Volume 21, Issue 4 (3-2025)
JSDP 2025, 21(4): 1-14 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Sarabi H, Abdali Mohammadi F. Diagnosing Children's Developmental Disorders By A Transfer Learning Based Architecture Using Knowledge Distillation. JSDP 2025; 21 (4) : 1
URL: http://jsdp.rcisp.ac.ir/article-1-1399-en.html
URL: http://jsdp.rcisp.ac.ir/article-1-1399-en.html
Razi University
Abstract: (205 Views)
Enhancing medical devices with Internet of Things (IOT) and diagnostic artificial intelligence technology, while considering the constraints of these systems, has the potential to modernize and enhance the diagnostic approach of future generations of Internet of Things systems in healthcare. The radiography device, commonly used in paraclinical settings, is widely used in various hospital departments. The automated assessment of abnormalities and bone age from radiographic images of the left hand assists radiologists, pediatricians, and forensic experts in determining the developmental stage of young individuals. The IoT devices in medicine are unable to process large amounts of data due to limited resources. This article uses a teacher-student network for bone age classification, using the decomposed knowledge distillation model of convolutional neural networks. This approach minimizes the computational resources needed for edge devices. The proposed method is comprised of two sequential steps. In the preprocessing step, the initial phase involves the elimination of non-clinical data and artifacts. This is followed by the extraction of region of interest (ROI). In this phase of the procedure, only the hand portion of the patient's X-ray remains for further evaluation. The subsequent phase involves the delineation of the boundaries of the region of interest. This is necessary because, in certain age groups, some bones are not ossified. Consequently, reliance on bones as landmarks is precluded. In the second step, The extracted ROI from the preceding step is utilized to train the teacher model. The student model utilizes the teacher model's knowledge to learn how to predict patient age. Therefore, the present study puts forth transfer learning methodologies founded on the distillation of knowledge, with the aim of facilitating the transference of knowledge between teacher and student models.
The proposed method is based on the data set of the Digital Hand Atlas (DHA) database. The evaluation criteria used in this work are Accuracy, recall, permission and mean absolute error (MAE). The proposed model achieves 96/47% test accuracy for bone age classification.
The proposed method is based on the data set of the Digital Hand Atlas (DHA) database. The evaluation criteria used in this work are Accuracy, recall, permission and mean absolute error (MAE). The proposed model achieves 96/47% test accuracy for bone age classification.
Article number: 1
Type of Study: Research |
Subject:
Paper
Received: 2023/09/15 | Accepted: 2024/12/4 | Published: 2025/04/2 | ePublished: 2025/04/2
Received: 2023/09/15 | Accepted: 2024/12/4 | Published: 2025/04/2 | ePublished: 2025/04/2
References
1. F. Cavallo, A. Mohn, F. Chiarelli, and C. Giannini, "Evaluation of bone age in children: a mini-review," Frontiers in Pediatrics, vol. 9, p. 580314, 2021. [DOI:10.3389/fped.2021.580314] [PMID] []
2. A. Tekın and K. Cesur Aydın, "Comparative determination of skeletal maturity by hand-wrist radiograph, cephalometric radiograph and cone beam computed tomography," Oral Radiology, vol. 36, pp. 327-336, 2020. [DOI:10.1007/s11282-019-00408-y] [PMID]
3. A. L. Dallora, P. Anderberg, O. Kvist, E. Mendes, S. Diaz Ruiz, and J. Sanmartin Berglund, "Bone age assessment with various machine learning techniques: a systematic literature review and meta-analysis," PloS one, vol. 14, no. 7, p. e0220242, 2019. [DOI:10.1371/journal.pone.0220242] [PMID] []
4. P. Sousa-e-Silva et al., "Skeletal age assessed by TW2 using 20-bone, carpal and RUS score systems: Intra-observer and inter-observer agreement among male pubertal soccer players," Plos one, vol. 17, no. 8, p. e0271386, 2022. [DOI:10.1371/journal.pone.0271386] [PMID] []
5. Y. M. Wang, T. H. Tsai, J. S. Hsu, M. F. Chao, Y. T. Wang, and T. S. Jaw, "Automatic assessment of bone age in Taiwanese children: a comparison of the Greulich and Pyle method and the Tanner and Whitehouse 3 method," The Kaohsiung Journal of Medical Sciences, vol. 36, no. 11, pp. 937-943, 2020. [DOI:10.1002/kjm2.12268] [PMID]
6. T. Widek, P. Genet, T. Ehammer, T. Schwark, M. Urschler, and E. Scheurer, "Bone age estimation with the Greulich-Pyle atlas using 3T MR images of hand and wrist," Forensic Science International, vol. 319, p. 110654, 2021. [DOI:10.1016/j.forsciint.2020.110654] [PMID]
7. D. D. Martin, A. D. Calder, M. B. Ranke, G. Binder, and H. H. Thodberg, "Accuracy and self-validation of automated bone age determination," Scientific Reports, vol. 12, no. 1, p. 6388, 2022. [DOI:10.1038/s41598-022-10292-y] [PMID] []
8. A. Elhakeem, M. Frysz, K. Tilling, J. H. Tobias, and D. A. Lawlor, "Association between age at puberty and bone accrual from 10 to 25 years of age," JAMA network open, vol. 2, no. 8, pp. e198918-e198918, 2019. [DOI:10.1001/jamanetworkopen.2019.8918] [PMID] []
9. H. Sarabi Sarvarani and F. Abdali-Mohammadi, "An Ensemble Convolutional Neural Networks for Detection of Growth Anomalies in Children with X-ray Images," Journal of AI and Data Mining, vol. 10, no. 4, pp. 479-492, 2022.
10. M. Sepahvand, F. Abdali-Mohammadi, and A. Taherkordi, "Teacher-student knowledge distillation based on decomposed deep feature representation for intelligent mobile applications," Expert Systems with Applications, vol. 202, p. 117474, 2022. [DOI:10.1016/j.eswa.2022.117474]
11. M. Sepahvand, F. Abdali-Mohammadi, and A. Taherkordi, "An adaptive teacher-student learning algorithm with decomposed knowledge distillation for on-edge intelligence," Engineering Applications of Artificial Intelligence, vol. 117, p. 105560, 2023. [DOI:10.1016/j.engappai.2022.105560]
12. F. Abdali-Mohammadi, M. Mardanpour, M. Sepahvand, H. Sarabi, "A Bone Age Assessment based on a hybrid Knowledge Distillation Paradigm using single ROI," available online at: https://www.authorea.com/doi/full/10.22541/au.166869703.37960946
13. C. Liu, H. Xie, Y. Liu, Z. Zha, F. Lin, and Y. Zhang, "Extract Bone Parts Without Human Prior: End-to-end Convolutional Neural Network for Pediatric Bone Age Assessment," in Medical Image Computing and Computer Assisted Intervention - MICCAI 2019, Cham, D. Shen et al., Eds., 2019: Springer International Publishing, pp. 667-675. [DOI:10.1007/978-3-030-32226-7_74]
14. S M. S. Hosseini et al., "Atlas of digital pathology: A generalized hierarchical histological tissue type-annotated database for deep learning," 2019, pp. 11747-11756. [DOI:10.1109/CVPR.2019.01202]
15. S. Koitka, M. S. Kim, M. Qu, A. Fischer, C. M. Friedrich, and F. Nensa, "Mimicking the radiologists' workflow: Estimating pediatric hand bone age with stacked deep neural networks," Medical Image Analysis, vol. 64, p. 101743, 2020.08.01. 2020, doi: https:..doi.org.10.1016.j.media.2020.101743. [DOI:10.1016/j.media.2020.101743] [PMID]
16. C. González, M. Escobar, L. Daza, F. Torres, G. Triana, and P. Arbeláez, "SIMBA: Specific Identity Markers for Bone Age Assessment," in Medical Image Computing and Computer Assisted Intervention - MICCAI 2020, Cham, A. L. Martel et al., Eds., 2020.. 2020: Springer International Publishing, pp. 753-763. [DOI:10.1007/978-3-030-59725-2_73]
17. D. Wang, K. Zhang, J. Ding, and L. Wang, "Improve Bone Age Assessment by Learning from Anatomical Local Regions," in Medical Image Computing and Computer Assisted Intervention - MICCAI 2020, Cham, A. L. Martel et al., Eds., 2020.. 2020: Springer International Publishing, pp. 631-640. [DOI:10.1007/978-3-030-59725-2_61]
18. A. Wibisono et al., "Deep learning and classic machine learning approach for automatic bone age assessment," in 2019 4th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS), 2019: IEEE, pp. 235-240. [DOI:10.1109/ACIRS.2019.8935965]
19. V. I. Iglovikov, A. Rakhlin, A. A. Kalinin, and A. A. Shvets, "Paediatric bone age assessment using deep convolutional neural networks," in Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support: 4th International Workshop, DLMIA 2018, and 8th International Workshop, ML-CDS 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 20, 2018, Proceedings 4, 2018: Springer, pp. 300-308. [DOI:10.1007/978-3-030-00889-5_34]
20. S. Deshmukh and A. Khaparde, "Faster region-convolutional neural network oriented feature learning with optimal trained recurrent neural network for bone age assessment for pediatrics," Biomedical Signal Processing and Control, vol. 71, p. 103016, 2022. [DOI:10.1016/j.bspc.2021.103016]
21. I. Salim and A. B. Hamza, "Ridge regression neural network for pediatric bone age assessment," Multimedia Tools and Applications, vol. 80, no. 20, pp. 30461-30478, 2021. [DOI:10.1007/s11042-021-10935-8]
22. S. J. Son et al., "TW3-based fully automated bone age assessment system using deep neural networks," IEEE Access, vol. 7, pp. 33346-33358, 2019. [DOI:10.1109/ACCESS.2019.2903131]
23. Z. Yang, C. Cong, M. Pagnucco, and Y. Song, "Multi-scale multi-reception attention network for bone age assessment in X-ray images," Neural Networks, vol. 158, pp. 249-257, 2023. [DOI:10.1016/j.neunet.2022.11.002] [PMID]
24. C. S. Politzer, J. D. Bomar, H. C. Pehlivan, P. Gurusamy, E. W. Edmonds, and A. T. Pennock, "Creation and validation of a shorthand magnetic resonance imaging bone age assessment tool of the knee as an alternative skeletal maturity assessment," The American Journal of Sports Medicine, vol. 49, no. 11, pp. 2955-2959, 2021. [DOI:10.1177/03635465211032986] [PMID]
25. M. N. Meqdad, H. T. Rauf, and S. Kadry, "Bone Anomaly Detection by Extracting Regions of Interest and Convolutional Neural Networks," Applied System Innovation, vol. 6, no. 1, p. 21, 2023. [Online]. Available: https:..www.mdpi.com.2571-5577.6.1.21. [DOI:10.3390/asi6010021]
26. C. Chen, Z. Chen, X. Jin, L. Li, W. Speier, and C. W. Arnold, "Attention-Guided Discriminative Region Localization and Label Distribution Learning for Bone Age Assessment," (in eng), IEEE J Biomed Health Inform, vol. 26, no. 3, pp. 1208-1218, Mar 2022, doi: 10.1109.jbhi.2021.3095128. [DOI:10.1109/JBHI.2021.3095128] [PMID]
27. C. Spampinato, S. Palazzo, D. Giordano, M. Aldinucci, and R. Leonardi, "Deep learning for automated skeletal bone age assessment in X-ray images," (in eng), Med Image Anal, vol. 36, pp. 41-51, Feb 2017, doi: 10.1016.j.media.2016.10.010. [DOI:10.1016/j.media.2016.10.010] [PMID]
28. M. Kashif, T. M. Deserno, D. Haak, and S. Jonas, "Feature description with SIFT, SURF, BRIEF, BRISK, or FREAK? A general question answered for bone age assessment," Computers in biology and medicine, vol. 68, pp. 67-75, 2016. [DOI:10.1016/j.compbiomed.2015.11.006] [PMID]
29. A K. Alshamrani and A. C. Offiah, "Applicability of two commonly used bone age assessment methods to twenty-first century UK children," European radiology, vol. 30, pp. 504-513, 2020. [DOI:10.1007/s00330-019-06300-x] [PMID] []
30. X. Pan, Y. Zhao, H. Chen, D. Wei, C. Zhao, and Z. Wei, "Fully Automated Bone Age Assessment on Large‐Scale Hand X‐Ray Dataset," International journal of biomedical imaging, vol. 2020, no. 1, p. 8460493, 2020. [DOI:10.1155/2020/8460493] [PMID] []
31. Y. A. Ding, F. Mutz, K. F. Côco, L. A. Pinto, and K. S. Komati, "Bone age estimation from carpal radiography images using deep learning," Expert Systems, vol. 37, no. 6, p. e12584, 2020, doi: https:..doi.org.10.1111.exsy.12584. [DOI:10.1111/exsy.12584]
32. J. Jasper Gnana Chandran, R. Karthick, R. Rajagopal, and P. Meenalochini, "Dual-Channel Capsule Generative Adversarial Network Optimized with Golden Eagle Optimization for Pediatric Bone Age Assessment from Hand X-Ray Image," International Journal of Pattern Recognition and Artificial Intelligence, vol. 37, no. 02, p. 2354001, 2023/02/01 2022, doi: 10.1142/S021800142354001. [DOI:10.1142/S0218001423540010]
33. Z. Li et al., "Bone age assessment based on deep neural networks with annotation-free cascaded critical bone region extraction," Frontiers in Artificial Intelligence, vol. 6, p. 1142895, 2023. [DOI:10.3389/frai.2023.1142895] [PMID] []
34. P. Sousa-e-Silva et al., "Intra-observer reproducibility and inter-observer agreement of Fels skeletal age assessments among male tennis players 8-16 years," BMC Pediatrics, vol. 23, no. 1, p. 196, 2023/04/26 2023, doi: 10.1186/s12887-023-03965-8. [DOI:10.1186/s12887-023-03965-8] [PMID] []
35. A. Hassan Pour Askari, A. Khatibi Bardsiri, M. Mohammadi Ghanat Ghestani, "IoT privacy for the transmission of data in the field of health using blockchain", signal and data processing, vol.21, no. 3, pp. 149-178, 2024 [DOI:10.61186/jsdp.21.3.149]
36. M. khalooei, M. Homayounpour, M. Amirmazlaghani, "A survey on vulnerability of deep neural networks to adversarial examples and defense approaches to deal with them", signal and data processing, vol. 20, no. 2, pp. 113-144, 2023 [DOI:10.61186/jsdp.20.2.113]
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
