Ensemble Deep learning model using panoramic radiographs and clinical variables for osteoporosis disease detection
DOI:
https://doi.org/10.59461/ijdiic.v4i1.158Keywords:
Osteoporosis, Deep Convolutional Neural Network, Deep learning, Machine Learning, Image processingAbstract
Worldwide, a large number of people suffer from the bone disease osteoporosis. Accurate diagnosis and classification are essential for managing and preventing many disorders. In order to classify bone density images into two categories—normal and osteoporotic—this study suggests a hybrid model that combines a multiclass Support Vector Machine (MSVM) with a Deep Convolutional Neural Network (DCNN). The bone density pictures are subjected to feature extraction by the DCNN, and the information is then classified into two categories using the MSVM. The National Health and Nutrition Examination Survey (NHANES) database's dataset of bone density photos was used to train and evaluate the suggested hybrid model. According to the results, the ensemble model performs better than the most advanced methods available today in terms of F1 score, sensitivity, accuracy, and specificity. According to our research, osteoporosis may be efficiently classified by the DCNN and MSVM ensemble model, which can help with the diagnosis and treatment of various bone disorders. The proposed model gives better performance in terms of accuracy of 0.8913 and specificity of 0.9123 when compared to other models. Thus, a deep-learning diagnostic network applied to lumbar spine radiographs could facilitate screening for osteoporosis.
Downloads
References
T. Sozen, L. Ozisik, and N. Calik Basaran, “An overview and management of osteoporosis,” Eur. J. Rheumatol., vol. 4, no. 1, pp. 46–56, Mar. 2017, doi: 10.5152/eurjrheum.2016.048.
T. Suzuki and H. Yoshida, “Low bone mineral density at femoral neck is a predictor of increased mortality in elderly Japanese women,” Osteoporos. Int., vol. 21, no. 1, pp. 71–79, Jan. 2010, doi: 10.1007/s00198-009-0970-6.
K. E. Ensrud et al., “Prevalent Vertebral Deformities Predict Mortality and Hospitalization in Older Women with Low Bone Mass,” J. Am. Geriatr. Soc., vol. 48, no. 3, pp. 241–249, Mar. 2000, doi: 10.1111/j.1532-5415.2000.tb02641.x.
N. D. Nguyen, J. R. Center, J. A. Eisman, and T. V Nguyen, “Bone Loss, Weight Loss, and Weight Fluctuation Predict Mortality Risk in Elderly Men and Women,” J. Bone Miner. Res., vol. 22, no. 8, pp. 1147–1154, Aug. 2007, doi: 10.1359/jbmr.070412.
P. J. Mitchell, “Fracture Liaison Services: the UK experience,” Osteoporos. Int., vol. 22, no. S3, pp. 487–494, Aug. 2011, doi: 10.1007/s00198-011-1702-2.
S. J. Curry et al., “Screening for Osteoporosis to Prevent Fractures,” JAMA, vol. 319, no. 24, p. 2521, Jun. 2018, doi: 10.1001/jama.2018.7498.
D. Mueller and A. Gandjour, “Cost-Effectiveness of Using Clinical Risk Factors with and without DXA for Osteoporosis Screening in Postmenopausal Women,” Value Heal., vol. 12, no. 8, pp. 1106–1117, Nov. 2009, doi: 10.1111/j.1524-4733.2009.00577.x.
M. F. V. Sim, M. Stone, A. Johansen, and W. Evans, “Cost effectiveness analysis of BMD referral for DXA using ultrasound as a selective pre-screen in a group of women with low trauma Colles’ fractures,” Technol. Heal. Care, vol. 8, no. 5, pp. 277–284, Nov. 2000, doi: 10.3233/THC-2000-8503.
C. A. Sedlak, M. O. Doheny, and S. L. Jones, “Osteoporosis Education Programs: Changing Knowledge and Behaviors,” Public Health Nurs., vol. 17, no. 5, pp. 398–402, Sep. 2000, doi: 10.1046/j.1525-1446.2000.00398.x.
M. Sato, J. Vietri, J. A. Flynn, and S. Fujiwara, “Bone fractures and feeling at risk for osteoporosis among women in Japan: patient characteristics and outcomes in the National Health and Wellness Survey,” Arch. Osteoporos., vol. 9, no. 1, p. 199, Dec. 2014, doi: 10.1007/s11657-014-0199-7.
A. Taguchi, “Triage screening for osteoporosis in dental clinics using panoramic radiographs,” Oral Dis., vol. 16, no. 4, pp. 316–327, May 2010, doi: 10.1111/j.1601-0825.2009.01615.x.
D. A. Kumar and M. Anburajan, “The role of hip and chest radiographs in osteoporotic evaluation among south Indian women population: a comparative scenario with DXA,” J. Endocrinol. Invest., vol. 37, no. 5, pp. 429–440, May 2014, doi: 10.1007/s40618-014-0074-9.
H. Chen, X. Zhou, H. Fujita, M. Onozuka, and K.-Y. Kubo, “Age-Related Changes in Trabecular and Cortical Bone Microstructure,” Int. J. Endocrinol., vol. 2013, pp. 1–9, 2013, doi: 10.1155/2013/213234.
S. A. Holcombe, E. Hwang, B. A. Derstine, and S. C. Wang, “Measuring rib cortical bone thickness and cross section from CT,” Med. Image Anal., vol. 49, pp. 27–34, Oct. 2018, doi: 10.1016/j.media.2018.07.003.
K. He, X. Zhang, S. Ren, and J. Sun, “Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification,” in 2015 IEEE International Conference on Computer Vision (ICCV), IEEE, Dec. 2015, pp. 1026–1034. doi: 10.1109/ICCV.2015.123.
J. Smets, E. Shevroja, T. Hügle, W. D. Leslie, and D. Hans, “Machine Learning Solutions for Osteoporosis—A Review,” J. Bone Miner. Res., vol. 36, no. 5, pp. 833–851, Dec. 2020, doi: 10.1002/jbmr.4292.
T. P. Nguyen, D.-S. Chae, S.-J. Park, and J. Yoon, “A novel approach for evaluating bone mineral density of hips based on Sobel gradient-based map of radiographs utilizing convolutional neural network,” Comput. Biol. Med., vol. 132, p. 104298, May 2021, doi: 10.1016/j.compbiomed.2021.104298.
C.-I. Hsieh et al., “Automated bone mineral density prediction and fracture risk assessment using plain radiographs via deep learning,” Nat. Commun., vol. 12, no. 1, p. 5472, Sep. 2021, doi: 10.1038/s41467-021-25779-x.
N. Yamamoto et al., “Deep Learning for Osteoporosis Classification Using Hip Radiographs and Patient Clinical Covariates,” Biomolecules, vol. 10, no. 11, p. 1534, Nov. 2020, doi: 10.3390/biom10111534.
B. Zhang et al., “Deep learning of lumbar spine X-ray for osteopenia and osteoporosis screening: A multicenter retrospective cohort study,” Bone, vol. 140, p. 115561, Nov. 2020, doi: 10.1016/j.bone.2020.115561.
Ohta Y, Yamamoto K, Matsuzawa H, Kobayashi T, “Development of a fast screening method for osteoporosis using chest X-ray images and machine learning,” Can J Biomed Res Tech, vol. 3, no. 5, pp. 1–7, 2020.
M. Jang, M. Kim, S. J. Bae, S. H. Lee, J.-M. Koh, and N. Kim, “Opportunistic Osteoporosis Screening Using Chest Radiographs With Deep Learning: Development and External Validation With a Cohort Dataset,” J. Bone Miner. Res., vol. 37, no. 2, pp. 369–377, Dec. 2020, doi: 10.1002/jbmr.4477.
R. Yamashita, M. Nishio, R. K. G. Do, and K. Togashi, “Convolutional neural networks: an overview and application in radiology,” Insights Imaging, vol. 9, no. 4, pp. 611–629, Aug. 2018, doi: 10.1007/s13244-018-0639-9.
N. Yamamoto et al., “Effect of Patient Clinical Variables in Osteoporosis Classification Using Hip X-rays in Deep Learning Analysis,” Medicina (B. Aires)., vol. 57, no. 8, p. 846, Aug. 2021, doi: 10.3390/medicina57080846.
G. S. Collins, J. B. Reitsma, D. G. Altman, and K. G. M. Moons, “Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD),” Circulation, vol. 131, no. 2, pp. 211–219, Jan. 2015, doi: 10.1161/CIRCULATIONAHA.114.014508.
H. P. Dimai, “Use of dual-energy X-ray absorptiometry (DXA) for diagnosis and fracture risk assessment; WHO-criteria, T- and Z-score, and reference databases,” Bone, vol. 104, pp. 39–43, Nov. 2017, doi: 10.1016/j.bone.2016.12.016.
K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Jun. 2016, pp. 770–778. doi: 10.1109/CVPR.2016.90.
M. M. Mukaka, “Statistics corner: A guide to appropriate use of correlation coefficient in medical research.,” Malawi Med. J., vol. 24, no. 3, pp. 69–71, Sep. 2012.
G. Liu, M. Peacock, O. Eilam, G. Dorulla, E. Braunstein, and C. C. Johnston, “Effect of osteoarthritis in the lumbar spine and hip on bone mineral density and diagnosis of osteoporosis in elderly men and women,” Osteoporos. Int., vol. 7, no. 6, pp. 564–569, Nov. 1997, doi: 10.1007/BF02652563.
E. S. Siris et al., “Bone Mineral Density Thresholds for Pharmacological Intervention to Prevent Fractures,” Arch. Intern. Med., vol. 164, no. 10, p. 1108, May 2004, doi: 10.1001/archinte.164.10.1108.
K. Vasu and S. Choudhary, “Music Information Retrieval Using Similarity Based Relevance Ranking Techniques,” Scalable Comput. Pract. Exp., vol. 23, no. 3, pp. 103–114, Oct. 2022, doi: 10.12694/scpe.v23i3.2005.
V. Karthik and S. Choudhary, “TaCbF-‘Trending Architecture for Content based Filtering using Data Mining,’” in 2017 International Conference on Current Trends in Computer, Electrical, Electronics and Communication (CTCEEC), IEEE, Sep. 2017, pp. 417–420. doi: 10.1109/CTCEEC.2017.8455036.
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 T Ramesh, V Santhi
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
