 
    Journal of Forensic Medicine ›› 2025, Vol. 41 ›› Issue (3): 208-216.DOI: 10.12116/j.issn.1004-5619.2025.250106
• Original Articles • Previous Articles Next Articles
					
													Hui-ming ZHOU1,2( ), Dan-yang LI2,3,4, Lei WAN2, Tai-ang LIU5, Yuan-zhe LI5, Mao-wen WANG2, Ya-hui WANG2(
), Dan-yang LI2,3,4, Lei WAN2, Tai-ang LIU5, Yuan-zhe LI5, Mao-wen WANG2, Ya-hui WANG2( )
)
												  
						
						
						
					
				
Received:2025-01-26
															
							
															
							
															
							
																	Online:2025-08-29
															
							
																	Published:2025-06-25
															
						Contact:
								Ya-hui WANG   
													CLC Number:
Hui-ming ZHOU, Dan-yang LI, Lei WAN, Tai-ang LIU, Yuan-zhe LI, Mao-wen WANG, Ya-hui WANG. Dual-Channel Shoulder Joint X-ray Bone Age Estimation in Chinese Han Adolescents Based on the Fusion of Segmentation Labels and Original Images[J]. Journal of Forensic Medicine, 2025, 41(3): 208-216.
Add to citation manager EndNote|Ris|BibTeX
URL: http://www.fyxzz.cn/EN/10.12116/j.issn.1004-5619.2025.250106
| 年龄段/岁 | 男性 | 女性 | 合计 | ||
|---|---|---|---|---|---|
| 训练集和验证集 | 测试集 | 训练集和验证集 | 测试集 | ||
| 合计 | 570 | 138 | 462 | 116 | 1 286 | 
| 12.0~<13.0 | 67 | 20 | 59 | 9 | 155 | 
| 13.0~<14.0 | 90 | 14 | 87 | 25 | 216 | 
| 14.0~<15.0 | 75 | 16 | 76 | 19 | 186 | 
| 15.0~<16.0 | 104 | 32 | 93 | 32 | 261 | 
| 16.0~<17.0 | 112 | 34 | 84 | 15 | 245 | 
| 17.0~<18.0 | 122 | 22 | 63 | 16 | 223 | 
Tab. 1 Population distribution of training, validation and test sets in each age group
| 年龄段/岁 | 男性 | 女性 | 合计 | ||
|---|---|---|---|---|---|
| 训练集和验证集 | 测试集 | 训练集和验证集 | 测试集 | ||
| 合计 | 570 | 138 | 462 | 116 | 1 286 | 
| 12.0~<13.0 | 67 | 20 | 59 | 9 | 155 | 
| 13.0~<14.0 | 90 | 14 | 87 | 25 | 216 | 
| 14.0~<15.0 | 75 | 16 | 76 | 19 | 186 | 
| 15.0~<16.0 | 104 | 32 | 93 | 32 | 261 | 
| 16.0~<17.0 | 112 | 34 | 84 | 15 | 245 | 
| 17.0~<18.0 | 122 | 22 | 63 | 16 | 223 | 
| 评价指标 | VGG16 | ResNet18 | ResNet50 | DenseNet121 | 人工评估 | ||||
|---|---|---|---|---|---|---|---|---|---|
| 单通道 | 双通道 | 单通道 | 双通道 | 单通道 | 双通道 | 单通道 | 双通道 | ||
| MAE/岁 | 1.20 | 1.17 | 1.251) | 1.091)2) | 1.211) | 0.851)2) | 1.161) | 0.541)2) | 0.82 | 
| RMSE/岁 | 1.47 | 1.45 | 1.521) | 1.371)2) | 1.481) | 1.061)2) | 1.431) | 0.821)2) | 1.13 | 
| R2 | 0.24 | 0.26 | 0.251) | 0.341)2) | 0.281) | 0.601)2) | 0.301) | 0.761)2) | 0.68 | 
| r | 0.51 | 0.51 | 0.541) | 0.591)2) | 0.471) | 0.801)2) | 0.561) | 0.881)2) | 0.82 | 
Tab. 2 Comparison of prediction results from four network models based on single-channel anddual-channel inputs, and manual evaluation results in the test set
| 评价指标 | VGG16 | ResNet18 | ResNet50 | DenseNet121 | 人工评估 | ||||
|---|---|---|---|---|---|---|---|---|---|
| 单通道 | 双通道 | 单通道 | 双通道 | 单通道 | 双通道 | 单通道 | 双通道 | ||
| MAE/岁 | 1.20 | 1.17 | 1.251) | 1.091)2) | 1.211) | 0.851)2) | 1.161) | 0.541)2) | 0.82 | 
| RMSE/岁 | 1.47 | 1.45 | 1.521) | 1.371)2) | 1.481) | 1.061)2) | 1.431) | 0.821)2) | 1.13 | 
| R2 | 0.24 | 0.26 | 0.251) | 0.341)2) | 0.281) | 0.601)2) | 0.301) | 0.761)2) | 0.68 | 
| r | 0.51 | 0.51 | 0.541) | 0.591)2) | 0.471) | 0.801)2) | 0.561) | 0.881)2) | 0.82 | 
| [1] | 王亚辉,陈腾. 法医学活体年龄推断研究前沿与挑战[J].法医学杂志,2024,40(2):109-111. doi:10.12116/j.issn.1004-5619.2024.240410 . | 
| WANG Y H, CHEN T. Research frontiers and challenges of living age estimation in forensic science[J]. Fayixue Zazhi,2024,40(2):109-111. | |
| [2] | GRÄFE D, BESKOW A B, PFÄFFLE R, et al. Automated bone age assessment in a German pediatric cohort: Agreement between an artificial intelligence software and the manual Greulich and Pyle method[J]. Eur Radiol,2024,34(7):4407-4413. doi: 10.1007/s00330-023-10543-0 . | 
| [3] | MALINA R M, BEUNEN G P. Assessment of skeletal maturity and prediction of adult height (TW3 method)[J]. Am J Hum Biol,2002,14(6):788-789. doi:10.1002/ajhb.10098 . | 
| [4] | ZHANG D, LIU B, HUANG Y, et al. An automated TW3-RUS bone age assessment method with ordinal regression-based determination of skeletal maturity[J]. J Digit Imaging,2023,36(3):1001-1015. doi:10.1007/s10278-023-00794-0 . | 
| [5] | ŠTERN D, PAYER C, URSCHLER M. Automated age estimation from MRI volumes of the hand[J]. Med Image Anal,2019,58:101538. doi:10.1016/j.media.2019.101538 . | 
| [6] | ALTINSOY H B, GURSES M S, BOGAN M, et al. Applicability of 3.0 T MRI images in the estimation of full age based on shoulder joint ossification: Single-centre study[J]. Leg Med (Tokyo),2020,47:101767. doi:10.1016/j.legalmed.2020.101767 . | 
| [7] | KELLINGHAUS M, SCHULZ R, VIETH V, et al. Enhanced possibilities to make statements on the ossification status of the medial clavicular epiphysis using an amplified staging scheme in evaluating thin-slice CT scans[J]. Int J Legal Med,2010,124(4):321-325. doi:10.1007/s00414-010-0448-2 . | 
| [8] | SCHMELING A, SCHULZ R, REISINGER W, et al. Studies on the time frame for ossification of the medial clavicular epiphyseal cartilage in conventional radiography[J]. Int J Legal Med,2004,118(1):5-8. doi:10.1007/s00414-003-0404-5 . | 
| [9] | LU T, QIU L R, REN B, et al. Forensic age estimation based on magnetic resonance imaging of the proximal humeral epiphysis in Chinese living individuals[J]. Int J Legal Med,2021,135(6):2437-2446. doi:10.1007/s00414-021-02653-5 . | 
| [10] | 朱广友,王亚辉,万雷. 中国青少年骨龄鉴定标准图谱法[M].上海:上海科学技术文献出版社,2016:96-107. | 
| ZHU G Y, WANG Y H, WAN L. Determination of skeleton age for Chinese teenagers by standard radiographic atlas[M]. Shanghai: Shanghai Scientific and Technological Literature Press,2016:96-107. | |
| [11] | FURDOCK R J, KUO A, CHEN K J, et al. Applicability of shoulder, olecranon, and wrist-based skeletal maturity estimation systems to the modern pediatric population[J]. J Pediatr Orthop,2023,43(7):465-469. doi:10.1097/BPO.0000000000002430 . | 
| [12] | NELSON S, HANS M G, BROADBENT BH JR, et al. The Brush Inquiry: An opportunity to investigate health outcomes in a well-characterized cohort[J]. Am J Hum Biol,2000,12(1):1-9. doi:10.1002/(SICI ) | 
| 1520-6300(200001/02)12:1<1::AID-AJHB1>3.0.CO;2-3. | |
| [13] | SHARIF A F, EID H, GHALAB M A A, et al. Evaluation of two scoring systems assessing the epiphyseal union at shoulder joint as predictors of chronological age among a sample of Egyptians[J]. Leg Med (Tokyo),2024,71:102546. doi:10.1016/j.legalmed.2024.102546 . | 
| [14] | TOURNOIS L, TROUSSET V, HATSCH D, et al. Artificial intelligence in the practice of forensic medicine: A scoping review[J]. Int J Legal Med,2024,138(3):1023-1037. doi:10.1007/s00414-023-03140-9 . | 
| [15] | 李丹阳,潘宇,周慧明,等. 医学统计和机器学习方法在活体年龄推断中的应用[J].法医学杂志,2024,40(2):118-127. doi:10.12116/j.issn.1004-5619.2023.231103 . | 
| LI D Y, PAN Y, ZHOU H M, et al. Application of medical statistical and machine learning methods in the age estimation of living individuals[J]. Fayixue Zazhi,2024,40(2):118-127. | |
| [16] | BEHESHTIAN E, PUTMAN K, SANTOMARTINO S M, et al. Generalizability and bias in a deep learning pediatric bone age prediction model using hand radiographs[J]. Radiology,2023,306(2):e220505. doi:10.1148/radiol.220505 . | 
| [17] | YANG Z, CONG C, PAGNUCCO M, et al. Multi-scale multi-reception attention network for bone age assessment in X-ray images[J]. Neural Netw,2023,158:249-257. doi:10.1016/j.neunet.2022.11.002 . | 
| [18] | FAN F, LIU H, DAI X, et al. Automated bone age assessment from knee joint by integrating deep learning and MRI-based radiomics[J]. Int J Legal Med,2024,138(3):927-938. doi:10.1007/s00414-023-03148-1 . | 
| [19] | ZHOU H M, ZHOU Z L, HE Y H, et al. Forensic bone age assessment of hand and wrist joint MRI images in Chinese Han male adolescents based on deep convolutional neural networks[J]. Int J Leg Med,2024,138(6):2427-2440. doi:10.1007/s00414-024-03282-4 . | 
| [20] | KOITKA S, KIM M S, QU M, et al. Mimicking the radiologists’ workflow: Estimating pediatric hand bone age with stacked deep neural networks[J]. Med Image Anal,2020,64:101743. doi:10.1016/j.media.2020.101743 . | 
| [21] | 中国学生体质与健康研究组. 2005年中国学生体质与健康调研报告[M].北京:高等教育出版社,2007:228-232. | 
| National Student Physical Fitness and Health Research Group. Report on the physical fitness and health surveillance of Chinese school students in 2005[M]. Beijing: Higher Education Press,2007:228- 232. | |
| [22] | ZHOU Z, RAHMAN SIDDIQUEE M M, TAJBAKHSH N, et al. UNet++: A nested U-Net architecture for medical image segmentation[J/OL]. arXiv:1807.10165. (2018-07-18)[2025-04-21]. . | 
| [23] | GEUBBELMANS M, ROUSSEAU A J, BURZY-KOWSKI T, et al. Artificial neural networks and deep learning[J]. Am J Orthod Dentofacial Orthop,2024,165(2):248-251. doi:10.1016/j.ajodo.2023.11.003 . | 
| [24] | 周慧明,李丹阳,万雷,等. 人工智能技术在法医学骨龄和牙龄评估中的研究前沿及展望[J].中国司法鉴定,2023(5):31-38. doi:10.3969/j.issn.1671-2072.2023.05.004 . | 
| ZHOU H M, LI D Y, WAN L, et al. Research frontiers and prospects of artificial intelligence technology in forensic bone age and dental age assessment[J]. Zhongguo Sifa Jianding,2023(5):31-38. | |
| [25] | HUANG G, LIU Z, VAN DER MAATEN L, et al. Densely connected convolutional networks[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, HI, USA, 2017:2261-2269. doi:10.1109/CVPR.2017.243 . | 
| [26] | PAN I, BAIRD G L, MUTASA S, et al. Rethinking Greulich and Pyle: A deep learning approach to pediatric bone age assessment using pediatric trauma hand radiographs[J]. Radiol Artif Intell,2020,2(4):e190198. doi:10.1148/ryai.2020190198 . | 
| [27] | LU T, DIAO Y R, TANG X E, et al. Deep learning enables automatic adult age estimation based on CT reconstruction images of the costal cartilage[J]. Eur Radiol,2023,33(11):7519-7529. doi:10.1007/s00330-023-09761-3 . | 
| [28] | DALLORA A L, BERGLUND J S, BROGREN M, et al. Age assessment of youth and young adults using magnetic resonance imaging of the knee: A deep learning approach[J]. JMIR Med Inform,2019,7(4):e16291. doi:10.2196/16291 . | 
| [29] | 中华人民共和国公安部. 法庭科学 汉族青少年骨龄鉴定技术规程: [S].北京:中国标准出版社,2019. | 
| Ministry of Public Security of the People’s Republic of China. Forensic sciences — Technical specifications for skeletal age evaluation of Han population teenagers: [S]. Beijing: Standards Press of China,2019. | |
| [30] | WANG Y H, ZHOU H M, WAN L, et al. An X-ray bone age assessment method for hands and wrists of adolescents in Western China based on feature fusion deep learning models[J]. Int J Leg Med,2025. doi:10.1007/s00414-025-03497-z . | 
| [31] | PAN S J, YANG Q. A survey on transfer learning[J]. IEEE Trans Knowl Data Eng,2010,22(10):1345-1359. doi:10.1109/TKDE.2009.191 . | 
| [32] | CHOI G, HAM S, JE B K, et al. Olecranon bone age assessment in puberty using a lateral elbow radiograph and a deep-learning model[J]. Eur Radiol,2024,34(10):6396-6406. doi:10.1007/s00330-024-10748-x . | 
| [33] | AVUÇLU E, BAŞÇIFTÇI F. Novel approaches to determine age and gender from dental X-ray images by using multiplayer perceptron neural networks and image processing techniques[J]. Chaos Soliton Fract,2019,120:127-138. doi:10.1016/j.chaos.2019.01.023 . | 
| [34] | 李丹阳,周慧明,万雷,等. 基于多种深度卷积神经网络模型的汉族青少年儿童肘关节X线骨龄推断[J].法医学杂志,2025,41(1):48-58. doi:10.12116/j.issn.1004-5619.2024.241202 . | 
| LI D Y, ZHOU H M, WAN L, et al. Bone age estimation of Chinese Han adolescents’ and children’s elbow joint X-rays based on multiple deep convolutional neural network models[J]. Fayixue Zazhi,2025,41(1):48-58. | |
| [35] | VILA-BLANCO N, VARAS-QUINTANA P, TOMÁS I, et al. A systematic overview of dental methods for age assessment in living individuals: From traditional to artificial intelligence-based approaches[J]. Int J Legal Med,2023,137(4):1117-1146. doi:10.1007/s00414-023-02960-z . | 
| [36] | QIU L, LIU A, DAI X, et al. Machine learning and deep learning enabled age estimation on medial clavicle CT images[J]. Int J Legal Med,2024,138(2):487-498. doi:10.1007/s00414-023-03115-w . | 
| [37] | OZDEMIR C, GEDIK M A, KAYA Y. Age estimation from left-hand radiographs with deep learning methods[J]. Trait Signal,2021,38(6):1565-1574. doi:10.18280/ts.380601 . | 
| [38] | KASANI A A, SAJEDI H. Hand bone age estimation using divide and conquer strategy and lightweight convolutional neural networks[J]. Eng Appl Artif Intell,2023,120:105935. doi:10.1016/j.engap pai.2023.105935 . | 
| [39] | PENG L Q, GUO Y C, WAN L, et al. Forensic bone age estimation of adolescent pelvis X-rays based on two-stage convolutional neural network[J]. Int J Legal Med,2022,136(3):797-810. doi:10. 1007/s00414-021-02746-1 . | 
| [40] | LI Y, NIU C, WANG J, et al. A fully automated sex estimation for proximal femur X-ray images through deep learning detection and classification[J]. Leg Med (Tokyo),2022,57:102056. doi:10.1016/j.legal med.2022.102056 . | 
| [41] | LI Y, HUANG Z, DONG X, et al. Forensic age estimation for pelvic X-ray images using deep learning[J]. Eur Radiol,2019,29(5):2322-2329. doi:10.1007/s00330-018-5791-6 . | 
| [42] | DENG X D, LU T, LIU G F, et al. Forensic age prediction and age classification for critical age thresholds via 3.0T magnetic resonance imaging of the knee in the Chinese Han population[J]. Int J Legal Med,2022,136(3):841-852. doi:10.1007/s00414-022-02797-y . | 
| [43] | WAN L, HAO H, WANG Y, et al. The feasibility of age estimation based on MRI and radiographs of the knee joint in the Chinese population of Han nationality[J]. Aust J Forensic Sci,2024,56(3):242-252. doi:10.1080/00450618.2022.2143562 . | 
| [44] | MAUER M A, WELL E J, HERRMANN J, et al. Automated age estimation of young individuals based on 3D knee MRI using deep learning[J]. Int J Legal Med,2021,135(2):649-663. doi:10.1007/s00414-020-02465-z . | 
| [45] | CEKDEMIR Y E, MUTLU U, KARAMAN G, et al. Evaluation of the ossification stage of proximal humeral epiphysis by 1.5-T magnetic resonance imaging for determination of skeletal age[J]. Am J Forensic Med Pathol,2021,42(1):36-41. doi:10.1097/ paf.0000000000000636 . | 
| [46] | JIAO Y S, TUERHONG Y, CHEN C X, et al. Bone age assessment based on different MRI modalities of the proximal humerus epiphysis: The comparisons of T1WI, T2WI, and PDWI[J]. Int J Legal Med,2024,138(4):1509-1521. doi:10.1007/s00414-024-03182-7 . | 
| [1] | Dan-yang LI, Hui-ming ZHOU, Lei WAN, Tai-ang LIU, Yuan-zhe LI, Mao-wen WANG, Ya-hui WANG. Bone Age Estimation of Chinese Han Adolescents’s and Children’s Elbow Joint X-rays Based on Multiple Deep Convolutional Neural Network Models [J]. Journal of Forensic Medicine, 2025, 41(1): 48-58. | 
| [2] | Yan-jie DING, Xiao ZHANG, Wen-li SHI, Zi-yi LI, Wei WANG, Shi-lin ZHANG, Gen-jie YANG, A-ji GUO, Bo JIN. Estimate the Age of Han Adult Based on the Pulp Chamber Volume and Pulp Dentinal Index of Right First Molars Using Oral and Maxillofacial CBCT [J]. Journal of Forensic Medicine, 2025, 41(1): 59-65. | 
| [3] | Zhi-lu ZHOU, Dong-fei ZHANG, Jie-min CHEN, Ya-hui WANG, Hong-xia HAO, Tai-ang LIU, Yu-heng HE, Ding-nian LONG, Rui-jue LIU, Lei WAN. MRI Application in Quantification of Epiphyseal Development in the Wrist and Bone Age Estimation of Han Male Adolescents in East China [J]. Journal of Forensic Medicine, 2024, 40(6): 589-596. | 
| [4] | Jia-xuan HAN, Shi-hui SHEN, Yi-wen WU, Xiao-dan SUN, Tian-nan CHEN, Jiang TAO. Adolescents and Children Age Estimation Using Machine Learning Based on Pulp and Tooth Volumes on CBCT Images [J]. Journal of Forensic Medicine, 2024, 40(2): 143-148. | 
| [5] | Lei SHI, Ye XUE, Li-rong QIU, Ting LU, Fei FAN, Yu-chi ZHOU, Zhen-hua DENG. Research Progress on Dental Age Estimation Based on MRI Technology [J]. Journal of Forensic Medicine, 2024, 40(2): 112-117. | 
| [6] | Xuan WEI, Yu-shan CHEN, Jie DING, Chang-xing SONG, Jun-jing WANG, Zhao PENG, Zhen-hua DENG, Xu YI, Fei FAN. Age Estimation by Machine Learning and CT-Multiplanar Reformation of Cranial Sutures in Northern Chinese Han Adults [J]. Journal of Forensic Medicine, 2024, 40(2): 128-134. | 
| [7] | Yu-xin GUO, Wen-qing BU, Yu TANG, Di WU, Hui YANG, Hao-tian MENG, Yu-cheng GUO. Dental Age Estimation in Northern Chinese Han Children and Adolescents Using Demirjian’s Method Combined with Machine Learning Algorithms [J]. Journal of Forensic Medicine, 2024, 40(2): 135-142. | 
| [8] | Dan-yang LI, Yu PAN, Hui-ming ZHOU, Lei WAN, Cheng-tao LI, Mao-wen WANG, Ya-hui WANG. Application of Medical Statistical and Machine Learning Methods in the Age Estimation of Living Individuals [J]. Journal of Forensic Medicine, 2024, 40(2): 118-127. | 
| [9] | Huai-han ZHANG, Yong-jie CAO, Ji ZHANG, Jian XIONG, Ji-wei MA, Xiao-tong YANG, Ping HUANG, Yong-gang MA. Adults Ischium Age Estimation Based on Deep Learning and 3D CT Reconstruction [J]. Journal of Forensic Medicine, 2024, 40(2): 154-163. | 
| [10] | De-min HUO, Kai-jun MA, Jing-lan XU, Xu SONG, Xiao-yan MAO, Xia LIU, Kai-fang ZHAO, Jian ZHANG, Meng DU. Determining Whether an Individual is 18 Years or Older Based on the Third Molar Root Pulp Visibility in East China [J]. Journal of Forensic Medicine, 2024, 40(2): 149-153. | 
| [11] | Yi-hang HUANG, Wei-bo LIANG, Hui JIAN, Sheng-qiu QU. Modeling Methods and Influencing Factors for Age Estimation Based on DNA Methylation [J]. Journal of Forensic Medicine, 2023, 39(6): 601-607. | 
| [12] | Xing-yu MA, Hao CHENG, Zhong-duo ZHANG, Ye-ming LI, Dong ZHAO. Research Progress of Metabolomics Techniques Combined with Machine Learning Algorithm in Wound Age Estimation [J]. Journal of Forensic Medicine, 2023, 39(6): 596-600. | 
| [13] | Zi-wei WANG, Cheng-tao LI, Xi-ling LIU. Cross-Platform Application of DNA Methylation Age Estimation Model in Eastern Chinese Han Population [J]. Journal of Forensic Medicine, 2023, 39(5): 441-446. | 
| [14] | Yong-gang MA, Yong-jie CAO, Yi-hua ZHAO, Xin-jun ZHOU, Bin HUANG, Gao-chao ZHANG, Ping HUANG, Ya-hui WANG, Kai-jun MA, Feng CHEN, Dong-chuan ZHANG, Ji ZHANG. Sex Estimation of Medial Aspect of the Ischiopubic Ramus in Adults Based on Deep Learning [J]. Journal of Forensic Medicine, 2023, 39(2): 129-136. | 
| [15] | Hong-xia HAO, Ya-hui WANG, Zhi-lu ZHOU, Tai-ang LIU, Jin CHEN, Yu-heng HE, Lei WAN, Wen-tao XIA. Research Progress of Age Estimation in the Living by Knee Joint MRI [J]. Journal of Forensic Medicine, 2023, 39(1): 66-71. | 
| Viewed | ||||||
| Full text |  | |||||
| Abstract |  | |||||