A Review of the Application of Artificial Intelligence in Orthopedic Diseases
Source abstract
Abstract
In recent years, Artificial Intelligence (AI) has revolutionized people’s lives. AI has long made breakthrough progress in the field of surgery. However, the research on the application of AI in orthopedics is still in the exploratory stage. The paper first introduces the background of AI and orthopedic diseases, addresses the shortcomings of traditional methods in the detection of fractures and orthopedic diseases, draws out the advantages of deep learning and machine learning in image detection, and reviews the latest results of deep learning and machine learning applied to orthopedic image detection in recent years, describing the contributions, strengths and weaknesses, and the direction of the future improvements that can be made in each study. Next, the paper also introduces the difficulties of traditional orthopedic surgery and the roles played by AI in preoperative, intraoperative, and postoperative orthopedic surgery, scientifically discussing the advantages and prospects of AI in orthopedic surgery. Finally, the article discusses the limitations of current research and technology in clinical applications, proposes solutions to the problems, and summarizes and outlines possible future research directions. The main objective of this review is to inform future research and development of AI in orthopedics.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Medical Imaging and Analysis · Artificial Intelligence in Healthcare and Education · Hip and Femur Fractures
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (100+)
Show source-provided references
1. John McCarthy: Father of AI10.1109/MIS.2002.1039837 ↗
2. A logical calculus of the ideas immanent in nervous activity
3. Deep learning10.1038/nature14539 ↗
4. Bending the curve: The recent marked slowdown in growth of noninvasive diagnostic imaging10.2214/AJR.10.4835 ↗
5. Artificial intelligence in orthopedics: False hope or not? A narrative review along the line of Gartner’s hype cycle10.1302/2058-5241.5.190092 ↗
6. Machine learning in orthopedics: A literature review10.3389/fbioe.2018.00075 ↗
7. Artificial intelligence and machine learning in orthopedic surgery: A systematic review protocol10.1186/s13018-020-02002-z ↗
8. A review of deep-learning-based medical image segmentation methods10.3390/su13031224 ↗
9. Lung nodule detection in medical images based on improved YOLOv5s10.1109/ACCESS.2023.3296530 ↗
10. Research on mask-wearing detection algorithm based on improved YOLOv510.3390/s22134933 ↗
11. Symmetry-based fusion algorithm for bone age detection with YOLOv5 and ResNet3410.3390/sym15071377 ↗
12. YOLOv5-R: Lightweight real-time detection based on improved YOLOv510.1117/1.JEI.31.3.033033 ↗
13. Real-time recognition and warning of mask wearing based on improved YOLOv5 R6.110.1002/int.22994 ↗
14. An effective tumor detection in MR brain images based on deep CNN approach: i-YOLOV510.1080/08839514.2022.2151180 ↗
15. Mitotic cell detection in histopathological images of neuroendocrine tumors using improved YOLOv5 by transformer mechanism10.1007/s11760-023-02642-8 ↗
16. Research on medical image object detection based on swin-transformer and YOLOv5
17. KPE-YOLOv5: An improved small target detection algorithm based on YOLOv510.3390/electronics12040817 ↗
18. U-Net: Convolutional networks for biomedical image segmentation
19. V-Net: Fully convolutional neural networks for volumetric medical image segmentation
20. M. Z. Alom, M. Hasan, C. Yakopcic, T. Taha, and V. Asari, “Recurrent residual convolutional neural network based on U-Net (R2U-Net) for medical image segmentation,” 2018. doi: 10.48550/arXiv.1802.06955.10.1109/NAECON.2018.8556686 ↗
21. MultiResUNet: Rethinking the U-Net architecture for multimodal biomedical image segmentation10.1016/j.neunet.2019.08.025 ↗
22. Fully dense UNet for 2-D sparse photoacoustic tomography artifact removal10.1109/JBHI.2019.2912935 ↗
23. MDU-Net: Multi-scale densely connected U-Net for biomedical image segmentation10.1007/s13755-022-00204-9 ↗
24. H-DenseUNet: Hybrid densely connected UNet for liver and tumor segmentation from CT volumes10.1109/TMI.2018.2845918 ↗
25. CE-Net: Context encoder network for 2D medical image segmentation10.1109/TMI.2019.2903562 ↗
26. MFP-Unet: A novel deep learning based approach for left ventricle segmentation in echocardiography10.1016/j.ejmp.2019.10.001 ↗
27. N. V. Keetha and C. S. R. Annavarapu, “U-Det: A modified U-Net architecture with bidirectional feature network for lung nodule segmentation,” 2020. doi: 10.48550/arxiv.2003.09293.
28. Prostate segmentation using 2D bridged U-net
29. RAUNet: Residual attention U-Net for semantic segmentation of cataract surgical instruments
30. AnatomyNet: Deep learning for fast and fully automated whole-volume segmentation of head and neck anatomy10.1002/mp.13300 ↗
31. UNet++: A nested u-Net architecture for medical image segmentation
32. RA-UNet: A hybrid deep attention-aware network to extract liver and tumor in CT scans10.3389/fbioe.2020.605132 ↗
33. ANU-Net: Attention-based nested U-Net to exploit full resolution features for medical image segmentation10.1016/j.cag.2020.05.003 ↗
34. Mask R-CNN
35. Intervertebral disc instance segmentation using a multistage optimization mask-RCNN (MOM-RCNN)
36. Improved-Mask R-CNN: Towards an accurate generic MSK MRI instance segmentation platform (data from the Osteoarthritis Initiative)10.1016/j.compmedimag.2022.102056 ↗
37. Probability-based Mask R-CNN for pulmonary embolism detection10.1016/j.neucom.2020.10.022 ↗
38. Application of generated mask method based on Mask R-CNN in classification and detection of melanoma10.1016/j.cmpb.2021.106174 ↗
39. Nuclei R-CNN: Improve mask R-CNN for nuclei segmentation
40. Improved mask R-CNN for lung nodule segmentation
41. Multi-detection and segmentation of breast lesions based on mask RCNN-FPN
42. Application of improved mask R-CNN algorithm based on gastroscopic image in detection of early gastric cancer
43. Mask-refined R-CNN: A network for refining object details in instance segmentation10.3390/s20041010 ↗
44. Liver segmentation from multimodal images using HED-mask R-CNN
45. Attention is all you need
46. J. Chen et al., “TransUNet: Transformers make strong encoders for medical image segmentation,” arXiv:2102.04306, 2021. doi: 10.48550/arxiv.2102.04306.
47. UNETR: Transformers for 3D medical image segmentation
48. Transfuse: Fusing transformers and cnns for medical image segmentation
49. Medical transformer: Gated axial-attention for medical image segmentation
50. Swin-Unet: Unet-like pure transformer for medical image segmentation
51. DS-TransUNet: Dual swin transformer U-Net for medical image segmentation
52. Artificial intelligence in fracture detection: A systematic review and meta-analysis10.1148/radiol.211785 ↗
53. Automatic detection and classification of rib fractures on thoracic CT using convolutional neural network: Accuracy and feasibility10.3348/kjr.2019.0651 ↗
54. Development of an artificial intelligence-assisted computed tomography diagnosis technology for rib fracture and evaluation of its clinical usefulness10.1038/s41598-022-12453-5 ↗
55. Deep-learning-assisted detection and segmentation of rib fractures from CT scans: Development and validation of FracNet10.1016/j.ebiom.2020.103106 ↗
56. Development and assessment of deep learning system for the location and classification of rib fractures via computed tomography10.1016/j.ejrad.2022.110434 ↗
57. Artificial intelligence for the detection of vertebral fractures on plain spinal radiography10.1038/s41598-020-76866-w ↗
58. Deep neural network improves fracture detection by clinicians10.1073/pnas.1806905115 ↗
59. Detecting pelvic fracture on 3D-CT using deep convolutional neural networks with multi-orientated slab images10.1038/s41598-021-91144-z ↗
60. Using artificial intelligence to diagnose osteoporotic vertebral fractures on plain radiographs10.1002/jbmr.4879 ↗
61. Detecting intertrochanteric hip fractures with orthopedist-level accuracy using a deep convolutional neural network10.1007/s00256-018-3016-3 ↗
62. Artificial intelligence to detect the femoral intertrochanteric fracture: The arrival of the intelligent-medicine era10.3389/fbioe.2022.927926 ↗
63. Detection of incomplete atypical femoral fracture on anteroposterior radiographs via explainable artificial intelligence10.1038/s41598-023-37560-9 ↗
64. Artificial intelligence for analyzing orthopedic trauma radiographs: Deep learning algorithms—Are they on par with humans for diagnosing fractures?10.1080/17453674.2017.1344459 ↗
65. Assessment of a deep-learning system for fracture detection in musculoskeletal radiographs10.1038/s41746-020-00352-w ↗
66. Automated fracture screening using an object detection algorithm on whole-body trauma computed tomography10.1038/s41598-022-20996-w ↗
67. Artificial intelligence to diagnose tibial plateau fractures: An intelligent assistant for orthopedic physicians10.1007/s11596-021-2501-4 ↗
68. Automated detection and classification of the proximal humerus fracture by using deep learning algorithm10.1080/17453674.2018.1453714 ↗
69. Artificial intelligence detection of distal radius fractures: A comparison between the convolutional neural network and professional assessments10.1080/17453674.2019.1600125 ↗
70. Using a dual-input convolutional neural network for automated detection of pediatric supracondylar fracture on conventional radiography10.1097/RLI.0000000000000615 ↗
71. The feature ambiguity mitigate operator model helps improve bone fracture detection on X-ray radiograph10.1038/s41598-021-81236-1 ↗
72. Classification of femur fracture in pelvic X-ray images using meta-learned deep neural network10.1038/s41598-020-70660-4 ↗
73. BoostNet: A method to enhance the performance of deep learning model on musculoskeletal radiographs X-ray images10.1007/s13198-021-01580-3 ↗
74. Development and validation of deep learning algorithms for scoliosis screening using back images10.1038/s42003-019-0635-8 ↗
75. Computerized image understanding system for reliable estimation of spinal curvature in idiopathic scoliosis10.1038/s41598-021-86436-3 ↗
76. Deep learning-based high-accuracy quantitation for lumbar intervertebral disc degeneration from MRI10.1038/s41467-022-28387-5 ↗
77. Prediction of osteoporosis from simple hip radiography using deep learning algorithm10.1038/s41598-021-99549-6 ↗
78. Clinical application of artificial intelligence-assisted diagnosis using anteroposterior pelvic radiographs in children with developmental dysplasia of the hip10.1302/0301-620X.102B11.BJJ-2020-0712.R2 ↗
79. Diagnostic accuracy of a deep learning model using YOLOv5 for detecting developmental dysplasia of the hip on radiography images10.1038/s41598-023-33860-2 ↗
80. A deep learning model for detection of cervical spinal cord compression in MRI scans10.1038/s41598-021-89848-3 ↗
81. Degenerative cervical myelopathy: Epidemiology, genetics, and pathogenesis10.1097/BRS.0000000000000913 ↗
82. A screening method for cervical myelopathy using machine learning to analyze a drawing behavior10.1038/s41598-023-37253-3 ↗
83. Multimodal machine learning-based knee osteoarthritis progression prediction from plain radiographs and clinical data10.1038/s41598-019-56527-3 ↗
84. Interpretable and parameter optimized ensemble model for knee osteoarthritis assessment using radiographs10.1038/s41598-021-93851-z ↗
85. Osteoarthritis detection and classification from knee X-ray images based on artificial neural network
86. Automatic estimation of knee effusion from limited MRI data10.1038/s41598-022-07092-9 ↗
87. Gutartige Knochentumoren10.1007/s00113-014-2577-4 ↗
88. Automatic benign and malignant estimation of bone tumors using deep learning
89. Malignant bone tumors diagnosis using magnetic resonance imaging based on deep learning algorithms10.3390/medicina58050636 ↗
90. Primary bone tumor detection and classification in full-field bone radiographs via YOLO deep learning model10.1007/s00330-022-09289-y ↗
91. Initial diagnostic management of pediatric bone tumors10.1016/j.jpedsurg.2016.02.068 ↗
92. Bone tumor necrosis rate detection in few-shot X-rays based on deep learning10.1016/j.compmedimag.2022.102141 ↗
93. An AI based classifier model for lateral pillar classification of Legg-Calve–Perthes10.1038/s41598-023-34176-x ↗
94. Development of machine learning algorithms to predict patient dissatisfaction after primary total knee arthroplasty10.1016/j.arth.2020.05.061 ↗
95. Development and validation of a machine learning algorithm after primary total hip arthroplasty: Applications to length of stay and payment models10.1016/j.arth.2018.12.030 ↗
96. Anatomical variations that can lead to spine surgery at the wrong level: Part II thoracic spine
97. Automatic localization and identification of vertebrae in spine CT via a joint learning model with deep neural networks
98. Machine learning techniques for the optimization of joint replacements: Application to a short-stem hip implant10.1371/journal.pone.0183755 ↗
99. Loosening of total knee arthroplasty–Always aseptic?10.1016/j.jcot.2019.05.001 ↗
100. Detecting mechanical loosening of total hip arthroplasty using deep convolutional neural network