Artificial intelligence enables reliable and standardized measurements of implant alignment in long leg radiographs with total knee arthroplasties

Schwarz, Gilbert M.; Simon, Sebastian; Mitterer, Jennyfer A.; Frank, Bernhard J. H.; Aichmair, Alexander; Dominkus, Martin; Hofstaetter, Jochen G.

doi:10.1007/s00167-022-07037-9

Cited by 18 publications

(10 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The equivalence-index (γ) was between 0.54 and 3.03° for angles and − 0.70 to 1.95 mm for lengths. The evaluation of LLRs by LAMA™ after TKA showed a high reproducibility and reliability [21]. Correct detection of femoral and tibial components was achieved in 92.1%.…”

Section: Discussionmentioning

confidence: 83%

“…The software used in this study (LAMA™) is a commercially available FDA- and CE-marked software that has been studied for native LLRs and implant alignment measurement after TKA [ 21 , 23 ]. Simon et al performed a retrospective single-center analysis of 295 native LLRs, where they compared AI measurements with manual readers that constituted a “ground truth” [ 23 ].…”

Section: Discussionmentioning

confidence: 99%

“…The evaluation of LLRs by LAMA™ after TKA showed a high reproducibility and reliability [ 21 ]. Correct detection of femoral and tibial components was achieved in 92.1%.…”

Section: Discussionmentioning

confidence: 99%

“…The American College of Radiology Data Science Institute has recognized leg length measurement in radiographs as an AI use case. Studies for angle measurements on native long-leg radiographs with neutral alignment and postoperatively after total knee arthroplasty (TKA) showed good results compared with manual readers [ 12 , 21 , 23 ].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Artificial intelligence‐based analyses of varus leg alignment and after high tibial osteotomy show high accuracy and reproducibility

Stotter,

Klestil,

Chen

et al. 2023

Knee surg. sports traumatol. arthrosc.

View full text Add to dashboard Cite

Purpose The aim of this study was to investigate the performance of an artificial intelligence (AI)-based software for fully automated analysis of leg alignment pre- and postoperatively after high tibial osteotomy (HTO) on long-leg radiographs (LLRs). Methods Long-leg radiographs of 95 patients with varus malalignment that underwent medial open-wedge HTO were analyzed pre- and postoperatively. Three investigators and an AI software using deep learning algorithms (LAMA™, ImageBiopsy Lab, Vienna, Austria) evaluated the hip–knee–ankle angle (HKA), mechanical axis deviation (MAD), joint line convergence angle (JLCA), medial proximal tibial angle (MPTA), and mechanical lateral distal femoral angle (mLDFA). All measurements were performed twice and the performance of the AI software was compared with individual human readers using a Bayesian mixed model. In addition, the inter-observer intraclass correlation coefficient (ICC) for inter-observer reliability was evaluated by comparing measurements from manual readers. The intra-reader variability for manual measurements and the AI-based software was evaluated using the intra-observer ICC. Results Initial varus malalignment was corrected to slight valgus alignment after HTO. Measured by the AI algorithm and manually HKA (5.36° ± 3.03° and 5.47° ± 2.90° to − 0.70 ± 2.34 and − 0.54 ± 2.31), MAD (19.38 mm ± 11.39 mm and 20.17 mm ± 10.99 mm to − 2.68 ± 8.75 and − 2.10 ± 8.61) and MPTA (86.29° ± 2.42° and 86.08° ± 2.34° to 91.6 ± 3.0 and 91.81 ± 2.54) changed significantly from pre- to postoperative, while JLCA and mLDFA were not altered. The fully automated AI-based analyses showed no significant differences for all measurements compared with manual reads neither in native preoperative radiographs nor postoperatively after HTO. Mean absolute differences between the AI-based software and mean manual observer measurements were 0.5° or less for all measurements. Inter-observer ICCs for manual measurements were good to excellent for all measurements, except for JLCA, which showed moderate inter-observer ICCs. Intra-observer ICCs for manual measurements were excellent for all measurements, except for JLCA and for MPTA postoperatively. For the AI-aided analyses, repeated measurements showed entirely consistent results for all measurements with an intra-observer ICC of 1.0. Conclusions The AI-based software can provide fully automated analyses of native long-leg radiographs in patients with varus malalignment and after HTO with great accuracy and reproducibility and could support clinical workflows. Level of evidence Diagnostic study, Level III.

show abstract

Section: Discussionmentioning

confidence: 83%

Section: Discussionmentioning

confidence: 99%

“…The evaluation of LLRs by LAMA™ after TKA showed a high reproducibility and reliability [ 21 ]. Correct detection of femoral and tibial components was achieved in 92.1%.…”

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Artificial intelligence‐based analyses of varus leg alignment and after high tibial osteotomy show high accuracy and reproducibility

Stotter,

Klestil,

Chen

et al. 2023

Knee surg. sports traumatol. arthrosc.

View full text Add to dashboard Cite

show abstract

“…In another physical sphere it does appear the ability to optimize implant alignment, 23 as well asrobotic rehabilitation training of lower limbs along with synchronizing acupuncture exercise therapy could enhance the hip joint activity function, life quality, and quadriceps muscle group function of elderly postoperative patients with hip fractures. 23 This might be extremely valuable given the generally very low certainty of evidence available for supported discharge and current multidisciplinary home rehabilitation approaches for hip fracture injuries 24 now found to be largely flawed and limited. 25 This needs to be tested more widely and whether this is practical in diverse settings and how the results do compare to traditional practices.…”

Section: Resultsmentioning

confidence: 99%

Artificial intelligence and rehabilitation: what’s new and promising

Marks

2023

IPMRJ

View full text Add to dashboard Cite

The development of artificially intelligent technological machine systems that can integrate large volumes of data, and also ‘learn’ to recognize notable patterns, are currently being widely discussed and employed in various health and other realms. In this regard, what promise do these systems hold for ameliorating the late life chronic disease burden of increasing numbers of adults globally that may stem from one or multiple chronic longstanding health conditions. To explore this issue, a broad exploration of rehabilitation associated artificial intelligence implications was conducted using leading data bases. Results show that there are some active advances in both artificial intelligence and machine learning realms, but not in the context of desirable robust observations in all cases. Much future work is indicated though and is strongly recommended.

show abstract

Inverse kinematic total knee arthroplasty using conventional instrumentation restores constitutional coronal alignment

Keyes,

Russell,

Bertalan

et al. 2024

Knee surg. sports traumatol. arthrosc.

View full text Add to dashboard Cite

PurposeRestricted inverse kinematic alignment (iKA) is a contemporary alignment strategy for total knee arthroplasty (TKA), commonly performed with robotic assistance. While superior clinical results are reported for kinematic‐type alignment strategies, registry data indicate no survivorship benefit for navigation or robotic assistance. This study aimed to determine the efficacy of an instrumented, restricted iKA technique for achieving patient‐specific alignment.MethodsSeventy‐nine patients undergoing 84 TKAs (five bilateral procedures) using an iKA technique were included for preoperative and postoperative lower limb alignment analysis. The mean age was 66.5 (range: 43–82) with 33 male and 51 female patients. Artificial intelligence was employed for radiographic measurements. Alignment profiles were classified using the Coronal Plane Alignment of the Knee (CPAK) system. Preoperative and postoperative alignment profiles were compared with subanalyses for preoperative valgus, neutral and varus profiles.ResultsThe mean joint‐line convergence angle (JLCA) reduced from 2.5° to −0.1° postoperatively. The mean lateral distal femoral angle (LDFA) remained unchanged postoperatively, while the mean medial proximal tibial angle (MPTA) increased by 2.5° (p = 0.001). By preservation of the LDFA and restoration of the MPTA, the mean hip knee ankle angle (HKA) moved through 3.5° varus to 1.2° valgus.The CPAK system was used to visually depict changes in alignment profiles for preoperative valgus, neutral and varus knees; with 63% of patients observing an interval change in classification.ConclusionEncouraged by the latest evidence supporting both conventional instrumentation and kinematic‐type TKA strategies, this study describes how a restricted, conventionally instrumented iKA technique may be utilised to restore constitutional lower limb alignment.Level of EvidenceLevel III.

show abstract

Artificial intelligence enables reliable and standardized measurements of implant alignment in long leg radiographs with total knee arthroplasties

Cited by 18 publications

References 21 publications

Artificial intelligence‐based analyses of varus leg alignment and after high tibial osteotomy show high accuracy and reproducibility

Artificial intelligence‐based analyses of varus leg alignment and after high tibial osteotomy show high accuracy and reproducibility

Artificial intelligence and rehabilitation: what’s new and promising

Inverse kinematic total knee arthroplasty using conventional instrumentation restores constitutional coronal alignment

Contact Info

Product

Resources

About