J Shanghai Jiaotong Univ Sci

Journal of Shanghai Jiaotong University(Science) >

2026 , Vol. 31 >Issue 3: 622 - 630

DOI: https://doi.org/10.1007/s12204-026-2937-6

Celebrating 30 Years

Accuracy of AI-Assisted Preoperative Templating in Total Hip Arthroplasty: A Comparison Between Anteroposterior Pelvic Radiographs and Robotic Advanced X-Ray Machine-Acquired Long-Leg Radiographs

Expand
  • 1. Department of Orthopaedics, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200011, China; 2. Department of General Medicine, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200011, China; 3. Yingwei Medical Technology (Shanghai) Co., Ltd., Shanghai 201103, China

Received date: 2026-03-23

  Revised date: 2026-04-28

  Accepted date: 2026-04-29

  Online published: 2026-06-11

Fold

Abstract

To investigate the prosthesis prediction accuracy of an artificial intelligence (AI)-assisted preoperative planning system, this study compared standard anteroposterior (AP) pelvic radiographs with long-leg radiographs (LLRs) acquired by a robotic advanced X-ray (RAX) system (Multitom Rax). A total of 29 patients (29 hips) undergoing primary total hip arthroplasty (THA) were retrospectively analyzed, excluding those with severe structural anomalies such as Crowe type IV developmental dysplasia of the hip. Preoperative planning was performed using the “Cuantian” AI system across four groups: AP pelvic radiographs with and without calibration markers, and RAX-acquired LLRs with and without calibration markers. The actual implanted component sizes recorded in intraoperative logs served as the standard. The results demonstrated that for AP pelvic radiographs, the inclusion of calibration markers was associated with improved prediction accuracy, achieving a 100% compliance rate compared with 51.7%–82.8% without calibration. Conversely, RAX-acquired LLRs maintained a 100% compliance rate and higher perfect-match rates (72.4%–75.9% for femoral stems; 55.2%–58.6% for acetabular cups) in this cohort. Regardless of the imaging modality employed, femoral stem size prediction remained consistently more accurate than acetabular cup prediction. The 300 cm source-to-image distance of the RAX system may reduce magnification distortion, making it a potentially useful imaging option for 2D planning in THA. For primary hospitals without access to RAX imaging, standard AP pelvic radiographs with calibration markers remain a more economical and pragmatic choice. The AI-assisted workflow may provide standardized support for preoperative templating, although further validation in larger and more anatomically diverse cohorts is still required.

Cite this article

Liao Jiabo, Xu Yufan, Wang Yicang, Ding Huan, Xie Kai, Jiang Xu, Li Xing, Wang Liao, Yan Mengning . Accuracy of AI-Assisted Preoperative Templating in Total Hip Arthroplasty: A Comparison Between Anteroposterior Pelvic Radiographs and Robotic Advanced X-Ray Machine-Acquired Long-Leg Radiographs[J]. Journal of Shanghai Jiaotong University(Science), 2026 , 31(3) : 622 -630 . DOI: 10.1007/s12204-026-2937-6

References

[1] Colombi A, Schena D, Castelli C C. Total hip arthroplasty planning [J]. EFORT Open Reviews, 2019, 4(11): 626-632.
[2] Bian YY, Cheng KY, Chang X, et al. Preliminary statistics and analysis of hip and knee arthroplasty surgical volume in China from 2011 to 2019 [J]. Chinese Journal of Orthopaedics, 2020, 40(21): 1453-1460. (in Chinese)
[3] Huang J, Zhu Y, Ma W X, et al. A novel method for accurate preoperative templating for total hip arthroplasty using a biplanar digital radiographic (EOS) system [J]. JBJS Open Access, 2020, 5(4): e20.00078.
[4] Ezzet K A, McCauley J C. Use of intraoperative X-rays to optimize component position and leg length during total hip arthroplasty [J]. The Journal of Arthroplasty, 2014, 29(3): 580-585.
[5] Murphy W S, Yun H H, Hayden B, et al. The safe zone range for cup anteversion is narrower than for inclination in THA [J]. Clinical Orthopaedics & Related Research, 2018, 476(2): 325-335.
[6] Wang J, Li H W, Yang P, et al. Expert consensus on the technical process for preoperative three-dimensional planning of total hip arthroplasty using a dual fluoroscopic imaging system (2024 version) [J]. Journal of Medical Biomechanics, 2024, 39(6): 1016-1025 (in Chinese).
[7] Shi X T, Li C F, Cheng C M, et al. Preoperative planning for total hip arthroplasty for neglected developmental dysplasia of the hip [J]. Orthopaedic Surgery, 2019, 11(3): 348-355.
[8] Holzer L A, Scholler G, Wagner S, et al. The accuracy of digital templating in uncemented total hip arthroplasty [J]. Archives of Orthopaedic and Trauma Surgery, 2019, 139(2): 263-268.
[9] Attwood J, Banks P, Sidhom A, et al. Preoperative templating for total hip arthroplasty: A method for calibrating digital radiographs using patient demographics and anthropometric measurements [J]. Cureus, 2023, 15(10): e47668.
[10] Shichman I, Factor S, Shaked O, et al. Effects of surgeon experience and patient characteristics on accuracy of digital pre-operative planning in total hip arthroplasty [J]. International Orthopaedics, 2020, 44(10): 1951-1956.
[11] Sariali E, Mauprivez R, Khiami F, et al. Accuracy of the preoperative planning for cementless total hip arthroplasty. A randomised comparison between three-dimensional computerised planning and conventional templating [J]. Orthopaedics & Traumatology: Surgery & Research, 2012, 98(2): 151-158.
[12] Hassani H, Cherix S, Ek E T, et al. Comparisons of preoperative three-dimensional planning and surgical reconstruction in primary cementless total hip arthroplasty [J]. The Journal of Arthroplasty, 2014, 29(6): 1273-1277.
[13] Osmani F A, Thakkar S, Ramme A, et al. Variance in predicted cup size by 2-dimensional vs 3-dimensional computerized tomography–based templating in primary total hip arthroplasty [J]. Arthroplasty Today, 2017, 3(4): 289-293.
[14] Ben-Ari E, Shichman I, Sissman E, et al. Calibration of magnification in two-dimensional low-dose full-body imaging for preoperative planning of total hip arthroplasty [J]. Archives of Orthopaedic and Trauma Surgery, 2023, 143(11): 6875-6881.
[15] Efe T, El Zayat B F, Heyse T J, et al. Precision of preoperative digital templating in total hip arthroplasty [J]. Acta Orthopaedica Belgica, 2011, 77(5): 616-621.
[16] Wiese K R, Kock F W, Blake C A, et al. The accuracy of pre-operative digital templating in total hip arthroplasty performed in a low-volume, resource-constrained orthopaedic unit [J]. SA Orthopaedic Journal, 2020, 19(1): 28-32.
[17] Fontalis A, Berry D J, Shimmin A, et al. Prevention of early complications following total hip replacement [J]. Sicot-J, 2021, 7: 61.
[18] Davila J A, Kransdorf M J, Duffy G P. Surgical planning of total hip arthroplasty: Accuracy of computer-assisted EndoMap software in predicting component size [J]. Skeletal Radiology, 2006, 35(6): 390-393.
[19] Shaarani S R, McHugh G, Collins D A. Accuracy of digital preoperative templating in 100 consecutive uncemented total hip arthroplasties a single surgeon series [J]. The Journal of Arthroplasty, 2013, 28(2): 331-337.
[20] Grunz J P, Pennig L, Fieber T, et al. Twin robotic X-ray system in small bone and joint trauma: Impact of cone-beam computed tomography on treatment decisions [J]. European Radiology, 2021, 31(6): 3600-3609.
[21] Chen X, Liu X Y, Wang Y O, et al. Development and validation of an artificial intelligence preoperative planning system for total hip arthroplasty [J]. Frontiers in Medicine, 2022, 9: 841202.
[22] Huo J B, Huang G X, Han D, et al. Value of 3D preoperative planning for primary total hip arthroplasty based on artificial intelligence technology [J]. Journal of Orthopaedic Surgery and Research, 2021, 16(1): 156.

Options
Outlines

/

〈 〉