An artificial intelligence based on a convolutional neural network allows a precise analysis of the alignment of the lower limb

Artificial intelligence-based assessment of leg axis parameters shows excellent agreement with human raters: A systematic review and meta-analysis

PURPOSE

The aim of this study was to conduct a systematic review and meta-analysis on the reliability and applicability of artificial intelligence (AI)-based analysis of leg axis parameters. We hypothesized that AI-based leg axis measurements would be less time-consuming and as accurate as those performed by human raters.

METHODS

The study protocol was registered with the International Prospective Register of Systematic Reviews (PROSPERO). PubMed, Epistemonikos, and Web of Science were searched up to 24 February 2024, using a BOOLEAN search strategy. Titles and abstracts of identified records were screened through a stepwise process. Data extraction and quality assessment of the included papers were followed by a frequentist meta-analysis employing a common effect/random effects model with inverse variance and the Sidik-Jonkman heterogeneity estimator.

RESULTS

A total of 13 studies encompassing 3192 patients were included in this meta-analysis. All studies compared AI-based leg axis measurements on long-leg radiographs (LLR) with those performed by human raters. The parameters hip knee ankle angle (HKA), mechanical lateral distal femoral angle (mLDFA), mechanical medial proximal tibial angle (mMPTA), and joint-line convergence angle (JLCA) showed excellent agreement between AI and human raters. The AI system was approximately 3 min faster in reading standing long-leg anteroposterior radiographs (LLRs) compared with human raters.

CONCLUSION

AI-based assessment of leg axis parameters is an efficient, accurate, and time-saving procedure. The quality of AI-based assessment of the investigated parameters does not appear to be affected by the presence of implants or pathological conditions.

LEVEL OF EVIDENCE

Level I.

'One millimetre equals one degree' is a major source of inaccuracy in planning osteotomies around the knee for metaphyseal deformities compared to the digital planning

PURPOSE

The objective of this study was to compare the accuracy of virtually performed osteotomies around the knee. The comparison was made between the Miniaci method (method 1), considered the gold standard planning, with the widely held dogma that one degree of correction required equates to one millimetre of opening/closing (method 2).

METHODS

This retrospective cross-sectional study was conducted between December 2018 and September 2022 in patients aged at least 15 years with metaphyseal knee deformity. Osteotomy planning was performed in methods 1 and 2 utilising calibrated long-leg alignment X-rays in the frontal plane. In both methods, the desired correction was defined by the Fujisawa point. The error % in measurement (ratio method 1/method 2) and the difference in millimetres (method 1 - method 2) between the two methods were analysed.

RESULTS

A total of 107 osteotomies with 27 (25.2%) distal femoral osteotomies, 54 (50.5%) proximal tibial osteotomies and 26 (24.3%) double-level osteotomies were performed virtually with a mean hip-knee-ankle angle of 176.4 ± 6.6. In distal femur osteotomy, the mean error % between methods 1 and 2 was 38.9 ± 16.7% and 22.4 ± 16.8% for the opening and closing groups, respectively. In proximal tibial osteotomies, the mean error % was 22.7 ± 15.6% and 9 ± 10.8% for the opening and closing groups, respectively. In double-level osteotomy, the mean error % of femur-based corrections was 34.9 ± 19% and 19.5 ± 21% for the opening and closing groups, respectively, and the mean error of the tibial-based corrections was 26.4 ± 12.1% for the opening group and 10.8 ± 10% for the closing group, respectively.

CONCLUSION

Planning one millimeter per degree of desired correction for osteotomies around the knee in metaphyseal deformities is a major source of error when compared with digital planning using the Miniaci method. This was seen most frequently with osteotomies of the distal femur and all opening wedge osteotomies.

LEVEL OF EVIDENCE

Level Ⅲ, retrospective cross-sectional study.