Jian Qin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Jian Qin has a total of 83 co-authors. Here are the top co-authors by number of shared publications:
Changqin Li
Department of Radiology, The Second Affiliated Hospital of Shandong First Medical University, Tai’an City, China
12 shared publicationsQianqian Yao
Department of Radiology, The Second Affiliated Hospital of Shandong First Medical University, No. 366 Taishan Street, Tai'an 271000, Shandong, China
12 shared publicationsHui Yang
Department of Radiology, The Second Affiliated Hospital of Shandong First Medical University, Taian, China
11 shared publicationsZhe Yang
Department of Radiology, The Second Affiliated Hospital of Shandong First Medical University, Tai’an, Shandong, 271000, People’s Republic of China
7 shared publicationsXiuzhu Zheng
Department of Radiology, The Second Affiliated Hospital of Shandong First Medical University, Tai’an, China
6 shared publicationsZhaojuan Shi
Department of Radiology, The Second Affiliated Hospital of Shandong First Medical University, Tai’an, Shandong, 271000, People’s Republic of China
6 shared publications
Latest Publications
- Open Access
- 1 May 2026
- Published by Taylor & Francis in Clinical Interventions in Aging
- Vol. ume 21, 1-15
Deep Learning-Assisted Radiomics for Predicting Thoracolumbar Osteoporotic Vertebral Fractures
Rationale and Objectives: Osteoporotic vertebral compression fractures (OVFs), particularly at the thoracolumbar spinal junction spanning levels T11 to L2, represent a significant and debilitating global health challenge. The objective of the present research was to establish and verify a robust radiomics model using routine non-contrast computed tomography (CT) to predict thoracolumbar OVFs risk. Materials and Methods: In this retrospective cohort study, 80 patients with new thoracolumbar OVFs were propensity-matched 1:2 with 160 controls. A 3D U-Net automatically segmented T11-L2 cortical and cancellous bone. Following minimum redundancy maximum relevance (mRMR) and least absolute shrinkage and selection operator (LASSO) feature selection, 13 cortical and 16 cancellous radiomics features were extracted. Logistic regression models were developed using corresponding radscores. The best-performing model was compared to volumetric bone mineral density (vBMD) and evaluated via ROC curves, decision curve analysis (DCA), and calibration plots. Results: A total of 240 patients (147 females, 93 males) were enrolled, with no significant age or sex differences between groups. The combined cortical and cancellous radscore model (vertebral model) attained an AUC of 0.825 and 0.840 for OVF prediction, outperforming the vBMD model (AUC: 0.752/0.735). DCA and calibration plots verified its outstanding predictive performance. Notably, integrating vBMD with the vertebral model did not yield a statistically significant improvement (p > 0.05). The selected features highlighted crucial microstructural insights, with cancellous features reflecting trabecular heterogeneity and cortical features indicating mineralization uniformity and integrity. Conclusion: Our findings demonstrate that radiomics derived from routine non-contrast CT, leveraging deep learning for automated bone compartment segmentation, offers a superior and practical tool for Early identification of high-risk individuals for thoracolumbar OVFs. This approach provides valuable, complementary information beyond vBMD, potentially enhancing clinical decision-making and reducing the burden of osteoporosis.
- 1 May 2026
- Published by Taylor & Francis in Clinical Interventions in Aging
- Vol. ume 21, 1-15
Open AccessDeep Learning-Assisted Radiomics for Predicting Thoracolumbar Osteoporotic Vertebral Fractures
Rationale and Objectives: Osteoporotic vertebral compression fractures (OVFs), particularly at the thoracolumbar spinal junction spanning levels T11 to L2, represent a significant and debilitating global health challenge. The objective of the present research was to establish and verify a robust radiomics model using routine non-contrast computed tomography (CT) to predict thoracolumbar OVFs risk. Materials and Methods: In this retrospective cohort study, 80 patients with new thoracolumbar OVFs were propensity-matched 1:2 with 160 controls. A 3D U-Net automatically segmented T11-L2 cortical and cancellous bone. Following minimum redundancy maximum relevance (mRMR) and least absolute shrinkage and selection operator (LASSO) feature selection, 13 cortical and 16 cancellous radiomics features were extracted. Logistic regression models were developed using corresponding radscores. The best-performing model was compared to volumetric bone mineral density (vBMD) and evaluated via ROC curves, decision curve analysis (DCA), and calibration plots. Results: A total of 240 patients (147 females, 93 males) were enrolled, with no significant age or sex differences between groups. The combined cortical and cancellous radscore model (vertebral model) attained an AUC of 0.825 and 0.840 for OVF prediction, outperforming the vBMD model (AUC: 0.752/0.735). DCA and calibration plots verified its outstanding predictive performance. Notably, integrating vBMD with the vertebral model did not yield a statistically significant improvement (p > 0.05). The selected features highlighted crucial microstructural insights, with cancellous features reflecting trabecular heterogeneity and cortical features indicating mineralization uniformity and integrity. Conclusion: Our findings demonstrate that radiomics derived from routine non-contrast CT, leveraging deep learning for automated bone compartment segmentation, offers a superior and practical tool for Early identification of high-risk individuals for thoracolumbar OVFs. This approach provides valuable, complementary information beyond vBMD, potentially enhancing clinical decision-making and reducing the burden of osteoporosis.
- Open Access
- 1 September 2025
- Published by Taylor & Francis in Clinical Interventions in Aging
- Vol. ume 20, 1635-1646
Assessing Lumbar Spine Microstructure in Osteoporosis Using IVIM-DWI and IDEAL-IQ Sequences
Background: Currently, dual-energy X-ray absorptiometry (DEXA) and quantitative CT (QCT) are commonly used in clinical practice to measure bone mineral density (BMD), offering diagnostic value but involving radiation and inability to visualize bone microstructure. This study aims to assess lumbar spine bone microstructure changes in normal, osteopenic, and osteoporotic groups using IVIM-DWI and IDEAL-IQ sequences to provide useful information for clinical practice. Methods: A total of 346 patients (50– 87 years, 232 females, 114 males) underwent spinal DEXA and MRI. Based on the BMD obtained from DEXA, the patients were stratified into: normal (n=79), osteopenia (n=92), and OP (n=175) groups. Then to evaluated the results of IVIM-DWI and IDEAL-IQ and extracted quantitative parameters from regions of interest covering the L1 to L4 vertebrae. Group comparisons used One-way analysis of variance and the Kruskal‒Wallis H-test. Receiver operating characteristic (ROC) and Spearman’s analyses evaluated diagnostic performance and correlations. Results: Significant differences existed in the ADCslow, f, FF and R2* between groups (P< 0.05). BMD was weakly positively correlated with ADCslow, f, and R2* (r=0.494, 0.153, 0.182, 0.029, P< 0.001) but a negative correlation with FF (r=− 0.402, P< 0.001). BMD and the ADCslow and R2* decreased but FF increased with age (P< 0.05 for all), whereas no significant association existed between age and ADCfast or f value (P> 0.05). FF had the highest areas under the curve (AUCs) (0.624, 0.831 and 0.747) and sensitivity (72.2%, 70.9% and 81.5%) in differentiating normal from osteopenia patients, normal from osteoporosis patients, and osteopenia from osteoporosis patients, respectively. ADCslow and f had the highest specificity (88%) in differentiating between normal and osteopenia patients, while ADCslow had the highest specificity (91.4%) in differentiating between normal and osteoporosis patients. Conclusion: Quantitative parameters extracted from IVIM-DWI and IDEAL-IQ have the potential to become good biomarkers for diagnosing OP.
- 1 September 2025
- Published by Taylor & Francis in Clinical Interventions in Aging
- Vol. ume 20, 1635-1646
Open AccessAssessing Lumbar Spine Microstructure in Osteoporosis Using IVIM-DWI and IDEAL-IQ Sequences
Background: Currently, dual-energy X-ray absorptiometry (DEXA) and quantitative CT (QCT) are commonly used in clinical practice to measure bone mineral density (BMD), offering diagnostic value but involving radiation and inability to visualize bone microstructure. This study aims to assess lumbar spine bone microstructure changes in normal, osteopenic, and osteoporotic groups using IVIM-DWI and IDEAL-IQ sequences to provide useful information for clinical practice. Methods: A total of 346 patients (50– 87 years, 232 females, 114 males) underwent spinal DEXA and MRI. Based on the BMD obtained from DEXA, the patients were stratified into: normal (n=79), osteopenia (n=92), and OP (n=175) groups. Then to evaluated the results of IVIM-DWI and IDEAL-IQ and extracted quantitative parameters from regions of interest covering the L1 to L4 vertebrae. Group comparisons used One-way analysis of variance and the Kruskal‒Wallis H-test. Receiver operating characteristic (ROC) and Spearman’s analyses evaluated diagnostic performance and correlations. Results: Significant differences existed in the ADCslow, f, FF and R2* between groups (P< 0.05). BMD was weakly positively correlated with ADCslow, f, and R2* (r=0.494, 0.153, 0.182, 0.029, P< 0.001) but a negative correlation with FF (r=− 0.402, P< 0.001). BMD and the ADCslow and R2* decreased but FF increased with age (P< 0.05 for all), whereas no significant association existed between age and ADCfast or f value (P> 0.05). FF had the highest areas under the curve (AUCs) (0.624, 0.831 and 0.747) and sensitivity (72.2%, 70.9% and 81.5%) in differentiating normal from osteopenia patients, normal from osteoporosis patients, and osteopenia from osteoporosis patients, respectively. ADCslow and f had the highest specificity (88%) in differentiating between normal and osteopenia patients, while ADCslow had the highest specificity (91.4%) in differentiating between normal and osteoporosis patients. Conclusion: Quantitative parameters extracted from IVIM-DWI and IDEAL-IQ have the potential to become good biomarkers for diagnosing OP.
- Open Access
- 22 April 2025
- Published by Springer Nature in BMC Geriatrics
- Vol. 25 (1) , 1-11
Prediction of abnormal bone mass with a pericoronary adipose tissue Attenuation model
The aim is to explore the value of pericoronary adipose tissue (PCAT) attenuation in predicting abnormal bone mass by establishing a prediction model. 361 patients with coronary computed tomography angiography (CCTA) and quantitative computed tomography (QCT) scans were retrospectively recruited. 311 patients from institution 1 from July 2021 to January 2023 were divided into a training cohort (n = 217) and an internal cohort (n = 94). The external cohort comprised 50 patients from institution 2 from January 2023 to August 2023. Clinical variables and PCAT attenuation of the major epicardial vessels were obtained. Univariate and multivariate logistic regression analyses were used to identify factors with statistical significance. Model 1 was constructed based on clinical variables. Model 2 was constructed by combining the clinical variables with the PCAT attenuation. The performances of the models were assessed using receiver operating characteristic curve analysis, calibration curves and decision curve analysis (DCA). Age, gender, coronary artery disease reporting and data system (CAD-RADS), statins and RCAPCAT were found to be significant predictors of abnormal bone mass. The area under the curve (AUC) of Model 2 was superior to that of Model 1 in the training cohort (AUC: 0.959 vs. 0.920), internal (AUC: 0.943 vs. 0.890) and external validation cohorts (AUC: 0.889 vs. 0.812). The calibration curves and DCA indicated that Model 2 had the higher clinical value. The model incorporating clinical factors and RCAPCAT has good performance in predicting bone mass abnormalities.
- 22 April 2025
- Published by Springer Nature in BMC Geriatrics
- Vol. 25 (1) , 1-11
Open AccessPrediction of abnormal bone mass with a pericoronary adipose tissue Attenuation model
The aim is to explore the value of pericoronary adipose tissue (PCAT) attenuation in predicting abnormal bone mass by establishing a prediction model. 361 patients with coronary computed tomography angiography (CCTA) and quantitative computed tomography (QCT) scans were retrospectively recruited. 311 patients from institution 1 from July 2021 to January 2023 were divided into a training cohort (n = 217) and an internal cohort (n = 94). The external cohort comprised 50 patients from institution 2 from January 2023 to August 2023. Clinical variables and PCAT attenuation of the major epicardial vessels were obtained. Univariate and multivariate logistic regression analyses were used to identify factors with statistical significance. Model 1 was constructed based on clinical variables. Model 2 was constructed by combining the clinical variables with the PCAT attenuation. The performances of the models were assessed using receiver operating characteristic curve analysis, calibration curves and decision curve analysis (DCA). Age, gender, coronary artery disease reporting and data system (CAD-RADS), statins and RCAPCAT were found to be significant predictors of abnormal bone mass. The area under the curve (AUC) of Model 2 was superior to that of Model 1 in the training cohort (AUC: 0.959 vs. 0.920), internal (AUC: 0.943 vs. 0.890) and external validation cohorts (AUC: 0.889 vs. 0.812). The calibration curves and DCA indicated that Model 2 had the higher clinical value. The model incorporating clinical factors and RCAPCAT has good performance in predicting bone mass abnormalities.
- Open Access
- 18 September 2024
- Published by Springer Nature in BMC Musculoskeletal Disorders
- Vol. 25 (1) , 1-9
The effects of simvastatin on the bone microstructure and mechanics of ovariectomized mice: a micro-CT and micro-finite element analysis study
Osteoporosis is a major health concern for postmenopausal women, and the effect of simvastatin (Sim) on bone metabolism is controversial. This study aimed to investigate the effect of simvastatin on the bone microstructure and bone mechanical properties in ovariectomized (OVX) mice. 24 female C57BL/6J mice (8-week-old) were randomly allocated into three groups including the OVX + Sim group, the OVX group and the control group. At 8 weeks after operation, the L4 vertebral bones were dissected completely for micro-Computed Tomography (micro-CT) scanning and micro-finite element analysis (µFEA). The differences between three groups were compared using ANOVA with a LSD correction, and the relationship between bone microstructure and mechanical properties was analyzed using linear regression. Bone volume fraction, trabecular number, connectivity density and trabecular tissue mineral density in the OVX + Sim group were significantly higher than those in the OVX group (P < 0.05). For the mechanical properties detected via µFEA, the OVX + Sim group had lower total deformation, equivalent elastic strain and equivalent stress compared to the OVX group (P < 0.05). In the three groups, the mechanical parameters were significantly correlated with bone volume fraction and trabecular bone mineral density. The findings suggested that simvastatin had a potential role in the treatment of osteoporosis. The results of this study could guide future research on simvastatin and support the development of simvastatin-based treatments to improve bone health.
- 18 September 2024
- Published by Springer Nature in BMC Musculoskeletal Disorders
- Vol. 25 (1) , 1-9
Open AccessThe effects of simvastatin on the bone microstructure and mechanics of ovariectomized mice: a micro-CT and micro-finite element analysis study
Osteoporosis is a major health concern for postmenopausal women, and the effect of simvastatin (Sim) on bone metabolism is controversial. This study aimed to investigate the effect of simvastatin on the bone microstructure and bone mechanical properties in ovariectomized (OVX) mice. 24 female C57BL/6J mice (8-week-old) were randomly allocated into three groups including the OVX + Sim group, the OVX group and the control group. At 8 weeks after operation, the L4 vertebral bones were dissected completely for micro-Computed Tomography (micro-CT) scanning and micro-finite element analysis (µFEA). The differences between three groups were compared using ANOVA with a LSD correction, and the relationship between bone microstructure and mechanical properties was analyzed using linear regression. Bone volume fraction, trabecular number, connectivity density and trabecular tissue mineral density in the OVX + Sim group were significantly higher than those in the OVX group (P < 0.05). For the mechanical properties detected via µFEA, the OVX + Sim group had lower total deformation, equivalent elastic strain and equivalent stress compared to the OVX group (P < 0.05). In the three groups, the mechanical parameters were significantly correlated with bone volume fraction and trabecular bone mineral density. The findings suggested that simvastatin had a potential role in the treatment of osteoporosis. The results of this study could guide future research on simvastatin and support the development of simvastatin-based treatments to improve bone health.
- Open Access
- 24 July 2024
- Published by Springer Nature in BMC Medical Imaging
- Vol. 24 (1) , 1
Correction: IDEAL-IQ combined with intravoxel incoherent motion diffusion-weighted imaging for quantitative diagnosis of osteoporosis
- 24 July 2024
- Published by Springer Nature in BMC Medical Imaging
- Vol. 24 (1) , 1
Open AccessCorrection: IDEAL-IQ combined with intravoxel incoherent motion diffusion-weighted imaging for quantitative diagnosis of osteoporosis
- Open Access
- 20 June 2024
- Published by Springer Nature in BMC Medical Imaging
- Vol. 24 (1) , 1-10
IDEAL-IQ combined with intravoxel incoherent motion diffusion-weighted imaging for quantitative diagnosis of osteoporosis
Background: Osteoporosis (OP) is a common chronic metabolic bone disease characterized by decreased bone mineral content and microstructural damage, leading to increased fracture risk. Traditional methods for measuring bone density have limitations in accurately distinguishing vertebral bodies and are influenced by vertebral degeneration and surrounding tissues. Therefore, novel methods are needed to quantitatively assess changes in bone density and improve the accurate diagnosis of OP. Methods: This study aimed to explore the applicative value of the iterative decomposition of water and fat with echo asymmetry and least-squares estimation-iron (IDEAL-IQ) sequence combined with intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) for the diagnosis of osteoporosis. Data from 135 patients undergoing dual-energy X-ray absorptiometry (DXA), IDEAL-IQ, and IVIM-DWI were prospectively collected and analyzed. Various parameters obtained from IVIM-DWI and IDEAL-IQ sequences were compared, and their diagnostic efficacy was evaluated. Results: Statistically significant differences were observed among the three groups for FF, R2*, f, D, DDC values, and BMD values. FF and f values exhibited negative correlations with BMD values, with r=-0.313 and − 0.274, respectively, while R2*, D, and DDC values showed positive correlations with BMD values, with r = 0.327, 0.532, and 0.390, respectively. Among these parameters, D demonstrated the highest diagnostic efficacy for osteoporosis (AUC = 0.826), followed by FF (AUC = 0.713). D* exhibited the lowest diagnostic performance for distinguishing the osteoporosis group from the other two groups. Only D showed a significant difference between genders. The AUCs for IDEAL-IQ, IVIM-DWI, and their combination were 0.74, 0.89, and 0.90, respectively. Conclusions: IDEAL-IQ combined with IVIM-DWI provides valuable information for the diagnosis of osteoporosis and offers evidence for clinical decisions. The superior diagnostic performance of IVIM-DWI, particularly the D value, suggests its potential as a more sensitive and accurate method for diagnosing osteoporosis compared to IDEAL-IQ. These findings underscore the importance of integrating advanced imaging techniques into clinical practice for improved osteoporosis management and highlight the need for further research to explore the full clinical implications of these imaging modalities.
- 20 June 2024
- Published by Springer Nature in BMC Medical Imaging
- Vol. 24 (1) , 1-10
Open AccessIDEAL-IQ combined with intravoxel incoherent motion diffusion-weighted imaging for quantitative diagnosis of osteoporosis
Background: Osteoporosis (OP) is a common chronic metabolic bone disease characterized by decreased bone mineral content and microstructural damage, leading to increased fracture risk. Traditional methods for measuring bone density have limitations in accurately distinguishing vertebral bodies and are influenced by vertebral degeneration and surrounding tissues. Therefore, novel methods are needed to quantitatively assess changes in bone density and improve the accurate diagnosis of OP. Methods: This study aimed to explore the applicative value of the iterative decomposition of water and fat with echo asymmetry and least-squares estimation-iron (IDEAL-IQ) sequence combined with intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) for the diagnosis of osteoporosis. Data from 135 patients undergoing dual-energy X-ray absorptiometry (DXA), IDEAL-IQ, and IVIM-DWI were prospectively collected and analyzed. Various parameters obtained from IVIM-DWI and IDEAL-IQ sequences were compared, and their diagnostic efficacy was evaluated. Results: Statistically significant differences were observed among the three groups for FF, R2*, f, D, DDC values, and BMD values. FF and f values exhibited negative correlations with BMD values, with r=-0.313 and − 0.274, respectively, while R2*, D, and DDC values showed positive correlations with BMD values, with r = 0.327, 0.532, and 0.390, respectively. Among these parameters, D demonstrated the highest diagnostic efficacy for osteoporosis (AUC = 0.826), followed by FF (AUC = 0.713). D* exhibited the lowest diagnostic performance for distinguishing the osteoporosis group from the other two groups. Only D showed a significant difference between genders. The AUCs for IDEAL-IQ, IVIM-DWI, and their combination were 0.74, 0.89, and 0.90, respectively. Conclusions: IDEAL-IQ combined with IVIM-DWI provides valuable information for the diagnosis of osteoporosis and offers evidence for clinical decisions. The superior diagnostic performance of IVIM-DWI, particularly the D value, suggests its potential as a more sensitive and accurate method for diagnosing osteoporosis compared to IDEAL-IQ. These findings underscore the importance of integrating advanced imaging techniques into clinical practice for improved osteoporosis management and highlight the need for further research to explore the full clinical implications of these imaging modalities.
- Open Access
- 28 May 2024
- Published by Termedia Sp. z.o.o. in Archives of Medical Science
- Vol. 21 (4) , 1289-1298
Prenatal ultrasound reassessment of the corpus callosum based on cortical connectivity information
Introduction: Routine prenatal ultrasound assessment of the corpus callosum (CC) does not reflect information on fibrous connections. The primary purpose was to construct detailed reference ranges of quantitative characteristics of the foetal CC based on cortical connectivity information....
- 28 May 2024
- Published by Termedia Sp. z.o.o. in Archives of Medical Science
- Vol. 21 (4) , 1289-1298
Open AccessPrenatal ultrasound reassessment of the corpus callosum based on cortical connectivity information
Introduction: Routine prenatal ultrasound assessment of the corpus callosum (CC) does not reflect information on fibrous connections. The primary purpose was to construct detailed reference ranges of quantitative characteristics of the foetal CC based on cortical connectivity information....
- Open Access
- 15 November 2023
- Published by Elsevier in Academic Radiology
- Vol. 31 (5) , 2003-2010
Applying Machine Learning Analysis Based on Proximal Femur of Abdominal Computed Tomography to Screen for Abnormal Bone Mass in Femur
- 15 November 2023
- Published by Elsevier in Academic Radiology
- Vol. 31 (5) , 2003-2010
Open AccessApplying Machine Learning Analysis Based on Proximal Femur of Abdominal Computed Tomography to Screen for Abnormal Bone Mass in Femur
- 26 October 2023
- Published by Clinical and Experimental Rheumatology in Clinical and Experimental Rheumatology
- Vol. 42 (7) , 1427-1434
Prediction of the activity of early ankylosing spondylitis using radiomics texture analysis on STIR
Full Papers; Authors: Z. Shi, Z. Yang, D. Su, J. Cheng, Z. Shi, M. Wang, H. Zheng, J. Han, C. Li, J. Qin
- 26 October 2023
- Published by Clinical and Experimental Rheumatology in Clinical and Experimental Rheumatology
- Vol. 42 (7) , 1427-1434
Prediction of the activity of early ankylosing spondylitis using radiomics texture analysis on STIR
Full Papers; Authors: Z. Shi, Z. Yang, D. Su, J. Cheng, Z. Shi, M. Wang, H. Zheng, J. Han, C. Li, J. Qin