Intelligent Sonographic Identification of Closed Fractures Using Deep Learning

doi:10.26599/AUDT.2026.260033

Abstract

Abstract:

Objective Closed limb fractures are highly prevalent in disaster rescue scenarios, frontline battlefields, and routine military training. Their diagnosis and treatment require significant expertise and timeliness, as missed or delayed diagnosis can lead to more severe secondary trauma. This study aimed to utilize deep learning and ultrasonography for identifying closed limb fractures, constructing an intelligent sonographic recognition model and evaluating its diagnostic value.
Methods A total of 173 patients with X-ray confirmed closed limb fractures and 122 healthy volunteers were enrolled in. Collected ultrasound images were used for deep learning feature extraction. An intelligent diagnostic model for limb fractures based on DenseNet121 was constructed. Model performance was evaluated using accuracy, sensitivity, specificity, precision, and F1-Score.
Results For bone classification (6-class), the model achieved accuracy of 90%, sensitivity of 85%, and F1-Score 85%. For fracture/non-fracture classification (2-class), the results were 99% accuracy and 99% F1-Score.
Conclusion The DenseNet121-based model demonstrated promising results in identifying closed limb fractures from ultrasound images. The model may hold potential for aiding rapid identification and triage in emergency settings.

Key words: Deep learning; Ultrasonography; Fractures; Intelligent diagnosis

Sun Siguo, Huang Jiahui, Ma Bin, Liu Zemin, Liu Xi. Intelligent Sonographic Identification of Closed Fractures Using Deep Learning. Advanced Ultrasound in Diagnosis and Therapy, 2026, 10(3): 223-231.

/ Recommend

Figures/Tables 12

Figure 1

Figure 2

Figure 3

Table 1

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Table 2

Table 3

References 12

[1]	Chartier LB, Bosco L, Lapointe-Shaw L, Chenkin J. Use of point-of-care ultrasound in long bone fractures: a systematic review and meta-analysis. CJEM 2017; 19: 131-142. doi: 10.1017/cem.2016.397
[2]	Kuo RYL, Harrison C, Curran TA, Jones B, Freethy A, Cussons D, et al. Artificial intelligence in fracture detection: a systematic review and meta-analysis. Radiology 2022; 304: 50-62. doi: 10.1148/radiol.211785
[3]	Maki S, Furuya T, Inoue M, Inage K, Eguchi Y, Orita S, et al. Machine learning and deep learning in spinal injury care: a narrative review. J Clin Med 2024; 13: 705. doi: 10.3390/jcm13030705
[4]	Huang G, Liu Z, Van Der Maaten L, Weinberger KQ. Densely connected convolutional networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017:2261-2269.
[5]	Choopong P, Kusakunniran W. Selection of pre-trained weights for transfer learning in automated cytomegalovirus retinitis classification. Sci Rep 2024; 14: 15899. doi: 10.1038/s41598-024-67121-7
[6]	Morid MA, Borjali A, Del Fiol G. A scoping review of transfer learning research on medical image analysis using ImageNet. Comput Biol Med 2021; 128: 104115. doi: 10.1016/j.compbiomed.2020.104115
[7]	Ju RY, Cai W. Fracture detection in pediatric wrist trauma X-ray images using YOLOv8 algorithm. Sci Rep 2023; 13: 20077. doi: 10.1038/s41598-023-47460-7
[8]	Young-Dae Jeon, Min-Jun Kang, Sung-Uk Kuh, Ha-Yeong Cha, Moo-Sub Kim, Ju-Yeon You, et al. Deep learning model based on you only look once algorithm for detection and visualization of fracture areas in three-dimensional skeletal images. Diagnostics (Basel) 2023; 14: 11. doi: 10.3390/diagnostics14010011
[9]	Rokhana, R., Priambodo, J., Karlita, T., Sunarya, I. M. G., Yuniarno, E. M., Purnama, et al. Convolutional neural networks for femoral fracture detection in B-mode ultrasound images. Jurnal Nasional Teknik Elektro dan Teknologi Informasi 2019; 8:59-67.
[10]	Zhang J, Boora N, Melendez S, Rakkunedeth Hareendranathan A, Jaremko. Diagnostic accuracy of 3D ultrasound and artificial intelligence for detection of pediatric wrist injuries. J Children (Basel) 2021; 8: 431.
[11]	Knight J, Zhou Y, Keen C, Hareendranathan AR, Alves-Pereira F, Ghasseminia S, et al. 2D/3D ultrasound diagnosis of pediatric distal radius fractures by human readers vs artificial intelligence. Sci Rep 2023; 13: 14535. doi: 10.1038/s41598-023-41807-w
[12]	Shrimanti Ghosh, Geetika Vadali, Yuyue Zhou, Ayush Singh, Jessica Knight, Christopher Keen, et al. Video summarization and fracture detection in pediatric wrist ultrasound using deep reinforcement learning. Annu Int Conf IEEE Eng Med Biol Soc 2025; 2025: 1-4.

Layers	Output size	DenseNet121
Convolution	112 × 112	7 × 7 Conv, Stride 2
Pooling	56 × 56	3 × 3 Maxpooling, Stride 2
Dense block 1	56 × 56	$ \left[\begin{array}{l}1\times \text{1 Conv}\\3\times 3\text{ Conv}\end{array}\right]\times 6 $
Transition layer 1	56 × 56	1 × 1 Conv
Transition layer 1	28 × 28	2 × 2 Avgpooling, Stride 2
Dense block 2	28 × 28	$ \left[\begin{array}{l}1\times \text{1 Conv}\\3\times 3\text{ Conv}\end{array}\right]\times 12 $
Transition layer 2	28 × 28	1 × 1 Conv
Transition layer 2	14 × 14	2 × 2 Avgpooling, Stride 2
Dense block 3	14 × 14	$ \left[\begin{array}{l}1\times \text{1 Conv}\\3\times 3\text{ Conv}\end{array}\right]\times 24 $
Transition layer 3	14 × 14	1 × 1 Conv
Transition layer 3	7 × 7	2 × 2 Avgpooling, Stride 2
Dense block 4	7 × 7	$ \left[\begin{array}{l}1\times \text{1 Conv}\\3\times 3\text{ Conv}\end{array}\right]\times 16 $
Classification layer	1 × 1	7 × 7 Global avgpooling
Classification layer	1 × 1	1000D Fully-connected, Softmax

	Accuracy	Spcecificity	Sensitivity	Preecision	F1-score	AUC
Bone site	90.54	99.17	85.15	85.85	85.01	99.2
Fracture/non-fracture	99.91	99.72	100	99.87	99.94	100

	Accuracy	Spcecificity	Sensitivity	Preecision	F1-score
Modle	92.34	81.36	95.77	94.27	95.01
Manual	87.20	85.81	87.63	95.27	90.46

[1]	Li Zuoyan, Du Lianfang, Li Fan. Ultrasound Image Segmentation in Cardiovascular Disease: A Review of Techniques and Clinical Applications [J]. Advanced Ultrasound in Diagnosis and Therapy, 2026, 10(3): 137-147.
[2]	Ruby A.Usha, Chandran.J George Chellin. Efficient Fetal Ultrasound Image Segmentation with MFP-Unet: A Deep Learning Approach [J]. Advanced Ultrasound in Diagnosis and Therapy, 2026, 10(3): 216-222.
[3]	Cui Yuanjie, Guo Cuixia, Li Zhen, Zhang Juan, Wu Yuting, Wu Qingqing, Sun Lijuan. Use of Artificial Intelligence in Fetal Brain Ultrasound Examination: A review [J]. Advanced Ultrasound in Diagnosis and Therapy, 2026, 10(2): 90-97.
[4]	Gao Yuanjing, Niu Zihan, Luo Yanwen, Zhou Mengyuan, Xiao Mengsu, Jiang Yuxin, Zhu Qingli. Research Progress on Ultrasound Radiomics in Preoperative Prediction of Axillary Lymph Node Metastasis in Breast Cancer [J]. Advanced Ultrasound in Diagnosis and Therapy, 2026, 10(2): 79-89.
[5]	Mo Sijie, Ding Zhimin, Huang Zhibin, Wang Mengyun, Xu Jinfeng, Zhang Hongan, Dong Fajin. Evaluating the Diagnostic Performance of Sound Touch Elastography, Visco-elastography, and Sound Attenuation in Chronic Liver Diseases Detection [J]. Advanced Ultrasound in Diagnosis and Therapy, 2026, 10(2): 112-122.
[6]	Shi Ming-Li, Liu Guo-Hui, Bao Fu-Xing. Advances in the Application of Ultrasound for Evaluating Placental Function in Fetal Growth Restriction (FGR) Pregnancy [J]. Advanced Ultrasound in Diagnosis and Therapy, 2026, 10(1): 42-50.
[7]	Hu Xuelin, Zhu Ye, Zhang Zisang, Quan Yuanting, Chen Wenwen, Chen Leichong, Xu Guangyu, Qin Luning, Xie Mingxing, Zhang Li. Explainable Artificial Intelligence in Echocardiography [J]. Advanced Ultrasound in Diagnosis and Therapy, 2025, 9(4): 409-425.
[8]	Li Yanran, Cui Yuanjie, Wu Qingqing, Zhang Na. Current Applications of Artificial Intelligence in Obstetric Ultrasound [J]. Advanced Ultrasound in Diagnosis and Therapy, 2025, 9(4): 449-456.
[9]	Zhong Xian, Xie Xiaoyan. Multimodal Ultrasound Radiomics in Liver Disease: Current Status and Future Directions [J]. Advanced Ultrasound in Diagnosis and Therapy, 2025, 9(4): 388-408.
[10]	Jin Tong, Yu Xiaohu, Ai Zheng, Guo Hongcheng. Artificial Intelligence in Ultrasound Imaging: A Review of Progress from Machine Learning to Large Language Model [J]. Advanced Ultrasound in Diagnosis and Therapy, 2025, 9(4): 483-496.
[11]	Zhang Rong, Xie Liting, Jin Qijing, Zhang Chengyue, Guo Teng, Zhao Qiyu, Jiang Tian’an. Research Progress on the Application of Irreversible Electroporation Ablation in Cancers [J]. Advanced Ultrasound in Diagnosis and Therapy, 2025, 9(3): 229-244.
[12]	Zhang Minyu, Jia Baocheng, Huang Liuming. Imaging Diagnosis of Neonatal Umbilical Arteriovenous Malformation Complicated with Portosystemic Shunt [J]. Advanced Ultrasound in Diagnosis and Therapy, 2025, 9(2): 224-227.
[13]	An Zichen, Li Fan. Advancements in the Application of Convolutional Neural Networks in Ultrasound Imaging for Breast Cancer Diagnosis and Treatment [J]. Advanced Ultrasound in Diagnosis and Therapy, 2025, 9(1): 21-31.
[14]	Li Tiantian, Zhu Miao, Shen Dejuan, Qian Xiaoqin. The Diagnostic Pitfall of Lymphadenopathy: Ultrasonic Imaging Findings in a Case of Cat Scratch Lymphadenitis [J]. Advanced Ultrasound in Diagnosis and Therapy, 2025, 9(1): 92-95.
[15]	Xu Jiale, Xia Shujun, Hua Qing, Mei Zihan, Hou Yiqing, Wei Minyan, Lai Limei, Yang Yixuan, Zhou Jianqiao. Performance of ChatGPT and Radiology Residents on Ultrasonography Board-Style Questions [J]. Advanced Ultrasound in Diagnosis and Therapy, 2024, 8(4): 250-254.