Academic Journal
Using deep networks for knee range of motion monitoring in total knee arthroplasty rehabilitation.
| Τίτλος: | Using deep networks for knee range of motion monitoring in total knee arthroplasty rehabilitation. |
|---|---|
| Συγγραφείς: | Zhang YX; Department of Joints, Tianjin Hospital of Tianjin University (Tianjin Hospital), Tianjin, China.; Clinical College of Orthopedics, Tianjin Medical University, Tianjin, China., Wang QY; School of Electrical and Information Engineering, Tianjin University, Tianjin, China., Yang T; Department of Joints, Tianjin Hospital of Tianjin University (Tianjin Hospital), Tianjin, China.; Clinical College of Orthopedics, Tianjin Medical University, Tianjin, China., Wang JH; School of Computer Science and Technology, Tiangong university, Tianjin, China., Yin HT; Department of Joints, Tianjin Hospital of Tianjin University (Tianjin Hospital), Tianjin, China.; Tianjin University Tianjin, Tianjin, China., Wang L; Department of Joints, Tianjin Hospital of Tianjin University (Tianjin Hospital), Tianjin, China., Liu J; Department of Joints, Tianjin Hospital of Tianjin University (Tianjin Hospital), Tianjin, China.; Clinical College of Orthopedics, Tianjin Medical University, Tianjin, China. |
| Πηγή: | Frontiers in bioengineering and biotechnology [Front Bioeng Biotechnol] 2025 Nov 19; Vol. 13, pp. 1691591. Date of Electronic Publication: 2025 Nov 19 (Print Publication: 2025). |
| Τύπος έκδοσης: | Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: Frontiers Media S.A Country of Publication: Switzerland NLM ID: 101632513 Publication Model: eCollection Cited Medium: Print ISSN: 2296-4185 (Print) Linking ISSN: 22964185 NLM ISO Abbreviation: Front Bioeng Biotechnol Subsets: PubMed not MEDLINE |
| Imprint Name(s): | Original Publication: Lausanne : Frontiers Media S.A., [2013]- |
| Περίληψη: | Background: Knee range of motion (ROM) is a key indicator of rehabilitation after total knee arthroplasty (TKA). Current tools, such as visual and protractor measurements, are cumbersome, imprecise, and require professional training, limiting their use in community or home settings. With the rise of smart healthcare, there is a need for a simple, accurate, and low-cost ROM assessment method that reduces healthcare burdens, enables home self-monitoring, and improves rehabilitation outcomes. Methods: A total of 1,103 knee images were collected from 1,790 patients who had undergone TKA. The images were classified into four categories: standard flexion, substandard flexion, standard extension, and substandard extension and six categories: 0°, 25°, 50°, 75°, 100°, and 125°. The images were processed using KROMNet, which was trained with a deep learning architecture that included convolutional, dilated convolution, channel attention layers, and fully connected layers. The model was trained and evaluated using a dataset split into training and test sets, and its performance was assessed with precision, recall, F1-score, and accuracy metrics for both the four-class and six-class tasks. Results: KROMNet achieved an accuracy of 95.02% in the four-class task and 94.12% in the more challenging six-class task. In the four-class task, the precision, recall, and F1-score were 95.04%, 94.96%, and 94.98%, respectively. In the six-class task, KROMNet demonstrated an accuracy of 94.12%, with precision, recall, and F1-scores of 94.64%, 94.59%, and 94.60%, respectively. The model's performance was compared with other state-of-the-art methods, including Hazra's, Du's, Xia's, Victoria's, and Shiwei Liu's models, with KROMNet consistently outperforming these models in both four-class and six-class tasks. Conclusion: The KROMNet model proposed in this study offers an accurate, efficient, cost-effective, and remotely deployable solution for monitoring knee ROM after TKA. KROMNet not only demonstrates superior recognition performance under small sample conditions but also shows strong clinical utility and potential for wider adoption, making it especially suitable for grassroots, community, and home rehabilitation settings. KROMNet is expected to become a key tool in the intelligent rehabilitation system, helping healthcare reduce costs, increase efficiency, and improve patient experience and rehabilitation quality. (Copyright © 2025 Zhang, Wang, Yang, Wang, Yin, Wang and Liu.) |
| Competing Interests: | The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. |
| References: | J Bone Joint Surg Am. 2009 Apr;91(4):753-60. (PMID: 19339558) Nat Rev Dis Primers. 2025 Feb 13;11(1):10. (PMID: 39948092) Sci Rep. 2024 Jul 1;14(1):15013. (PMID: 38951526) Sensors (Basel). 2017 Jun 01;17(6):. (PMID: 28587178) Rev Sci Instrum. 2022 Apr 1;93(4):044106. (PMID: 35489877) Lancet. 2012 Apr 7;379(9823):1331-40. (PMID: 22398175) BMC Musculoskelet Disord. 2025 Jul 4;26(1):630. (PMID: 40616021) Sensors (Basel). 2025 Mar 06;25(5):. (PMID: 40096483) J Arthroplasty. 2025 Nov;40(11):2843-2851.e6. (PMID: 40398579) Sci Rep. 2025 Jul 7;15(1):24286. (PMID: 40624241) J Arthroplasty. 2011 Feb;26(2):178-86. (PMID: 20413247) Clin Rehabil. 2014 Sep;28(9):835-46. (PMID: 24668361) IEEE Trans Neural Syst Rehabil Eng. 2025;33:728-738. (PMID: 40031675) J Arthroplasty. 1988;3(1):17-25. (PMID: 3361317) J Exp Orthop. 2018 Oct 19;5(1):46. (PMID: 30341552) J Biomech. 2025 Jun;186:112708. (PMID: 40286631) Clin Orthop Relat Res. 2017 Jan;475(1):160-167. (PMID: 27178041) Orthop Traumatol Surg Res. 2024 Nov 8;:104044. (PMID: 39522602) Arthritis Care Res (Hoboken). 2015 Oct;67(10):1397-405. (PMID: 25776869) IEEE J Biomed Health Inform. 2021 Mar;25(3):701-710. (PMID: 32396114) BMC Musculoskelet Disord. 2015 Feb 07;16:15. (PMID: 25886975) Gait Posture. 2009 Apr;29(3):360-9. (PMID: 19013070) J Bone Joint Surg Am. 2009 Aug;91(8):1874-81. (PMID: 19651944) Sensors (Basel). 2020 Jan 03;20(1):. (PMID: 31947865) BMC Musculoskelet Disord. 2019 Nov 3;20(1):506. (PMID: 31679511) Sensors (Basel). 2010;10(12):11556-65. (PMID: 22163542) Knee Surg Relat Res. 2016 Mar;28(1):39-45. (PMID: 26955612) Nat Rev Rheumatol. 2011 Jan;7(1):57-63. (PMID: 21119605) J Arthroplasty. 1993 Jun;8(3):307-13. (PMID: 8326313) Arch Phys Med Rehabil. 2010 Jan;91(1):58-66. (PMID: 20103397) Sensors (Basel). 2020 Sep 02;20(17):. (PMID: 32887326) J Arthroplasty. 2006 Jan;21(1):46-52. (PMID: 16446184) Sensors (Basel). 2025 Jan 24;25(3):. (PMID: 39943357) Ann Intern Med. 2000 Oct 17;133(8):635-46. (PMID: 11033593) Clin Orthop Relat Res. 2003 Nov;(416):167-73. (PMID: 14646757) Gait Posture. 2018 Jan;59:229-241. (PMID: 29096266) Disabil Rehabil. 2022 Oct;44(21):6348-6355. (PMID: 34397309) Bioengineering (Basel). 2025 Apr 16;12(4):. (PMID: 40281784) IEEE Trans Neural Syst Rehabil Eng. 2025;33:1048-1060. (PMID: 40031715) J Orthop Surg Res. 2024 Sep 28;19(1):599. (PMID: 39342376) J Arthroplasty. 2016 Jun;31(6):1199-1203. (PMID: 26777578) J Bone Joint Surg Am. 2015 Jul 15;97(14):1129-41. (PMID: 26178888) J Bone Joint Surg Am. 1997 Mar;79(3):342-8. (PMID: 9070521) Semin Arthritis Rheum. 2017 Apr;46(5):544-551. (PMID: 27894727) J Arthroplasty. 2002 Jun;17(4 Suppl 1):59-62. (PMID: 12068407) Arthroplast Today. 2022 Jan 29;13:205-207. (PMID: 35128013) Arch Phys Med Rehabil. 2001 Mar;82(3):396-402. (PMID: 11245764) Disabil Rehabil. 2021 Jan;43(2):150-162. (PMID: 31106616) Int J Surg. 2022 Aug;104:106759. (PMID: 35811014) JMIR Mhealth Uhealth. 2024 Jan 26;12:e47843. (PMID: 38277195) Gait Posture. 2009 Apr;29(3):398-402. (PMID: 19056271) J Bone Joint Surg Am. 2001 Dec;83(12):1856-64. (PMID: 11741066) Clin Rheumatol. 2016 Feb;35(2):371-9. (PMID: 25376465) |
| Contributed Indexing: | Keywords: deep networks; knee range of motion; osteoarthritis; rehabilitation monitoring; total knee arthroplasty |
| Entry Date(s): | Date Created: 20251205 Date Completed: 20251205 Latest Revision: 20251207 |
| Update Code: | 20260130 |
| PubMed Central ID: | PMC12673327 |
| DOI: | 10.3389/fbioe.2025.1691591 |
| PMID: | 41346475 |
| Βάση Δεδομένων: | MEDLINE |
| ISSN: | 2296-4185 |
|---|---|
| DOI: | 10.3389/fbioe.2025.1691591 |