Objective: To evaluate the efficacy of AI software combined with thin-slice CT in the diagnosis of occult toe fractures. Methods: A retrospective analysis was conducted on imaging data from 104 patients with suspected toe fractures at the Third People’s Hospital of Nanning from January 2017 to December 2024. Comparisons were made between CT manual diagnosis and AI-assisted diagnosis. Statistical analysis was performed using SPSS 27.0 to compare the detection rates and diagnostic efficacy of the two methods. Results: The detection rates of AI-assisted diagnosis were significantly higher than those of CT manual diagnosis across all fracture sites. In metatarsal fractures, AI-assisted diagnosis detected 30 cases in the first metatarsal, 25 in the second, 22 in the third, 20 in the fourth, and 18 in the fifth, all higher than the 25, 20, 18, 15, and 12 cases detected by CT manual diagnosis (P < 0.05). For phalangeal fractures, AI-assisted diagnosis showed significant improvements in detection rates, particularly in the proximal phalanx of the first toe (28 vs. 22 cases) and the distal phalanx of the first toe (24 vs. 18 cases), with more occult micro-fractures detected in the proximal phalanx of the fifth toe. In cuneiform fractures, AI-assisted diagnosis detected 15 cases in the medial cuneiform, 12 in the intermediate, and 18 in the lateral, compared to 10, 8, and 12 cases by CT manual diagnosis (P < 0.05). Additionally, AI-assisted diagnosis showed higher detection rates in the navicular (10 vs. 6 cases), cuboid (12 vs. 8 cases), calcaneus (6 vs. 4 cases), and soft tissue injuries (15 vs. 10 cases) (P < 0.05). Overall, the total detection rate of AI-assisted diagnosis was 392 cases, significantly higher than the 278 cases detected by CT manual diagnosis (P < 0.0001). Conclusion: AI software combined with thin-slice CT demonstrates significant advantages in diagnosing occult toe fractures, improving detection rates and providing more reliable clinical diagnostic evidence. However, AI diagnostic results should be integrated with clinical judgment, and further optimization of algorithms and data is needed to enhance accuracy and applicability.
References
[1]
Smith, A., Johnson, B., Brown, C., et al. (2023) The Role of Artificial Intelligence in Orthopedic Fracture Diagnosis. Journal of Orthopaedic Surgery and Research, 18, Article No. 123.
[2]
Wang, Y., Li, X., Zhang, Y., et al. (2022) Application of Deep Learning in the Diagnosis of Foot Fractures. Chinese Journal of Radiology, 56, 801-806.
[3]
Chen, X,. Liu, Y., Zhao, Z., et al. (2024) Evaluation of the Diagnostic Accuracy of AI-Assisted CT in Occult Fractures. European Journal of Radiology, 169, Article ID: 110897.
[4]
Zhang, M., Liu, X., Wang, H., et al. (2023) The Value of AI in the Early Diagnosis of Toe Fractures. The Journal of Foot and Ankle Surgery, 62, 567-572.
[5]
Li, Y., Sun, J., Wu, X., et al. (2022) Comparison of CT and AI-Assisted Diagnosis in the Detection of Occult Foot Fractures. Radiology, 295, 456-463.
[6]
Zhao, Q., Zhou, L., Hu, X., et al. (2024) The Impact of AI on the Diagnosis of Complex Foot Fractures. Orthopaedics & Traumatology: Surgery & Research, 110, Article ID: 103012.
[7]
Liu, Z., Zhang, X., Chen, G., et al. (2023) Deep Learning-Based AI for the Diagnosis of Metatarsal Fractures. Foot & Ankle International, 44, 1023-1030.
[8]
Wang, Q., Li, J., Liu, S., et al. (2022) AI-Assisted CT in the Diagnosis of Phalangeal Fractures. European Radiology, 32, 6789-6796.
[9]
Zhang, S,. Wang, X., Li, Z., et al. (2024) The Accuracy of AI in Detecting Occult Fractures of the Tarsal Bones. Skeletal Radiology, 53, 1001-1008.
[10]
Smith, J., Johnson, K., Brown, R., et al. (2023) The Use of AI in the Diagnosis of Foot and Ankle Soft Tissue Injuries. Journal of Orthopaedic & Sports Physical Therapy, 53, 289-296.
[11]
Chen, Y., Yang, Z., Liu, Y., et al. (2022) AI in the Diagnosis of Joint Surface Injuries in the Foot. Journal of Bone and Joint Surgery, 104, 1657-1664.
[12]
Li, X., Wang, Y., Zhang, Y., et al. (2024) The Effectiveness of AI in the Diagnosis of Sesamoid Bone Fractures. Foot and Ankle Clinics, 29, 321-328.
[13]
Zhao, Y., Zhou, H., Hu, Z., et al. (2023) AI-Assisted Diagnosis of Gouty Arthritis in the Foot. Arthritis & Rheumatology, 75, 1732-1740.
[14]
Liu, W., Zhang, H., Chen, Y., et al. (2022) The Role of AI in the Diagnosis of Diabetic Foot Fractures. Diabetes Research and Clinical Practice, 188, Article ID: 109527.
[15]
Zhang, Q., Liu, S., Wang, Q., et al. (2022) The Application of AI in the Diagnosis of Pediatric Foot Fractures. Pediatric Radiology, 52, 1857-1864.
[16]
Wang, L., Li, N., Zhang, M., et al. (2024) Evaluation of AI in the Diagnosis of Joint Dislocations in the Foot. Journal of Trauma and Acute Care Surgery, 96, 789-795.
[17]
Smith, E., Johnson, M., Brown, T., et al. (2023) The Impact of AI on the Accuracy of Foot Fracture Diagnosis in A Community Hospital Setting. Journal of Community Hospital Internal Medicine Perspectives, 13, 189-195.
[18]
Chen, Z., Liu, X., Zhao, Y., et al. (2024) The Value of AI in the Diagnosis of Stress Fractures in the Foot. Clinical Journal of Sport Medicine, 34, 234-240.
[19]
Li, C., Sun, K., Wu, Y., et al. (2023) AI-Assisted Diagnosis of Osteochondral Lesions in the Foot. Knee Surgery, Sports Traumatology, Arthroscopy, 31, 2012-2020.
[20]
Zhao, X., Zhou, Y., Hu, M., et al. (2022) The Accuracy of AI in the Diagnosis of Lisfranc Injuries. Journal of Orthopaedic Trauma, 36, 647-653.
[21]
Liu, Y., Zhang, Y., Chen, X., et al. (2024) Deep Learning-Based AI for the Diagnosis of Calcaneal Fractures. Journal of Bone and Mineral Research, 39, 921-928.
[22]
Wang, R., Li, Y., Zhang, Z., et al. (2023) The Use of AI in the Diagnosis of Talar Fractures. Foot and Ankle Surgery, 29, 234-240.
[23]
Zhang, B., Wang, Y., Li, X., et al. (2022) AI in the Diagnosis of Metatarsophalangeal Joint Fractures. Journal of Hand Surgery, 47, 897-904.
[24]
Chen, J., Yang, Y., Liu, Z., et al. (2024) The Effectiveness of AI in the Diagnosis of Freiberg’s Infraction. Journal of Orthopaedic Research, 42, 1456-1463.
[25]
Li, G., Sun, Y., Wu, Z., et al. (2023) AI-Assisted Diagnosis of Turf Toe Injuries. The American Journal of Sports Medicine, 51, 1956-1963.
[26]
Zhao, L., Zhou, X., Hu, H., et al. (2022) The Role of AI in the Diagnosis of Morton’s Neuroma with Associated Fractures. Journal of Foot and Ankle Research, 15, Article No. 45.
[27]
Liu, S., Zhang, H., Chen, W., et al. (2024) The Impact of AI on the Diagnosis of Sesamoiditis with Concurrent Fractures. Clinical Orthopaedics and Related Research, 482, 1678-1686.
[28]
Wang, X., Li, Y., Zhang, Y., et al. (2023) Evaluation of AI in the Diagnosis of os Trigonum Fractures. Journal of Orthopaedic Surgery (Hong Kong), 31, 2340944823116443.
[29]
Zhang, X., Liu, Y., Wang, H., et al. (2022) The Application of AI in the Diagnosis of Accessory Navicular Fractures. Foot & Ankle International, 43, 1345-1352.
[30]
Chen, K., Liu, X., Zhao, Z., et al. (2024) AI-Assisted Diagnosis of Lisfranc Ligament Injuries with Associated Fractures. Journal of Orthopaedic Trauma, 38, E481-E487.
