Utility of osteoporosis screening based on estimation of bone mineral density using bidirectional chest radiographs with deep learning models

IntroductionOsteoporosis increases the risk of fragility fractures, especially of the lumbar spine and femur. As fractures affect life expectancy, it is crucial to detect the early stages of osteoporosis. Dual X-ray absorptiometry (DXA) is the gold standard for bone mineral density (BMD) measurement...

Full description

Saved in:
Bibliographic Details
Main Authors: Akifumi Yoshida, Yoichi Sato, Chiharu Kai, Yuta Hirono, Ikumi Sato, Satoshi Kasai
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-03-01
Series:Frontiers in Medicine
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fmed.2025.1499670/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849393690472087552
author Akifumi Yoshida
Yoichi Sato
Chiharu Kai
Chiharu Kai
Yuta Hirono
Yuta Hirono
Ikumi Sato
Ikumi Sato
Satoshi Kasai
author_facet Akifumi Yoshida
Yoichi Sato
Chiharu Kai
Chiharu Kai
Yuta Hirono
Yuta Hirono
Ikumi Sato
Ikumi Sato
Satoshi Kasai
author_sort Akifumi Yoshida
collection DOAJ
description IntroductionOsteoporosis increases the risk of fragility fractures, especially of the lumbar spine and femur. As fractures affect life expectancy, it is crucial to detect the early stages of osteoporosis. Dual X-ray absorptiometry (DXA) is the gold standard for bone mineral density (BMD) measurement and the diagnosis of osteoporosis; however, its low screening usage is problematic. The accurate estimation of BMD using chest radiographs (CXR) could expand screening opportunities. This study aimed to indicate the clinical utility of osteoporosis screening using deep-learning-based estimation of BMD using bidirectional CXRs.MethodsThis study included 1,624 patients aged ≥ 20 years who underwent DXA and bidirectional (frontal and lateral) chest radiography at a medical facility. A dataset was created using BMD and bidirectional CXR images. Inception-ResNet-V2-based models were trained using three CXR input types (frontal, lateral, and bidirectional). We compared and evaluated the BMD estimation performances of the models with different input information.ResultsIn the comparison of models, the model with bidirectional CXR showed the highest accuracy. The correlation coefficients between the model estimates and DXA measurements were 0.766 and 0.683 for the lumbar spine and femoral BMD, respectively. Osteoporosis detection based on bidirectional CXR showed higher sensitivity and specificity than the models with single-view CXR input, especially for osteoporosis based on T-score ≤ –2.5, with 92.8% sensitivity at 50.0% specificity.DiscussionThese results suggest that bidirectional CXR contributes to improved accuracy of BMD estimation and osteoporosis screening compared with single-view CXR. This study proposes a new approach for early detection of osteoporosis using a deep learning model with frontal and lateral CXR inputs. BMD estimation using bidirectional CXR showed improved detection performance for low bone mass and osteoporosis, and has the potential to be used as a clinical decision criterion. The proposed method shows potential for more appropriate screening decisions, suggesting its usefulness in clinical practice.
format Article
id doaj-art-0b85b73ac3ba4bc1b0a134daf7a118cb
institution Kabale University
issn 2296-858X
language English
publishDate 2025-03-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Medicine
spelling doaj-art-0b85b73ac3ba4bc1b0a134daf7a118cb2025-08-20T03:40:21ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2025-03-011210.3389/fmed.2025.14996701499670Utility of osteoporosis screening based on estimation of bone mineral density using bidirectional chest radiographs with deep learning modelsAkifumi Yoshida0Yoichi Sato1Chiharu Kai2Chiharu Kai3Yuta Hirono4Yuta Hirono5Ikumi Sato6Ikumi Sato7Satoshi Kasai8Department of Radiological Technology, Faculty of Medical Technology, Niigata University of Health and Welfare, Niigata. JapanNagoya University Graduate School of Medicine, Aichi, JapanDepartment of Radiological Technology, Faculty of Medical Technology, Niigata University of Health and Welfare, Niigata. JapanMajor in Health and Welfare, Graduate School of Niigata University of Health and Welfare, Niigata, JapanMajor in Health and Welfare, Graduate School of Niigata University of Health and Welfare, Niigata, JapanTOITU Co., Ltd., Tokyo, JapanMajor in Health and Welfare, Graduate School of Niigata University of Health and Welfare, Niigata, JapanDepartment of Nursing, Faculty of Nursing, Niigata University of Health and Welfare, Niigata, JapanDepartment of Radiological Technology, Faculty of Medical Technology, Niigata University of Health and Welfare, Niigata. JapanIntroductionOsteoporosis increases the risk of fragility fractures, especially of the lumbar spine and femur. As fractures affect life expectancy, it is crucial to detect the early stages of osteoporosis. Dual X-ray absorptiometry (DXA) is the gold standard for bone mineral density (BMD) measurement and the diagnosis of osteoporosis; however, its low screening usage is problematic. The accurate estimation of BMD using chest radiographs (CXR) could expand screening opportunities. This study aimed to indicate the clinical utility of osteoporosis screening using deep-learning-based estimation of BMD using bidirectional CXRs.MethodsThis study included 1,624 patients aged ≥ 20 years who underwent DXA and bidirectional (frontal and lateral) chest radiography at a medical facility. A dataset was created using BMD and bidirectional CXR images. Inception-ResNet-V2-based models were trained using three CXR input types (frontal, lateral, and bidirectional). We compared and evaluated the BMD estimation performances of the models with different input information.ResultsIn the comparison of models, the model with bidirectional CXR showed the highest accuracy. The correlation coefficients between the model estimates and DXA measurements were 0.766 and 0.683 for the lumbar spine and femoral BMD, respectively. Osteoporosis detection based on bidirectional CXR showed higher sensitivity and specificity than the models with single-view CXR input, especially for osteoporosis based on T-score ≤ –2.5, with 92.8% sensitivity at 50.0% specificity.DiscussionThese results suggest that bidirectional CXR contributes to improved accuracy of BMD estimation and osteoporosis screening compared with single-view CXR. This study proposes a new approach for early detection of osteoporosis using a deep learning model with frontal and lateral CXR inputs. BMD estimation using bidirectional CXR showed improved detection performance for low bone mass and osteoporosis, and has the potential to be used as a clinical decision criterion. The proposed method shows potential for more appropriate screening decisions, suggesting its usefulness in clinical practice.https://www.frontiersin.org/articles/10.3389/fmed.2025.1499670/fullbone mineral densityosteoporosisscreeningchest radiographartificial intelligence
spellingShingle Akifumi Yoshida
Yoichi Sato
Chiharu Kai
Chiharu Kai
Yuta Hirono
Yuta Hirono
Ikumi Sato
Ikumi Sato
Satoshi Kasai
Utility of osteoporosis screening based on estimation of bone mineral density using bidirectional chest radiographs with deep learning models
Frontiers in Medicine
bone mineral density
osteoporosis
screening
chest radiograph
artificial intelligence
title Utility of osteoporosis screening based on estimation of bone mineral density using bidirectional chest radiographs with deep learning models
title_full Utility of osteoporosis screening based on estimation of bone mineral density using bidirectional chest radiographs with deep learning models
title_fullStr Utility of osteoporosis screening based on estimation of bone mineral density using bidirectional chest radiographs with deep learning models
title_full_unstemmed Utility of osteoporosis screening based on estimation of bone mineral density using bidirectional chest radiographs with deep learning models
title_short Utility of osteoporosis screening based on estimation of bone mineral density using bidirectional chest radiographs with deep learning models
title_sort utility of osteoporosis screening based on estimation of bone mineral density using bidirectional chest radiographs with deep learning models
topic bone mineral density
osteoporosis
screening
chest radiograph
artificial intelligence
url https://www.frontiersin.org/articles/10.3389/fmed.2025.1499670/full
work_keys_str_mv AT akifumiyoshida utilityofosteoporosisscreeningbasedonestimationofbonemineraldensityusingbidirectionalchestradiographswithdeeplearningmodels
AT yoichisato utilityofosteoporosisscreeningbasedonestimationofbonemineraldensityusingbidirectionalchestradiographswithdeeplearningmodels
AT chiharukai utilityofosteoporosisscreeningbasedonestimationofbonemineraldensityusingbidirectionalchestradiographswithdeeplearningmodels
AT chiharukai utilityofosteoporosisscreeningbasedonestimationofbonemineraldensityusingbidirectionalchestradiographswithdeeplearningmodels
AT yutahirono utilityofosteoporosisscreeningbasedonestimationofbonemineraldensityusingbidirectionalchestradiographswithdeeplearningmodels
AT yutahirono utilityofosteoporosisscreeningbasedonestimationofbonemineraldensityusingbidirectionalchestradiographswithdeeplearningmodels
AT ikumisato utilityofosteoporosisscreeningbasedonestimationofbonemineraldensityusingbidirectionalchestradiographswithdeeplearningmodels
AT ikumisato utilityofosteoporosisscreeningbasedonestimationofbonemineraldensityusingbidirectionalchestradiographswithdeeplearningmodels
AT satoshikasai utilityofosteoporosisscreeningbasedonestimationofbonemineraldensityusingbidirectionalchestradiographswithdeeplearningmodels