Validation of Opportunistic Artificial Intelligence-Based Bone Mineral Density Measurements in Coronary Artery Calcium Scans.

Artificial intelligence bone mineral density deep learning osteoporosis quantitative computed tomography

Journal

Journal of the American College of Radiology : JACR
ISSN: 1558-349X
Titre abrégé: J Am Coll Radiol
Pays: United States
ID NLM: 101190326

Informations de publication

Date de publication:
Apr 2024
Historique:
received: 10 12 2022
revised: 17 05 2023
accepted: 25 05 2023
pubmed: 20 6 2023
medline: 20 6 2023
entrez: 19 6 2023
Statut: ppublish

Résumé

Previously we reported a manual method of measuring thoracic vertebral bone mineral density (BMD) using quantitative CT in noncontrast cardiac CT scans used for coronary artery calcium (CAC) scoring. In this report, we present validation studies of an artificial intelligence-based automated BMD measurement (AutoBMD) that recently received FDA approval as an opportunistic add-on to CAC scans. A deep learning model was trained to detect vertebral bodies. Subsequently, signal processing techniques were developed to detect intervertebral discs and the trabecular components of the vertebral body. The model was trained using 132 CAC scans comprising 7,649 slices. To validate AutoBMD, we used 5,785 cases of manual BMD measurements previously reported from CAC scans in the Multi-Ethnic Study of Atherosclerosis. Mean ± SD for AutoBMD and manual BMD were 166.1 ± 47.9 mg/cc and 163.1 ± 46 mg/cc, respectively (P = .006). Multi-Ethnic Study of Atherosclerosis cases were 47.5% male and 52.5% female, with age 62.2 ± 10.3. A strong correlation was found between AutoBMD and manual measurements (R = 0.85, P < .0001). Accuracy, sensitivity, specificity, positive predictive value and negative predictive value for AutoBMD-based detection of osteoporosis were 99.6%, 96.7%, 97.7%, 99.7% and 99.8%, respectively. AutoBMD averaged 15 seconds per report versus 5.5 min for manual measurements (P < .0001). AutoBMD is an FDA-approved, artificial intelligence-enabled opportunistic tool that reports BMD with Z-scores and T-scores and accurately detects osteoporosis and osteopenia in CAC scans, demonstrating results comparable to manual measurements. No extra cost of scanning and no extra radiation to patients, plus the high prevalence of asymptomatic osteoporosis, make AutoBMD a promising candidate to enhance patient care.

Sections du résumé

BACKGROUND BACKGROUND
Previously we reported a manual method of measuring thoracic vertebral bone mineral density (BMD) using quantitative CT in noncontrast cardiac CT scans used for coronary artery calcium (CAC) scoring. In this report, we present validation studies of an artificial intelligence-based automated BMD measurement (AutoBMD) that recently received FDA approval as an opportunistic add-on to CAC scans.
METHODS METHODS
A deep learning model was trained to detect vertebral bodies. Subsequently, signal processing techniques were developed to detect intervertebral discs and the trabecular components of the vertebral body. The model was trained using 132 CAC scans comprising 7,649 slices. To validate AutoBMD, we used 5,785 cases of manual BMD measurements previously reported from CAC scans in the Multi-Ethnic Study of Atherosclerosis.
RESULTS RESULTS
Mean ± SD for AutoBMD and manual BMD were 166.1 ± 47.9 mg/cc and 163.1 ± 46 mg/cc, respectively (P = .006). Multi-Ethnic Study of Atherosclerosis cases were 47.5% male and 52.5% female, with age 62.2 ± 10.3. A strong correlation was found between AutoBMD and manual measurements (R = 0.85, P < .0001). Accuracy, sensitivity, specificity, positive predictive value and negative predictive value for AutoBMD-based detection of osteoporosis were 99.6%, 96.7%, 97.7%, 99.7% and 99.8%, respectively. AutoBMD averaged 15 seconds per report versus 5.5 min for manual measurements (P < .0001).
CONCLUSIONS CONCLUSIONS
AutoBMD is an FDA-approved, artificial intelligence-enabled opportunistic tool that reports BMD with Z-scores and T-scores and accurately detects osteoporosis and osteopenia in CAC scans, demonstrating results comparable to manual measurements. No extra cost of scanning and no extra radiation to patients, plus the high prevalence of asymptomatic osteoporosis, make AutoBMD a promising candidate to enhance patient care.

Identifiants

pubmed: 37336431
pii: S1546-1440(23)00405-2
doi: 10.1016/j.jacr.2023.05.006
pii:
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

624-632

Informations de copyright

Copyright © 2023. Published by Elsevier Inc.

Auteurs

Morteza Naghavi (M)

American Heart Technologies, Torrance, California. Electronic address: mn@vp.org.

Kyle Atlas (K)

American Heart Technologies, Torrance, California.

Amirhossein Jaberzadeh (A)

American Heart Technologies, Torrance, California.

Chenyu Zhang (C)

American Heart Technologies, Torrance, California.

Venkat Manubolu (V)

The Lundquist Institute, Torrance, California.

Dong Li (D)

The Lundquist Institute, Torrance, California.

Matthew Budoff (M)

The Lundquist Institute, Torrance, California.

Classifications MeSH