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

Villeneuve, Florent Bernard de; Jacquet, Christophe; Kadim, Bilal El; Donnez, Mathias; Coué, Olivier; Poujade, Thibault; Khakha, Raghbir; Argenson, Jean-Noël; Grasso, Francesco

doi:10.1007/s00264-022-05634-4

Cited by 5 publications

(2 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There was no significant difference in the accuracy in determining the mLDFA, MPTA and correction angle using the Miniaci method. The study published by Bernard De Villeneuve et al in 2023 [3] also describes good inter‐ and intraobserver agreement in the analysis of long‐leg standing radiographs. These studies, among others, highlight the value of manual preoperative planning to assess the appropriate correction.…”

Section: Discussionmentioning

confidence: 96%

‘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

Charre,

An,

Khakha

et al. 2024

Knee surg. sports traumatol. arthrosc.

Self Cite

View full text Add to dashboard Cite

PurposeThe 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).MethodsThis 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.ResultsA 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.ConclusionPlanning 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 EvidenceLevel Ⅲ, retrospective cross‐sectional study.

show abstract

Section: Discussionmentioning

confidence: 96%

‘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

Charre,

An,

Khakha

et al. 2024

Knee surg. sports traumatol. arthrosc.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Today, we have different software tools that allow us to measure medical images more easily, quickly, precisely, and accurately, with less intra-and inter-observer variability. There are even systems based on artificial intelligence which can automatically detect anatomical references on X-rays to establish determined angular measurements [21][22][23][24][25][26][27]. These advances in angle information management have not always been accompanied by the validation of accuracy and reliability, with few exceptions [28][29][30][31][32].…”

Section: Introductionmentioning

confidence: 99%

The Validity and Absolute Reliability of Lower Extremity Angle Values on Full-Leg Standing Radiographs Using the TraumaMeter Software

León-Muñoz,

Hurtado-Avilés,

Moya-Angeler

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

To establish classifications and to obtain pre- and post-operative information on patient-specific alignments, it is necessary to measure different angular values accurately and precisely, mainly on weight-bearing, full-length anteroposterior X-rays of the lower limbs (LLRs). This study evaluated angular measurements’ validity and absolute reliability on LLRs with a self-developed, computer-aided measurement system (TraumaMeter v.873). Eight independent observers measured the preoperative mechanical hip-knee-ankle (mHKA) angle of 52 lower extremities (26 cases) in a blinded fashion on three occasions separated by two weeks. We obtained an intra-observer mean bias error (MBE) of 0.40°, a standard deviation (SD) of 0.11°, and a 95% confidence interval (CI) of 0.37°–0.43°. We also obtained an inter-observer MBE of 0.49°, an SD of 0.15°, and a 95% C of 0.45°–0.53°. The intra-observer MBE for the measurement pair between the second and the first measurement round (T2T1) was 0.43°, the SD was 0.13°, and the 95% CI was 0.39°–0.47°; the MBE between the third and the second round (T3T2) was 0.37°, with an SD of 0.10° and a 95% CI of 0.34°–0.40°; and the MBE between the third and the first round (T3T1) was 0.40°, with an SD of 0.10° and a 95% CI of 0.37°–0.43°. The interobserver MBE for the first round of measurements was 0.52°, with an SD of 0.16° and a 95% CI of 0.48°–0.56°; the MBE for the second round was 0.50°, with an SD of 0.15° and a 95% CI of 0.46°–0.54°; and the MBE for the third round was 0.46°, with an SD of 0.14° and a 95% CI of 0.42°–0.50°. There were no statistically significant differences in the inter-observer errors for the three tests. In the case of the intra-observer analysis, there were differences between T2T1 and between T3T2, but these differences were minimal, with no overlaps in the lower or upper values, respectively, of the confidence intervals. These results led us to conclude that the TraumaMeter v.873 software extension for measuring lower-limb angles in LLRs is an accurate tool with low intra- and inter-observer variability.

show abstract

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

Salzmann,

Hassan Tarek,

Prill

et al. 2024

Knee surg. sports traumatol. arthrosc.

View full text Add to dashboard Cite

PurposeThe 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.MethodsThe 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.ResultsA 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.ConclusionAI‐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 EvidenceLevel I.

show abstract

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

Cited by 5 publications

References 25 publications

‘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

‘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

The Validity and Absolute Reliability of Lower Extremity Angle Values on Full-Leg Standing Radiographs Using the TraumaMeter Software

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

Contact Info

Product

Resources

About