dr, Atlanta, GA 30322, USA
| | - Thomas Atlas
- HeartLung AI Technologies, TMC Innovation, 2450 Holcomb Blvd, Houston, TX 77021
| | | | | | | | - Matthew Budoff
- Lundquist Institute, Harbor UCLA Medical Center, 1124 W Carson St, Torrance, CA 90502, USA
| |
Collapse
|
2
|
Guo Z, Blake GM, Li K, Liang W, Zhang W, Zhang Y, Xu L, Wang L, Brown JK, Cheng X, Pickhardt PJ. Liver Fat Content Measurement with Quantitative CT Validated against MRI Proton Density Fat Fraction: A Prospective Study of 400 Healthy Volunteers. Radiology 2020; 294:89-97. [PMID: 31687918 DOI: 10.1148/radiol.2019190467] [Citation(s) in RCA: 58] [Impact Index Per Article: 14.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/03/2023]
Abstract
Background Although chemical shift-encoded (CSE) MRI proton density fat fraction (PDFF) is the current noninvasive reference standard for liver fat quantification, the liver is more frequently imaged with CT. Purpose To validate quantitative CT measurements of liver fat against the MRI PDFF reference standard. Materials and Methods In this prospective study, 400 healthy participants were recruited between August 2015 and July 2016. Each participant underwent same-day abdominal unenhanced quantitative CT with a calibration phantom and CSE 3.0-T MRI. CSE MRI liver fat measurements were used to calibrate an equation to adjust CT fat measurements and put them on the PDFF measurement scale. CT and PDFF liver fat measurements were plotted as histograms, medians, and interquartile ranges compared; scatterplots and Bland-Altman plots obtained; and Pearson correlation coefficients calculated. Receiver operating characteristic curves including areas under the curve were evaluated for mild (PDFF, 5%) and moderate (PDFF, 14%) steatosis thresholds for both raw and adjusted CT measurements. Sensitivity, specificity, positive predictive value, and negative predictive value were calculated. Results Four hundred volunteers (mean age, 52.6 years ± 15.2; 227 women) were evaluated. MRI PDFF measurements of liver fat ranged between 0% and 28%, with 41.5% (166 of 400) of participants with PDFF greater than 5%. Both raw and adjusted quantitative CT values correlated well with MRI PDFF (r2 = 0.79; P < .001). Bland-Altman analysis of adjusted CT values showed no slope or bias. Both raw and adjusted CT had areas under the receiver operating characteristic curve of 0.87 and 0.99, respectively, to identify participants with mild (PDFF, >5%) and moderate (PDFF, >14%) steatosis, respectively. The sensitivity, specificity, positive predictive value, and negative predictive value for unadjusted CT was 75.9% (126 of 166), 85.0% (199 of 234), 78.3% (126 of 161), and 83.3% (199 of 239), respectively, for PDFF greater than 5%; and 84.8% (28 of 33), 98.4% (361 of 367), 82.4% (28 of 34), and 98.6% (361 of 366), respectively, for PDFF greater than 14%. Results for adjusted CT were mostly identical. Conclusion Quantitative CT liver fat exhibited good correlation and accuracy with proton density fat fraction measured with chemical shift-encoded MRI. © RSNA, 2019 Online supplemental material is available for this article.
Collapse
Affiliation(s)
- Zhe Guo
- From the Department of Radiology, Beijing Jishuitan Hospital, 31 Xinjiekou East Street, Beijing 100035, China (Z.G., K.L., W.L., W.Z., Y.Z., L.X., L.W., X.C.); School of Biomedical Engineering & Imaging Sciences, King's College London, St Thomas' Hospital, London, England (G.M.B.); Mindways Software Inc, Austin, Tex (J.K.B.); and Department of Radiology, University of Wisconsin School of Medicine and Public Health, Madison, Wis (P.J.P.)
| | - Glen M Blake
- From the Department of Radiology, Beijing Jishuitan Hospital, 31 Xinjiekou East Street, Beijing 100035, China (Z.G., K.L., W.L., W.Z., Y.Z., L.X., L.W., X.C.); School of Biomedical Engineering & Imaging Sciences, King's College London, St Thomas' Hospital, London, England (G.M.B.); Mindways Software Inc, Austin, Tex (J.K.B.); and Department of Radiology, University of Wisconsin School of Medicine and Public Health, Madison, Wis (P.J.P.)
| | - Kai Li
- From the Department of Radiology, Beijing Jishuitan Hospital, 31 Xinjiekou East Street, Beijing 100035, China (Z.G., K.L., W.L., W.Z., Y.Z., L.X., L.W., X.C.); School of Biomedical Engineering & Imaging Sciences, King's College London, St Thomas' Hospital, London, England (G.M.B.); Mindways Software Inc, Austin, Tex (J.K.B.); and Department of Radiology, University of Wisconsin School of Medicine and Public Health, Madison, Wis (P.J.P.)
| | - Wei Liang
- From the Department of Radiology, Beijing Jishuitan Hospital, 31 Xinjiekou East Street, Beijing 100035, China (Z.G., K.L., W.L., W.Z., Y.Z., L.X., L.W., X.C.); School of Biomedical Engineering & Imaging Sciences, King's College London, St Thomas' Hospital, London, England (G.M.B.); Mindways Software Inc, Austin, Tex (J.K.B.); and Department of Radiology, University of Wisconsin School of Medicine and Public Health, Madison, Wis (P.J.P.)
| | - Wei Zhang
- From the Department of Radiology, Beijing Jishuitan Hospital, 31 Xinjiekou East Street, Beijing 100035, China (Z.G., K.L., W.L., W.Z., Y.Z., L.X., L.W., X.C.); School of Biomedical Engineering & Imaging Sciences, King's College London, St Thomas' Hospital, London, England (G.M.B.); Mindways Software Inc, Austin, Tex (J.K.B.); and Department of Radiology, University of Wisconsin School of Medicine and Public Health, Madison, Wis (P.J.P.)
| | - Yong Zhang
- From the Department of Radiology, Beijing Jishuitan Hospital, 31 Xinjiekou East Street, Beijing 100035, China (Z.G., K.L., W.L., W.Z., Y.Z., L.X., L.W., X.C.); School of Biomedical Engineering & Imaging Sciences, King's College London, St Thomas' Hospital, London, England (G.M.B.); Mindways Software Inc, Austin, Tex (J.K.B.); and Department of Radiology, University of Wisconsin School of Medicine and Public Health, Madison, Wis (P.J.P.)
| | - Li Xu
- From the Department of Radiology, Beijing Jishuitan Hospital, 31 Xinjiekou East Street, Beijing 100035, China (Z.G., K.L., W.L., W.Z., Y.Z., L.X., L.W., X.C.); School of Biomedical Engineering & Imaging Sciences, King's College London, St Thomas' Hospital, London, England (G.M.B.); Mindways Software Inc, Austin, Tex (J.K.B.); and Department of Radiology, University of Wisconsin School of Medicine and Public Health, Madison, Wis (P.J.P.)
| | - Ling Wang
- From the Department of Radiology, Beijing Jishuitan Hospital, 31 Xinjiekou East Street, Beijing 100035, China (Z.G., K.L., W.L., W.Z., Y.Z., L.X., L.W., X.C.); School of Biomedical Engineering & Imaging Sciences, King's College London, St Thomas' Hospital, London, England (G.M.B.); Mindways Software Inc, Austin, Tex (J.K.B.); and Department of Radiology, University of Wisconsin School of Medicine and Public Health, Madison, Wis (P.J.P.)
| | - J Keenan Brown
- From the Department of Radiology, Beijing Jishuitan Hospital, 31 Xinjiekou East Street, Beijing 100035, China (Z.G., K.L., W.L., W.Z., Y.Z., L.X., L.W., X.C.); School of Biomedical Engineering & Imaging Sciences, King's College London, St Thomas' Hospital, London, England (G.M.B.); Mindways Software Inc, Austin, Tex (J.K.B.); and Department of Radiology, University of Wisconsin School of Medicine and Public Health, Madison, Wis (P.J.P.)
| | - Xiaoguang Cheng
- From the Department of Radiology, Beijing Jishuitan Hospital, 31 Xinjiekou East Street, Beijing 100035, China (Z.G., K.L., W.L., W.Z., Y.Z., L.X., L.W., X.C.); School of Biomedical Engineering & Imaging Sciences, King's College London, St Thomas' Hospital, London, England (G.M.B.); Mindways Software Inc, Austin, Tex (J.K.B.); and Department of Radiology, University of Wisconsin School of Medicine and Public Health, Madison, Wis (P.J.P.)
| | - Perry J Pickhardt
- From the Department of Radiology, Beijing Jishuitan Hospital, 31 Xinjiekou East Street, Beijing 100035, China (Z.G., K.L., W.L., W.Z., Y.Z., L.X., L.W., X.C.); School of Biomedical Engineering & Imaging Sciences, King's College London, St Thomas' Hospital, London, England (G.M.B.); Mindways Software Inc, Austin, Tex (J.K.B.); and Department of Radiology, University of Wisconsin School of Medicine and Public Health, Madison, Wis (P.J.P.)
| |
Collapse
|