A deep learning based automatic two‑dimensional digital templating model for total knee arthroplasty
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Background Preoperative templating is an important step for total knee arthroplasty (TKA), facilitating hospital personnel in the anticipation and preparation of necessary surgical resources. Despite its importance, this process currently lacks automation. This study aimed to develop an artificial intelligence (AI) model to automate implant size prediction. Methods A total of 13,281 (2938 anteroposterior, 10,343 lateral) knee radiographs obtained from the authors’ institute were utilized for model training, with 2302 (1034 anteroposterior, 1268 lateral) images set apart for validation and testing. The templating AI model integrates a pipeline composed of multiple steps for automated implant size estimation. To predict implant size, anterioposterior (AP) and lateral radiograph predictions were merged, selecting the smaller of the predicted sizes to prevent implant overhang. The model’s size predictions were validated with 81 real TKA data set apart from the training data, and its accuracy was compared to that of manual templating by an orthopedic specialist. Predictions matching the actual implanted sizes were labeled “exact” and those within one size, “accurate.” The influence of patient characteristics on the model’s prediction accuracy was also analyzed. The measurement time elapsed for implant sizing was recorded for both the AI model and the orthopedic specialist. Implant position predicted by the model was validated by comparing insert locations with postoperative images. Results Compared with data from 81 actual TKA procedures, the model provided exact predictions for 39.5% of femoral and 43.2% of tibial components. Allowing a one-size margin of error, 88.9% of predictions were deemed “accurate” for both components. Interobserver reliability (Cohen’s kappa) were 0.60 and 0.70 for femoral and tibial implants, respectively, both classified as “substantial.” The orthopedic specialist produced results accurate within one-size margin of error in 95.1% and 100% of cases for femoral and tibial components, respectively. Interobserver reliability between the orthopedic specialist and ground truth was 0.76 and 0.8 for femoral and tibial components, respectively. The measurement time per case was 48.7 s for the AI model, compared with 97.5 s for the orthopedic specialist. Compared with postoperative radiographs, predicted implant position had an error of less than 4 mm on average. Conclusions An AI-based templating tool for TKA was successfully developed, demonstrating satisfactory accuracy and efficiency. Its application could significantly reduce the clinical workload in TKA preparation.
Abstract
Background Preoperative templating is an important step for total knee arthroplasty (TKA), facilitating hospital personnel in the anticipation and preparation of necessary surgical resources. Despite its importance, this process currently lacks automation. This study aimed to develop an artificial intelligence (AI) model to automate implant size prediction. Methods A total of 13,281 (2938 anteroposterior, 10,343 lateral) knee radiographs obtained from the authors’ institute were utilized for model training, with 2302 (1034 anteroposterior, 1268 lateral) images set apart for validation and testing. The templating AI model integrates a pipeline composed of multiple steps for automated implant size estimation. To predict implant size, anterioposterior (AP) and lateral radiograph predictions were merged, selecting the smaller of the predicted sizes to prevent implant overhang. The model’s size predictions were validated with 81 real TKA data set apart from the training data, and its accuracy was compared to that of manual templating by an orthopedic specialist. Predictions matching the actual implanted sizes were labeled “exact” and those within one size, “accurate.” The influence of patient characteristics on the model’s prediction accuracy was also analyzed. The measurement time elapsed for implant sizing was recorded for both the AI model and the orthopedic specialist. Implant position predicted by the model was validated by comparing insert locations with postoperative images. Results Compared with data from 81 actual TKA procedures, the model provided exact predictions for 39.5% of femoral and 43.2% of tibial components. Allowing a one-size margin of error, 88.9% of predictions were deemed “accurate” for both components. Interobserver reliability (Cohen’s kappa) were 0.60 and 0.70 for femoral and tibial implants, respectively, both classified as “substantial.” The orthopedic specialist produced results accurate within one-size margin of error in 95.1% and 100% of cases for femoral and tibial components, respectively. Interobserver reliability between the orthopedic specialist and ground truth was 0.76 and 0.8 for femoral and tibial components, respectively. The measurement time per case was 48.7 s for the AI model, compared with 97.5 s for the orthopedic specialist. Compared with postoperative radiographs, predicted implant position had an error of less than 4 mm on average. Conclusions An AI-based templating tool for TKA was successfully developed, demonstrating satisfactory accuracy and efficiency. Its application could significantly reduce the clinical workload in TKA preparation.
참고문헌 (19)
- Klag EA, "Increased accuracy in templating for total knee arthroplasty using 3D models generated from radiographs", J Knee Surg, 36(8), pp.837~842 (2023)[DOI]
- Peek AC, "How useful is templating for total knee replacement component sizing?", Knee, 19(4), pp.266~269 (2012)[DOI]
- Kunze KN, "Validation and performance of a machine-learning derived prediction guide for total knee arthroplasty component sizing", Arch Orthop Trauma Surg, 141(12), pp.2235~2244 (2021)[DOI]
- Kanna R, "Notching is less, if femoral component sagittal positioning is planned perpendicular to distal femur anterior cortex axis, in navigated TKA", Knee Surg Relat Res, 33(1), pp.46~ (2021)[DOI]
- Culler SD, "Comparison of adverse events rates and hospital cost between customized individually made implants and standard off-the-shelf implants for total knee arthroplasty", Arthroplast Today, 3(4), pp.257~263 (2017)[DOI]
- Hsu AR, "Template-directed instrumentation in total knee arthroplasty : cost savings analysis", Orthopedics, 35(11), pp.e1596~e1600 (2012)[DOI]
- Riechelmann F, "Imprecise prediction of implant sizes with preoperative 2D digital templating in total knee arthroplasty", Arch Orthop Trauma Surg, 143(8), pp.4705~4711 (2023)[DOI]
- McLawhorn AS, "Template-directed instrumentation reduces cost and improves efficiency for total knee arthroplasty : an economic decision analysis and pilot study", J Arthroplasty, 30(10), pp.1699~1704 (2015)[DOI]
- Marchand KB, "The accuracy of computed tomography-based, three-dimensional implant planning in robotic-assisted total knee arthroplasty", J Knee Surg, 35(14), pp.1587~1594 (2022)[DOI]
- Seaver T, "Algorithm based automatic templating is less accurate than manual digital templating in total knee arthroplasty", J Orthop Res, 38(7), pp.1472~1476 (2020)[DOI]
- Masse V, "Using standard X-ray images to create 3D digital bone models and patient-matched guides for aiding implant positioning and sizing in total knee arthroplasty", Comput Assist Surg, 26(1), pp.31~40 (2021)[DOI]
- Jo C, "Deep learning-based landmark recognition and angle measurement of full-leg plain radiographs can be adopted to assess lower extremity alignment", Knee Surg Sport Traumatol Arthrosc, 31(4), pp.1388~1397 (2023)[DOI]
- Cao H, "Swin-unet : unet-like pure transformer for medical image segmentation", European conference on computer vision, pp.205~218 (2022), Springer
- Gao ZX, "Comparison of kinematic alignment and mechanical alignment in total knee arthroplasty : a meta-analysis of randomized controlled clinical trials", Orthop Surg, 12(6), pp.1567~1578 (2020)[DOI]
- Geng Z, "Bottom-up human pose estimation via disentangled keypoint regression", Proceedings of the IEEE, 2021, 14676~14686
- Landis JR, "The measurement of observer agreement for categorical data", Biometrics, 33(1), pp.159~174 (1977)
- Blevins JL, "Predicting implant size in total knee arthroplasty using demographic variables", Bone Joint J (2020)[DOI]
- Naylor BH, "Can component size in total knee arthroplasty be predicted preoperatively?-an analysis of patient characteristics", J Knee Surg, 36(9), pp.965~970 (2023)[DOI]
- Pietrzak JRT, "Preoperative CT-based three-dimensional templating in robot-assisted total knee arthroplasty more accurately predicts implant sizes than two-dimensional templating", J Knee Surg, 32(7), pp.642~648 (2019)[DOI]