法医学杂志 ›› 2025, Vol. 41 ›› Issue (3): 208-216.DOI: 10.12116/j.issn.1004-5619.2025.250106

• 论著 • 上一篇    下一篇

基于分割标签与原始图像融合的双通道汉族青少年肩关节X线骨龄评估

周慧明1,2(), 李丹阳2,3,4, 万雷2, 刘太昂5, 李远喆5, 汪茂文2, 王亚辉2()   

  1. 1.山西医科大学法医学院,山西 晋中 030600
    2.司法鉴定科学研究院 上海市法医学重点实验室 司法部司法鉴定重点实验室 上海市司法鉴定专业技术服务平台,上海 200063
    3.山西医科大学医学科学院,山西 太原 030000
    4.山西医科大学公共卫生学院,山西 太原 030000
    5.上海数之微信息科技有限公司,上海 200444
  • 收稿日期:2025-01-26 发布日期:2025-08-29 出版日期:2025-06-25
  • 通讯作者: 王亚辉
  • 作者简介:周慧明(1998—),女,硕士研究生,主要从事法医临床学、法医人类学研究;E-mail:huimingzhou1216@163.com
  • 基金资助:
    国家重点研发计划资助项目(2022YFC3302004);国家自然科学基金资助项目(81571859);国家自然科学基金资助项目(81102305);上海市2019年度“科技创新行动计划”技术标准项目(19DZ2201300);上海市法医学重点实验室资助项目(21DZ2270800);上海市司法鉴定专业技术服务平台资助项目;司法部司法鉴定重点实验室资助项目

Dual-Channel Shoulder Joint X-ray Bone Age Estimation in Chinese Han Adolescents Based on the Fusion of Segmentation Labels and Original Images

Hui-ming ZHOU1,2(), Dan-yang LI2,3,4, Lei WAN2, Tai-ang LIU5, Yuan-zhe LI5, Mao-wen WANG2, Ya-hui WANG2()   

  1. 1.School of Forensic Medicine, Shanxi Medical University, Jinzhong 030600, Shanxi Province, China
    2.Shanghai Key Laboratory of Forensic Medicine, Key Laboratory of Forensic Science, Ministry of Justice, Shanghai Forensic Service Platform, Academy of Forensic Science, Shanghai 200063, China
    3.Academy of Medical Sciences, Shanxi Medical University, Taiyuan 030000, China
    4.School of Public Health, Shanxi Medical University, Taiyuan 030000, China
    5.Shanghai Shuzhiwei Information Technology Co. , Ltd, Shanghai 200444, China
  • Received:2025-01-26 Online:2025-08-29 Published:2025-06-25
  • Contact: Ya-hui WANG

摘要:

目的 探索适用于中国汉族青少年肩关节X线骨龄评估的深度学习网络模型。 方法 回顾性收集12.0~<18.0岁中国汉族青少年肩关节X线图像1 286例(男性708例,女性578例)。随机抽取约80%的样本(1 032例)作为训练集和验证集,用于模型学习、选择和调优,约20%的样本(254例)作为测试集,用于评估模型泛化能力。分别将肩关节X线原始图像单通道、结合原始图像与分割标签(经人工标注的肩关节区域与原始图像进行逐像素点相乘操作后再经过U-Net++网络分割,仅保留肩关节关键区域信息)双通道输入VGG16、ResNet18、ResNet50、DenseNet121 4种网络模型进行骨龄评估。另外,对测试集数据进行人工骨龄评估,并与4种网络模型进行比较分析。使用平均绝对误差(mean absolute error,MAE)、均方根误差(root mean square error,RMSE)、决定系数(R2)和皮尔逊相关系数(Pearson correlation coefficient,PCC)作为主要评价指标。 结果 在测试集中,4种模型双通道输入的肩关节X线图像骨龄评估结果在4项评价指标上均优于单通道输入,其中DenseNet121模型的双通道输入方式结果最好,MAE为0.54岁,RMSE为0.82岁,R2为0.76,r为0.88。人工评估方法的MAE为0.82岁,仅次于DenseNet121模型的双通道输入结果。 结论 基于肩关节X线图像结合原始图像与分割标签双通道输入的DenseNet121网络模型评估结果优于人工评估结果,可有效评估中国汉族青少年骨龄。

关键词: 法医人类学, 年龄推断, X线图像, 肩关节, 卷积神经网络, 分割网络, 青少年

Abstract:

Objective To explore a deep learning network model suitable for bone age estimation using shoulder joint X-ray images in Chinese Han adolescents. Methods A retrospective collection of 1 286 shoulder joint X-ray images of Chinese Han adolescents aged 12.0 to <18.0 years (708 males and 578 females) was conducted. Using random sampling, approximately 80% of the samples (1 032 cases) were selected as the training and validation sets for model learning, selection and optimization, and the other 20% samples (254 cases) were used as the test set to evaluate the model’s generalization ability. The original single-channel shoulder joint X-ray images and dual-channel inputs combining original images with segmentation labels (manually annotated shoulder joint regions multiplied pixel-by-pixel with original images, followed by segmentation via the U-Net++ network to retain only key shoulder joint region information) were respectively input into four network models, namely VGG16, ResNet18, ResNet50 and DenseNet121 for bone age estimation. Additionally, manual bone age estimation was conducted on the test set data, and the results were compared with the four network models. The mean absolute error (MAE), root mean square error (RMSE), coefficient of determination (R2), and Pearson correlation coefficient (PCC) were used as main evaluation indicators. Results In the test set, the bone age estimation results of the four models with dual-channel input of shoulder joint X-ray images outperformed those with single-channel input in all four evaluation indicators. Among them, DenseNet121 with dual-channel input achieved best results with MAE of 0.54 years, RMSE of 0.82 years, R2 of 0.76, and PCC (r) of 0.88. Manual estimation yielded an MAE of 0.82 years, ranking second only to dual-channel DenseNet121. Conclusion The DenseNet121 model with dual-channel input combined with original images and segmentation labels is superior to manual evaluation results, and can effectively estimate the bone age of Chinese Han adolescents.

Key words: forensic anthropology, age estimation, X-ray image, shoulder joint, convolutional neural network, segmentation network, adolescents

中图分类号: