journal article·2025-07-04Open access

Assessment of Bone Aging—A Comparison of Different Methods for Evaluating Bone Tissue

Paweł Kamiński, Aleksander Gali, Rafał Obuchowicz, Michał Strzelecki, Adam Piórkowski, Marcin Kociołek, Elżbieta Pociask, Joanna Kwiecień, Karolina Nurzyńska

Applied Sciences· Volume 15· Issue 13

Abstract

This study tackles the challenge of automatically estimating age from pelvis radiographs. Furthermore, we aim to develop a methodology for applying artificial intelligence to classify or regress medical imagery data. Our dataset comprises 684 pelvis X-ray images of patients, each accompanied by annotations and masks for various regions of interest (e.g., the femur shaft). Radiomic features, e.g., the co-occurrence matrix, were computed to characterize the image content. We assessed statistical analysis, machine learning, and deep learning methods for their effectiveness in this task. Correlation analysis indicated that using certain features in specific regions of interest is promising for accurate age estimation. Machine learning models demonstrated that when using uncorrelated features, the optimal mean absolute error (MAE) for age estimation is 5.20, whereas when employing convolutional networks on the texture feature maps yields the best result of 9.56. Automatically selecting radiomic features for machine learning models achieves a MAE of 7.99, whereas utilizing well-known convolutional architectures on the original image results in a system efficacy of 7.96. The use of artificial intelligence in medical data analysis produces comparable outcomes; however, when dealing with a large number of descriptors, selecting the most optimal ones through statistical analysis enables the identification of the best solution quickly.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Bone health and osteoporosis research · Advanced X-ray and CT Imaging · Medical Imaging and Analysis

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Clinic of Locomotor Disorders, Andrzej Frycz Modrzewski Krakow University, Ul. Gustawa Herlinga-Grudzińskiego 1, 30-705 Krakow, Poland

Małopolska Orthopedic and Rehabilitation Hospital, Modrzewiowa 22, 30-224 Krakow, Poland

Independent Researcher, 54-427 Wrocław, Poland

Department of Diagnostic Imaging, Jagiellonian University Medical College, Ul. Kopernika 19, 31-501 Krakow, Poland

Institute of Electronics, Lodz University of Technology, Ul. Żeromskiego 116, 90-924 Lodz, Poland

Department of Biocybernetics and Biomedical Engineering, AGH University of Krakow, Al. Mickiewicza 30, 30-059 Krakow, Poland

Department of Automatic Control and Robotics, AGH University of Krakow, Al. Mickiewicza 30, 30-059 Krakow, Poland

Algorithmics and Software Division, Silesian University of Technology, Akademicka 16, 44-100 Gliwice, Poland

References (44)

Show source-provided references
1. Bone age: Assessment methods and clinical applications10.1297/cpe.24.143 ↗
2. Bone age assessment methods: A critical review
3. Forensic bone age estimation of adolescent pelvis X-rays based on two-stage convolutional neural network10.1007/s00414-021-02746-1 ↗
4. Forensic age estimation for pelvic X-ray images using deep learning10.1007/s00330-018-5791-6 ↗
5. Comparison of Three CNN Models Applied in Bone Age Assessment of Pelvic Radiographs of Adolescents
6. Assessing the bone age of children in an automatic manner newborn to 18 years range10.1007/s10278-019-00209-z ↗
7. Hui, Q., Wang, C., Weng, J., Chen, M., and Kong, D. (2022). A global-local feature fusion convolutional neural network for bone age assessment of hand X-ray images. Appl. Sci., 12.10.3390/app12147218 ↗
8. Mao, X., Hui, Q., Zhu, S., Du, W., Qiu, C., Ouyang, X., and Kong, D. (2023). Automated skeletal bone age assessment with two-stage convolutional transformer network based on X-ray images. Diagnostics, 13.10.3390/diagnostics13111837 ↗
9. Traditional and new methods of bone age assessment-An overview10.4274/jcrpe.galenos.2020.2020.0091 ↗
10. Forensic age estimation in living individuals: Methodological considerations in the context of medico-legal practice
11. Kamiński, P., Obuchowicz, R., Stępień, A., Lasek, J., Pociask, E., and Piórkowski, A. (2023). Correlation of bone textural parameters with age in the context of orthopedic X-ray studies. Appl. Sci., 13.10.3390/app13116618 ↗
12. Kamiński, P., Nurzynska, K., Kwiecień, J., Obuchowicz, R., Piórkowski, A., Pociask, E., Stępień, A., Kociołek, M., Strzelecki, M., and Augustyniak, P. (2024). Sex differentiation of trabecular bone structure based on textural analysis of pelvic radiographs. J. Clin. Med., 13.10.3390/jcm13071904 ↗
13. Forensic age estimation in human skeletal remains: Current concepts and future directions10.1016/j.legalmed.2009.09.001 ↗
14. Osteoporosis and Chronic Kidney Disease-Mineral and Bone Disorder (CKD-MBD): Back to Basics10.1053/j.ajkd.2020.12.024 ↗
15. Hyperparathyroidism10.1016/S0140-6736(17)31430-7 ↗
16. Hip implant selection for total hip arthroplasty in elderly patients10.1097/00003086-200212000-00007 ↗
17. MaZda—The software package for textural analysis of bio-medical images10.1007/978-3-642-04462-5_8 ↗
18. Computational radiomics system to decode the radiographic phenotype10.1158/0008-5472.CAN-17-0339 ↗
19. Application of texture features and machine learning methods to grain segmentation in rock material images
20. Obuchowicz, R., Nurzynska, K., Pierzchala, M., Piorkowski, A., and Strzelecki, M. (2023). Texture analysis for the bone age assessment from MRI images of adolescent wrists in boys. J. Clin. Med., 12.10.3390/jcm12082762 ↗
21. A Statistical Dominance Algorithm for Edge Detection and Segmentation of Medical Images
22. Does image normalization and intensity resolution impact texture classification?10.1016/j.compmedimag.2020.101716 ↗
23. Choraś, M., Choraś, R.S., Kurzyński, M., Trajdos, P., Pejaś, J., and Hyla, T. (2022). The influence of bit-depth reduction on correlation of texture features with a patient’s age. Progress in Image Processing, Pattern Recognition and Communication Systems, Springer International Publishing.10.1007/978-3-030-81523-3 ↗
24. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
25. Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., and Xie, S. (2022, January 18–24). A ConvNet for the 2020s. Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.10.1109/CVPR52688.2022.01167 ↗
26. Xie, S., Girshick, R., Dollár, P., Tu, Z., and He, K. (2017, January 21–26). Aggregated Residual Transformations for Deep Neural Networks. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.634 ↗
27. Tan, M., and Le, Q. (2019, January 9–15). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. Proceedings of the 36th Inter-national Conference on Machine Learning, Long Beach, CA, USA.
28. Tan, M., and Le, Q. (2021, January 18–24). EfficientNetV2: Smaller Models and Faster Training. Proceedings of the 38th International Conference on Machine Learning, Online.
29. Wawrzyniak, A., and Balawender, K. (2024). Structural and Metabolic Changes in Bone. J. Orthop. Surg. Res., 19.
30. Biological basis of bone strength: Anatomy, physiology and measurement
31. Bone age assessment from articular surface and epiphysis using deep neural networks10.3934/mbe.2023585 ↗
32. Attention-guided discriminative region localization and label distribution learning for bone age assessment10.1109/JBHI.2021.3095128 ↗
33. A bone age assessment system for real-world X-ray images based on convolutional neural networks10.1016/j.compeleceng.2019.106529 ↗
34. Dallora, A.L., Anderberg, P., Kvist, O., Mendes, E., Diaz Ruiz, S., and Sanmartin Berglund, J. (2019). Bone age assessment with various machine learning techniques: A systematic literature review and meta-analysis. PLoS ONE, 14.10.1371/journal.pone.0220242 ↗
35. Porter, J.L., and Varacallo, M.A. (2025). Osteoporosis. StatPearls, StatPearls Publishing.
36. Grad-CAM: Visual explanations from deep networks via gradient-based localization10.1007/s11263-019-01228-7 ↗
37. Cementless hip implants: An expanding choice10.5301/hipint.5000423 ↗
38. Revisiting cemented femoral fixation in hip arthroplasty10.2106/JBJS.21.00853 ↗
39. The impact of femoral bone quality on cementless total hip pre-operative templating10.1007/s00264-022-05482-2 ↗
40. The usefulness of trabecular bone score in patients with ankylosing spondylitis10.3904/kjim.2020.065 ↗
41. Comparison of bone mineral density at hip and lumbar spine in patients with femoral neck fractures and pertrochanteric fractures10.5604/01.3001.0014.7567 ↗
42. An overview of the use of the fracture risk assessment tool (FRAX) in osteoporosis10.1007/s40618-023-02219-9 ↗
43. Forensic age estimation in adults by pubic bone mineral density using multidetector computed tomography10.1007/s00414-023-03067-1 ↗
44. Age estimation on post-mortem CT based on pelvic bone mineral density measurement and the state of putrefaction: A multivariate method10.1007/s00414-024-03316-x ↗