Application of Deep Learning in Auxiliary Diagnosis of Rib Fractures

doi:10.3778/j.issn.1002-8331.2501-0153

Abstract

Abstract: Rib fracture refers to the complete or partial destruction of the integrity of the rib structure, which is one of the most common chest trauma in clinic. In recent years, deep learning technology has shown great potential in the auxiliary diagnosis of fracture. Therefore, this paper summarizes the deep learning methods used in the auxiliary diagnosis of rib fracture. This paper introduces the public image data set, systematically expounds the application of classical convolutional neural network in rib fracture lesion recognition, expounds the improved algorithm of rib fracture based on single network, the improved algorithm of rib fracture based on multi-network, the original rib fracture lesion recognition algorithm and the application of artificial intelligence in rib fracture diagnosis, compares the advantages and limitations of different models, points out the existing difficulties in this field, and prospects the future optimization direction.

Key words: deep learning, rib fracture, medical image processing, computer-aided diagnosis

摘要： 肋骨骨折特指肋骨结构的完整性遭受完全或部分破坏，是临床中最常见的胸部创伤之一。近几年深度学习技术在辅助骨折诊断方面展现出发展的巨大潜力，因此针对肋骨骨折辅助诊断中所采用的深度学习方法进行了总结梳理。介绍了公开的影像学数据集，系统阐述了经典卷积神经网络在肋骨骨折病灶识别中的应用，阐述了基于单网络模型的肋骨骨折改进算法、基于多网络模型的肋骨骨折改进算法、原创肋骨骨折病灶识别算法以及人工智能在肋骨骨折辅助诊断中的应用，比较了不同模型的优点以及局限性，指出该领域目前存在的难点并对未来优化方向进行展望。

关键词: 深度学习, 肋骨骨折, 医学图像处理, 计算机辅助诊断

LI Zhiwei, LIU Jing, ZHANG Junzhong, WEI Dejian, CAO Hui. Application of Deep Learning in Auxiliary Diagnosis of Rib Fractures[J]. Computer Engineering and Applications, 2025, 61(19): 74-91.

李智唯, 刘静, 张俊忠, 魏德健, 曹慧. 深度学习在肋骨骨折辅助诊断中的应用[J]. 计算机工程与应用, 2025, 61(19): 74-91.

References

[1] SIRMALI M, TüRüT H, TOP?U S, et al. A comprehensive analysis of traumatic rib fractures: morbidity, mortality and management[J]. European Journal of Cardio-Thoracic Surgery, 2003, 24(1): 133-138.
[2] 杨金良, 黄刚. 肋骨骨折治疗策略、操作技术以及未来方向[J]. 创伤外科杂志, 2016, 18(1): 1-5.
YANG J L, HUANG G. Treatment strategies, operating techniques and future directions of rib fractures[J]. Journal of Traumatic Surgery, 2016, 18(1): 1-5.
[3] KHUNG S, MASSET P, DUHAMEL A, et al. Automated 3D rendering of ribs in 110 polytrauma patients: strengths and limitations[J]. Academic Radiology, 2017, 24(2): 146-152.
[4] JIN L, GE X J, LU F, et al. Low-dose CT examination for rib fracture evaluation: a pilot study[J]. Medicine, 2018, 97(30): e11624.
[5] MAYBRRRY J C, SCHIPPER P H. Traumatic rib fracture: conservative therapy or surgical fixation?[M]//Difficult decisions in thoracic surgery. Springer: London, 2011: 489-493.
[6] LU M S, HUANG Y K, LIU Y H, et al. Delayed pneumothorax complicating minor rib fracture after chest trauma[J]. The American Journal of Emergency Medicine, 2008, 26(5): 551-554.
[7] 陈先昌. 基于卷积神经网络的深度学习算法与应用研究[D]. 杭州: 浙江工商大学, 2014.
CHEN X C. Research on algorithm and application of deep learning based on convolutional neural network[D]. Hangzhou: Zhejiang Gongshang University, 2014.
[8] SAOOD A, HATEM I. COVID-19 lung CT image segmentation using deep learning methods: U-Net versus SegNet[J]. BMC Medical Imaging, 2021, 21(1): 1-10.
[9] GESSERT N, SENTKER T, MADESTA F, et al. Skin lesion classification using CNNs with patch-based attention and diagnosis-guided loss weighting[J]. IEEE Transactions on Biomedical Engineering, 2020, 67(2): 495-503.
[10] SU Y, LI D, CHEN X D. Lung nodule detection based on faster R-CNN framework[J]. Computer Methods and Programs in Biomedicine, 2021, 200: 105866.
[11] EGGER J, GSAXNER C, PEPE A, et al. Medical deep learning: a systematic meta-review[J]. Computer Methods and Programs in Biomedicine, 2022, 221: 106874.
[12] VAN EIJNATTEN M, RUNDO L, BATENBURG K J, et al. 3D deformable registration of longitudinal abdominopelvic CT images using unsupervised deep learning[J]. Computer Methods and Programs in Biomedicine, 2021, 208: 106261.
[13] BAILLY A, BLANC C, FRANCIS é, et al. Effects of dataset size and interactions on the prediction performance of logistic regression and deep learning models[J]. Computer Methods and Programs in Biomedicine, 2022, 213: 106504.
[14] 吴玉超, 林岚, 王婧璇, 等. 基于卷积神经网络的语义分割在医学图像中的应用[J]. 生物医学工程学杂志, 2020, 37(3): 533-540.
WU Y C, LIN L, WANG J X, et al. Application of semantic segmentation based on convolutional neural network in medical images[J]. Journal of Biomedical Engineering, 2020, 37(3): 533-540.
[15] ROTH H R, WANG Y N, YAO J H, et al. Deep convolutional networks for automated detection of posterior-element fractures on spine CT[C]//Proceedings of the Medical Imaging 2016: Computer-Aided Diagnosis, 2016: 97850P.
[16] BAR A, WOLF L, AMITAI O B, et al. Compression fractures detection on CT[C]//Proceedings of the Medical Imaging 2017: Computer-Aided Diagnosis, 2017: 1013440.
[17] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[18] MIKOLOV T, KARAFIáT M, BURGET L, et al. Recurrent neural network based language model[C]//Proceedings of the Interspeech 2010, 2010: 1045-1048.
[19] RAGHAVENDRA U, BHAT N S, GUDIGAR A, et al. Automated system for the detection of thoracolumbar fractures using a CNN architecture[J]. Future Generation Computer Systems, 2018, 85: 184-189.
[20] BURNS J E, YAO J H, MU?OZ H, et al. Automated detection, localization, and classification of traumatic vertebral body fractures in the thoracic and lumbar spine at CT[J]. Radiology, 2016, 278(1): 64-73.
[21] CHILAMKURTHY S, GHOSH R, TANAMALA S, et al. Deep learning algorithms for detection of critical findings in head CT scans: a retrospective study[J]. The Lancet, 2018, 392(10162): 2388-2396.
[22] HUANG S T, LIU L R, CHIU H W, et al. Deep convolutional neural network for rib fracture recognition on chest radiographs[J]. Frontiers in Medicine, 2023, 10: 1178798.
[23] CASTRO-ZUNTI R, CHAE K J, CHOI Y, et al. Assessing the speed-accuracy trade-offs of popular convolutional neural networks for single-crop rib fracture classification[J]. Computerized Medical Imaging and Graphics, 2021, 91: 101937.
[24] SZEGEDY C, VANHOUCKE V, IOFFE S, et al. Rethinking the inception architecture for computer vision[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 2818-2826.
[25] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 770-778.
[26] SANDLER M, HOWARD A, ZHU M L, et al. MobileNetV2: inverted residuals and linear bottlenecks[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 4510-4520.
[27] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J]. arXiv:1409.
1556, 2014.
[28] 闫军, 田国钰. 医学影像技术学CT的工作原理以及新应用探讨[J]. 影像研究与医学应用, 2020, 4(3): 87-88.
YAN J, TIAN G Y. Discussion on the working principle and new application of CT in medical imaging technology[J]. Journal of Imaging Research and Medical Applications, 2020, 4(3): 87-88.
[29] GHOSH A, BOSE S, PATTON D, et al. Deep learning-based prediction of rib fracture presence in frontal radiographs of children under two years of age: a proof-of-concept study[J]. The British Journal of Radiology, 2023, 96(1145): 20220778.
[30] 罗鑫, 王永雄, 张佳鹏, 等. 基于多重注意力的肋骨骨折检测研究[J]. 控制工程, 2023, 30(9): 1679-1685.
LUO X, WANG Y X, ZHANG J P, et al. Detection of rib fractures based on multiple attention[J]. Control Engineering of China, 2023, 30(9): 1679-1685.
[31] 杨超朋, 赵俊彦, 何光龙, 等. 基于深度学习的人体肋骨骨折智能检测技术[J]. 刑事技术, 2021, 46(2): 134-139.
YANG C P, ZHAO J Y, HE G L, et al. Deep learning into intelligent detection of rib fracture from X-ray imagery[J]. Forensic Science and Technology, 2021, 46(2): 134-139.
[32] SUN H B, WANG X, LI Z R, et al. Automated rib fracture detection on chest X-ray using contrastive learning[J]. Journal of Digital Imaging, 2023, 36(5): 2138-2147.
[33] HUANG G, LIU Z, VAN DER MAATEN L, et al. Densely connected convolutional networks[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 2261-2269.
[34] 鹿静雅, 伍志发, 刘梦秋, 等. 基于卷积神经网络的胸部薄层CT图像肋骨骨折分割与检测研究[J]. 临床放射学杂志, 2023, 42(6): 996-1002.
LU J Y, WU Z F, LIU M Q, et al. Research on rib fracture segmentation and detection of chest thin-layer CT image based on convolution neural network[J]. Journal of Clinical Radiology, 2023, 42(6): 996-1002.
[35] REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149.
[36] ZHOU Q Q, WANG J S, TANG W, et al. Automatic detection and classification of rib fractures on thoracic CT using convolutional neural network: accuracy and feasibility[J]. Korean Journal of Radiology, 2020, 21(7): 869-879.
[37] EDAMADAKA S, BROWN D W, SWAROOP R, et al. FasterRib: a deep learning algorithm to automate identification and characterization of rib fractures on chest computed tomography scans[J]. The Journal of Trauma and Acute Care Surgery, 2023, 95(2): 181-185.
[38] GAO Y, LIU H Z, JIANG L, et al. CCE-Net: a rib fracture diagnosis network based on contralateral, contextual, and edge enhanced modules[J]. Biomedical Signal Processing and Control, 2022, 75: 103620.
[39] REDMON J, FARHADI A. YOLOv3: an incremental improvement[J]. arXiv:1804.02767, 2014.
[40] 白洁, 孙晶, 程晓光, 等. 基于YOLOv3算法的肋骨骨折诊断模型的构建及应用[J]. 法医学杂志, 2023, 39(4): 343-349.
BAI J, SUN J, CHENG X G, et al. Construction and application of rib fracture diagnosis model based on YOLOv3 algorithm[J]. Journal of Forensic Medicine, 2023, 39(4): 343-349.
[41] CHEN M, DU P, ZHAO J Y. SCRFD: spatial coherence based rib fracture detection[C]//Proceedings of the 2018 5th International Conference on Biomedical and Bioinformatics Engineering. New York: ACM, 2018: 105-109.
[42] SHELHAMER E, LONG J, DARRELL T. Fully convolutional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(4): 640-651.
[43] LENGA M, KLINDER T, BüRGER C, et al. Deep learning based rib centerline extraction and labeling[C]//Proceedings of the International Workshop on Computational Methods and Clinical Applications in Musculoskeletal Imaging. Cham: Springer, 2019: 99-113.
[44] RONNEBERGER O, FISCHER P, BROX T. U-Net: convolutional networks for biomedical image segmentation[C]//Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer, 2015: 234-241.
[45] WANG X M, WANG Y X. Composite attention residual U-Net for rib fracture detection[J]. Entropy, 2023, 25(3): 466.
[46] JIN L, YANG J C, KUANG K M, et al. Deep-learning-assisted detection and segmentation of rib fractures from CT scans: development and validation of FracNet[J]. eBioMedicine, 2020, 62: 103106.
[47] 何学才, 金倞, 李铭, 等. 基于完全融合集成网络候选框的肋骨骨折检测方法[J]. 解剖学报, 2022, 53(3): 396-401.
HE X C, JIN L, LI M, et al. Complete box fusion based on ensemble networks for rib fracture detection and localization[J]. Acta Anatomica Sinica, 2022, 53(3): 396-401.
[48] MILLETARI F, NAVAB N, AHMADI S A. V-Net: fully convolutional neural networks for volumetric medical image segmentation[C]//Proceedings of the 2016 4th International Conference on 3D Vision. Piscataway: IEEE, 2016: 565-571.
[49] LIN Z W, DAI W L, LAI Q Q, et al. Deep learning-based computed tomography applied to the diagnosis of rib fractures[J]. Journal of Radiation Research and Applied Sciences, 2023, 16(2): 100558.
[50] MENG X H, WU D J, WANG Z, et al. A fully automated rib fracture detection system on chest CT images and its impact on radiologist performance[J]. Skeletal Radiology, 2021, 50(9): 1821-1828.
[51] ZHANG B, JIA C X, WU R Z, et al. Improving rib fracture detection accuracy and reading efficiency with deep learning-based detection software: a clinical evaluation[J]. The British Journal of Radiology, 2021, 94(1118): 20200870.
[52] WANG S H, WU D J, YE L F, et al. Assessment of automatic rib fracture detection on chest CT using a deep learning algorithm[J]. European Radiology, 2023, 33(3): 1824-1834.
[53] WU M X, CHAI Z Z, QIAN G W, et al. Development and evaluation of a deep learning algorithm for rib segmentation and fracture detection from multicenter chest CT images[J]. Radiology Artificial Intelligence, 2021, 3(5): e200248.
[54] WEIKERT T, NOORDTZIJ L A, BREMERICH J, et al. Assessment of a deep learning algorithm for the detection of rib fractures on whole-body trauma computed tomography[J]. Korean Journal of Radiology, 2020, 21(7): 891-899.
[55] LI N, WU Z, JIANG C, et al. An automatic fresh rib fracture detection and positioning system using deep learning[J]. The British Journal of Radiology, 2023, 96(1146): 20221006.
[56] 梁洁, 孙金磊, 李梦远, 等. 基于深度学习人工智能辅助系统用于CT检出肋骨新鲜骨折[J]. 中国介入影像与治疗学, 2023, 20(9): 555-560.
LIANG J, SUN J L, LI M Y, et al. Artificial intelligence assisted system based on deep learning for detecting fresh rib fractures on CT[J]. Chinese Journal of Interventional Imaging and Therapy, 2023, 20(9): 555-560.
[57] ZHANG J Z, LI Z W, YAN S X, et al. An algorithm for automatic rib fracture recognition combined with nnU-net and DenseNet[J]. Evidence-Based Complementary and Alternative Medicine, 2022, 2022(1): 5841451.
[58] YAO L D, GUAN X J, SONG X W, et al. Rib fracture detection system based on deep learning[J]. Scientific Reports, 2021, 11(1): 23513.
[59] HU Y T, HE X C, ZHANG R, et al. Slice grouping and aggregation network for auxiliary diagnosis of rib fractures[J]. Biomedical Signal Processing and Control, 2021, 67: 102547.
[60] CAO Z, XU L M, CHEN D Z, et al. A robust shape-aware rib fracture detection and segmentation framework with contrastive learning[J]. IEEE Transactions on Multimedia, 2023, 25: 1584-1591.
[61] CHAI Z Z, LIN H J, LUO L Y, et al. ORF-net: deep omni-supervised rib fracture detection from chest CT scans[C]//Proceedings of the 25th International Conference on Medical Image Computing and Computer Assisted Intervention. Cham: Springer, 2022: 238-248.
[62] IBANEZ V, GUNZ S, ERNE S, et al. RiFNet: automated rib fracture detection in postmortem computed tomography[J]. Forensic Science, Medicine, and Pathology, 2022, 18(1): 20-29.
[63] GAO Y, CHEN H, GE R J, et al. Deep learning-based framework for segmentation of multiclass rib fractures in CT utilizing a multi-angle projection network[J]. International Journal of Computer Assisted Radiology and Surgery, 2022, 17(6): 1115-1124.
[64] 张倩, 王大为, 隋时, 等. 深度学习计算机辅助诊断系统检测胸部DR肋骨骨折的验证性研究[J]. 中国临床医学影像杂志, 2022, 33(6): 430-434.
ZHANG Q, WANG D W, SUI S, et al. A confirmatory study of deep learning based computer-aided diagnosis system for detecting chest DR rib fractures[J]. Journal of China Clinic Medical Imaging, 2022, 33(6): 430-434.
[65] 吴育鑫, 薛蕴菁, 段青, 等. 基于深度学习的计算机辅助诊断系统检出DR胸部正位片中的骨折[J]. 中国介入影像与治疗学, 2020, 17(11): 675-678.
WU Y X, XUE Y J, DUAN Q, et al. Deep-learning based computer aided diagnosis system in detecting fractures on anteroposterior chest DR films[J]. Chinese Journal of Interventional Imaging and Therapy, 2020, 17(11): 675-678.
[66] TAN H, XU H, YU N, et al. The value of deep learning-based computer aided diagnostic system in improving diagnostic performance of rib fractures in acute blunt trauma[J]. BMC Medical Imaging, 2023, 23(1): 55.
[67] KAIUME M, SUZUKI S, YASAKA K, et al. Rib fracture detection in computed tomography images using deep convolutional neural networks[J]. Medicine, 2021, 100(20): e26024.
[68] 刘玉蒙, 吴若岱, 陆超, 等. 人工智能在胸部骨折CT诊断中的应用[J]. 广东医学, 2024, 45(8): 993-997.
LIU Y M, WU R D, LU C, et al. Application of artificial intelligence in CT diagnosis of thoracic fracture[J]. Guangdong Medical Journal, 2024, 45(8): 993-997.
[69] 刘想, 谢辉辉, 许玉峰, 等. 人工智能在胸部创伤肋骨骨折CT诊断中应用的初步研究[J]. 上海交通大学学报 (医学版), 2021, 41(7): 920-925.
LIU X, XIE H H, XU Y F, et al. Application of artificial intelligence to CT diagnosis of thoracic traumatic rib sites: a preliminary study[J]. Journal of Shanghai Jiao Tong University (Medical Science), 2021, 41(7): 920-925.
[70] 刘想, 谢辉辉, 许玉峰, 等. 人工智能对提高放射科住院医生诊断胸部肋骨骨折一致性的价值[J]. 北京大学学报 (医学版), 2023, 55(4): 670-675.
LIU X, XIE H H, XU Y F, et al. Value of artificial intelligence in the improvement of diagnostic consistency of radiology residents[J]. Journal of Peking University (Health Sciences), 2023, 55(4): 670-675.
[71] YANG C H, WANG J, XU J X, et al. Development and assessment of deep learning system for the location and classification of rib fractures via computed tomography[J]. European Journal of Radiology, 2022, 154: 110434.
[72] 张斌, 成跃, 杜静波, 等. 基于深度学习的计算机辅助诊断系统在诊断肋骨骨折方面的应用价值[J]. 武警医学, 2023, 34(8): 656-659.
ZHANG B, CHENG Y, DU J B, et al. Application value of deep learning-based computer-aided diagnosis system in diagnosing rib fractures[J]. Medical Journal of the Chinese People’s Armed Police Force, 2023, 34(8): 656-659.
[73] 熊山, 陈博, 毛杰, 等. 基于深度学习的计算机辅助诊断系统在肋骨骨折诊断中的应用[J]. CT理论与应用研究, 2022, 31(5): 617-622.
XIONG S, CHEN B, MAO J, et al. Application of computer-aided diagnosis system based on deep learning in rib fracture diagnosis[J]. Computerized Tomography Theory and Applications, 2022, 31(5): 617-622.
[74] 朱雅茹, 祁良, 徐磊, 等. 人工智能软件辅助诊断新鲜肋骨骨折的效能评估[J]. 南京医科大学学报 (自然科学版), 2022, 42(2): 227-232.
ZHU Y R, QI L, XU L, et al. Effectiveness evaluation of artificial intelligence system in the diagnosis of fresh rib fractures[J]. Journal of Nanjing Medical University (Natural Sciences), 2022, 42(2): 227-232.
[75] 李星宇, 雷禹, 黄晓旗, 等. 基于AI与人工阅片对肋骨骨折性质诊断价值的比较[J]. 中国医疗设备, 2022, 37(8): 32-36.
LI X Y, LEI Y, HUANG X Q, et al. Comparison of the diagnostic value of rib fracture properties based on AI and manual reading[J]. China Medical Devices, 2022, 37(8): 32-36.