1.无锡市中医医院,江苏省无锡市中南西路8号,214071
2.南京邮电大学
3.苏州市中医医院
4.常州市中医院
wangjianwei_1963@163.com
收稿:2025-11-27,
修回:2026-04-29,
录用:2026-04-08,
纸质出版:2026-05-17
移动端阅览
戴国达,王建伟,吴毛等.基于深度学习的桡骨远端骨折掌倾角与尺偏角自动测量模型构建及临床验证[J].中医杂志,2026,67(10):1093-1100.
DAI Guoda,WANG Jianwei,WU Mao,et al.Construction and Clinical Validation of a Deep Learning-Based Automatic Measurement Model for Palmar Tilt and Radial Inclination in Distal Radius Fractures[J].Journal of Traditional Chinese Medicine,2026,67(10):1093-1100.
戴国达,王建伟,吴毛等.基于深度学习的桡骨远端骨折掌倾角与尺偏角自动测量模型构建及临床验证[J].中医杂志,2026,67(10):1093-1100. DOI: 10.13288/j.11-2166/r.2026.10.011.
DAI Guoda,WANG Jianwei,WU Mao,et al.Construction and Clinical Validation of a Deep Learning-Based Automatic Measurement Model for Palmar Tilt and Radial Inclination in Distal Radius Fractures[J].Journal of Traditional Chinese Medicine,2026,67(10):1093-1100. DOI: 10.13288/j.11-2166/r.2026.10.011.
目的
2
构建适配中医临床场景的掌倾角与尺偏角自动测量模型,并验证其在中医手法整复相关场景中的准确率与效率。
方法
2
通过江苏省中医优势病种诊疗大数据平台收集2023年9月1日至2024年9月1日于江苏省18家中医医院及中西医结合医院就诊的桡骨远端骨折患者的桡骨远端正、侧位X线片资料。采用基于多尺度特征融合及边缘感知的医学影像分割框架,结合中医骨伤科解剖认知特点优化人工智能(AI)模型特征提取策略,实现骨折区域自动分割与桡骨远端掌倾角、尺偏角测量,并验证评价AI模型测量尺偏角、掌倾角的准确率,比较AI模型与人工测量的使用时间及平均时间增益率。
结果
2
共收集桡骨远端骨折患者正、侧位X线片15 444张,经预处理后划分为训练集(11 144张,包括正位5066张、侧位6078张)、验证集(3700张,包括正位1840张、侧位1860张)、独立测试集(600张,包括正位300张、侧位300张)。测试集300张正位X线片尺偏角测量中,AI测量与人工测量数据度数误差<3°、<5°时,AI测量准确率分别为83%、93%;300张侧位X线片掌倾角测量中,AI测量与人工测量数据度数误差
<3°、<5°,AI测量准确率分别达78%、90%。测量50张X线片,对于尺偏角,AI测量使用时间为(1.37±0.05)min,较人工测量使用时间(22.57±2.52)min缩短(
P
<0.001);对于掌倾角,AI测量使用时间为(1.33±0.14)min,较人工测量使用时间(23.70±2.80)min缩短(
P
<0.001)。人工测量和AI测量的平均时间增益率分别为93.93%、94.39%。
结论
2
构建了适配临床场景的桡骨远端掌倾角与尺偏角的自动测量模型,可较为高效、精准地测量桡骨远端骨折掌倾角与尺偏角,为中医手法整复疗效量化评估及大样本临床科研提供工具支撑。
Objective
2
To construct an automatic measurement model for palmar tilt and radial inclination suitable for traditional Chinese medicine (TCM) clinical scenarios, and to validate its accuracy and efficiency in TCM manipulative reduction settings.
Methods
2
Data on anteroposterior (AP) and lateral X-rays of distal radius fractures were collected from patients admitted to 18 TCM/ integrated TCM and western medicine hospitals in Jiangsu province between September 1st, 2023, and September 1st, 2024, via the Jiangsu Diagnosis and Treatment Big Data Platform for TCM Dominant Diseases. A medical image segmentation framework based on multi-scale feature fusion and edge-awareness was employed, combined with anatomical knowledge specific to TCM orthopedics, to optimize the feature extraction strategy of an artificial intelligence (AI) model. This framework enabled automatic segmentation of fracture regions and measurement of distal radius palmar tilt and radial inclination. The accuracy of the AI model in measuring radial inclination and volar tilt was validated, and the measurement time and average time gain rate of the AI model were compared to those of manual measurement.
Results
2
A total of 15
444 AP and lateral X-ray images of distal radius fractures were collected, and were divided into a training set (11
144 images, 5066 AP and 6078 lateral), a validation set (3700 images, 1840 AP and 1860 lateral), and an independent test set (600 images, 300 AP and 300 lateral) after preprocessing. In the measurement of 300 AP X-ra
ys in the independent test set for radial inclination, when the degree error between AI measurement and manual measurement was <3° and <5°, AI measurement accuracy was 83% and 93%, respectively. In 300 lateral X-rays in the test set for palmar tilt, when AI measurements had an error of <3° and <5° compared to manual measurements, corresponding accuracy rate was 78% and 90%, respectively. For 50 X-ray images, AI measurement time was (1.37±0.05) min for radial inclination while manual measurement time was (22.57±2.52) min (
P
<0.001); in terms of palmar tilt, the AI measurement time was (1.33±0.14) min, shorter than (23.70±2.80) min for manual measurement time (
P
<0.001). Average time gain rates for manual and AI measurements were 93.93% and 94.39% respectively.
Conclusion
2
An automatic measurement model for palmar tilt and radial inclination in distal radius fractures has been established, enabling more accurate and efficient assessment as well as providing a tool to support the quantitative evaluation of the efficacy of TCM manipulative reduction and large-sample clinical research.
中华中医药学会 . 桡骨远端骨折中西医结合诊疗指南(2024年版) [J]. 中医正骨 , 2025 , 37 ( 1 ): 1 - 8 .
国家骨科医学中心(北京积水潭医院) , 中华医学会骨科学分会创新与转化学组 , 中国康复医学会骨与关节康复专业委员会创伤学组 , 等 . 成人桡骨远端骨折诊断与治疗循证指南(2024) [J]. 骨科临床与研究杂志 , 2024 , 9 ( 5 ): 257 - 274 .
ZHANG N , FANG J . Clinical features and surgical strategies of distal radius posttraumatic deformity [J]. Emerg Med Int , 2022 , 2022 : 5268822 . doi: 10.1155/2022/5268822 http://dx.doi.org/10.1155/2022/5268822 .
LEE S J , KANG M , LEE J S , et al . Automatic assessment of radiological parameters of the distal radius using a hybrid approach combining deep learning and a computer-aided diagnostic algorithm [J]. Clin Orthop Surg , 2025 , 17 ( 6 ): 1035 - 1045 .
KIM D H , MACKINNON T . Artificial intelligence in fracture detection: transfer learning from deep convolutional neural networks [J]. Clin Radiol , 2018 , 73 ( 5 ): 439 - 445 .
SUZUKI T , MAKI S , YAMAZAKI T , et al . Detecting distal radial fractures from wrist radiographs using a deep convolutional neural network with an accuracy comparable to hand orthopedic surgeons [J]. J Digit Imaging , 2022 , 35 ( 1 ): 39 - 46 .
YOON A P , LEE Y L , KANE R L , et al . Development and validation of a deep learning model using convolutional neural networks to identify scaphoid fractures in radiographs [J]. JAMA Netw Open , 2021 , 4 ( 5 ): e216096 .
中华医学会骨科学分会创伤骨科学组 , 中华医学会骨科学分会外固定与肢体重建学组 . 中国成人桡骨远端骨折诊疗指南(2023) [J]. 中华创伤骨科杂志 , 2023 , 25 ( 1 ): 6 - 13 .
国家中医药管理局 . 中医病证诊断疗效标准 [M]. 南京 : 南京大学出版社 , 1994 : 168 .
CHEN J , MEI J , LI X , et al . TransUNet: rethinking the U-Net architecture design for medical image segmentation through the lens of transformers [J]. Med Image Anal , 2024 , 97 : 103280 . doi: 10.1016/j.media.2024. 103280 http://dx.doi.org/10.1016/j.media.2024.103280 .
LIN A , CHEN B , XU J , et al . DS-TRANSUNET: dual swin transformer u-net for medical image segmentation [J]. IEEE Trans Instrum Meas , 2022 , 71 : 1 - 15 . doi: 10. 1109/TIM.2022.3178991 http://dx.doi.org/10.1109/TIM.2022.3178991 .
LIU X , GAO P , YU T , et al . CSWin-UNet: transformer UNet with crossshaped windows for medical image segmentation [J]. Information Fusion , 2025 , 113 : 102634 . doi: 10.1016/j.inffus.2024.102634 http://dx.doi.org/10.1016/j.inffus.2024.102634 .
SUN G , PAN Y , KONG W , et al . DA-TransUNet: integrating spatial and channel dual attention with transformer U-net for medical image segmentation [J]. Front Bioeng Biotechnol , 2024 , 12 : 1398237 . doi: 10.3389/fbioe.2024.1398237 http://dx.doi.org/10.3389/fbioe.2024.1398237 .
LI J , YE J , ZHANG R , et al . CPFTransformer: transformer fusion context pyramid medical image segmentation network [J]. Front Neurosci , 2023 , 17 : 1288366 . doi: 10.3389/fnins.2023.1288366 http://dx.doi.org/10.3389/fnins.2023.1288366 .
ZHANG L , YIN X , LIU X , et al . Medical image segmentation by combining feature enhancement Swin Transformer and UperNet [J]. Sci Rep , 2025 , 15 ( 1 ): 14565 .
JI Y , SHI W , LEI J , et al . DBRSNet: a dual-branch remote sensing image segmentation model based on feature interaction and multi-scale feature fusion [J]. Sci Rep , 2025 , 15 ( 1 ): 27786 .
LI H , LI Y , ZHANG G , et al . Global and local contrastive self-supervised learning for semantic segmentation of HR remote sensing images [J]. IEEE Trans Geosci Remote Sens , 2022 , 60 : 1 - 14 . doi: 10.1109/TGRS. 2022.3147513 http://dx.doi.org/10.1109/TGRS.2022.3147513 .
CHENG D , GAO X , MAO Y , et al . Brain tumor feature extraction and edge enhancement algorithm based on U-Net network [J]. Heliyon , 2023 , 9 ( 11 ): e22536 .
LIN C , ZHANG Z , HU Y . Bio-inspired feature enhancement network for edge detection [J]. Appl Intell , 2022 , 52 ( 10 ): 11027 - 11042 .
PAN Y , YUAN Y , YIN Y , et al . Preparing lessons for progressive training on language models [C]// Proceedings of the AAAI Conference on Artificial Intelligence , 2024 , 38 ( 17 ): 18860 - 18868 . doi: 10.1609/aaai.v38i17.29851 http://dx.doi.org/10.1609/aaai.v38i17.29851 .
PLOMPEN A J M , CABELLOS O , DE SAINT JEAN C , et al . The joint evaluated fission and fusion nuclear data library, JEFF-3.3 [J]. Eur Phys J A Hadron Nucl , 2020 , 56 ( 7 ): 181 .
LEE S , KIM K G , KIM Y J , et al . Automatic segmentation and radiologic measurement of distal radius fractures using deep learning [J]. Clin Orthop Surg , 2024 , 16 ( 1 ): 113 - 124 .
韦家旭 , 所世腾 , 李传争 , 等 . 人工智能技术辅助分析头颈部CTA的应用价值研究 [J]. 中国CT和MRI杂志 , 2024 , 22 ( 8 ): 159 - 161 .
莫军杰 , 裘晓冬 , 周君鹏 . 掌背侧联合入路内固定治疗桡骨远端C3型骨折疗效观察 [J]. 浙江创伤外科 , 2024 , 29 ( 10 ): 1941 - 1943 .
蒿俊行 , 张恒云 , 杨子函 , 等 . 两种不同石膏外固定方式治疗桡骨远端骨折的对比研究 [J]. 中国骨与关节杂志 , 2026 , 15 ( 3 ): 200 - 206 .
杨成 , 张腾 , 杜杰利 . 桡骨远端骨折合并尺骨茎突骨折内固定术后掌倾角和尺偏角与腕关节功能的关系 [J]. 中国中医骨伤科杂志 , 2026 , 34 ( 4 ): 71 - 78 .
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010102007558号