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

PURPOSE: The objective of this study was to develop a numeric tool to automate the analysis of deformity from lower limb telemetry and assess its accuracy. Our hypothesis was that artificial intelligence (AI) algorithm would be able to determine mechanical and anatomical angles to within 1°. METHODS: After institutional review board approval, 1175 anonymized patient telemetries were extracted from a database of more than ten thousand telemetries. From this selection, 31 packs of telemetries were composed and sent to 11 orthopaedic surgeons for analysis. Each surgeon had to identify on the telemetries fourteen landmarks allowing determination of the following four angles: hip-knee-ankle angle (HKA), medial proximal tibial angle (MPTA), lateral distal femoral angle (LDFA), and joint line convergence angle (JLCA). An algorithm based on a machine learning process was trained on our database to automatically determine angles. The reliability of the algorithm was evaluated by calculating the difference of determination precision between the surgeons and the algorithm. RESULTS: The analysis time for obtaining 28 points and 8 angles per image was 48 ± 12 s for the algorithm. The average difference between the angles measured by the surgeons and the algorithm was around 1.9° for all the angles of interest: 1.3° for HKA, 1.6° for MPTA, 2.1° for LDFA, and 2.4° for JLCA. Intraclass correlation was greater than 95% for all angles. CONCLUSION: The algorithm showed high accuracy for automated angle measurement, allowing the estimation of limb frontal alignment to the nearest degree.

Adding a protective K-wire during opening high tibial osteotomy increases lateral hinge resistance to fracture.

PURPOSE: It was hypothesized in this in-vitro study that positioning a K-wire intersecting the cutting plane at the theoretical lateral hinge location would limit the cut depth and help preserve the lateral hinge during the opening of the osteotomy. Objectives were (1) to compare the mechanical resistance of the hinge and the protective effect of leaving the K-wire during the opening procedure (2) to check if the K-wire would limit the depth of the osteotomy. METHODS: An ex-vivo mechanical study, testing 5 pairs of fresh-frozen tibias, was designed. CT-scan based Patient-specific cutting guides were obtained to define the cutting plane and the location of the K-wire at the hinge, using standardized 3D planning protocol. In each pair, OWHTO was performed either with or without the K-wire. To evaluate the hinge's resistance to fracture, the specimens were rigidly fixed at the proximal tibia and a direct load was applied on the free tibial diaphysis to open the osteotomy. The maximum load at breakage, maximum permissible displacement and maximal angulation of the osteotomy before hinge failure was measured. To assess the preservation of an unscathed hinge (protected by the K-wire), the distance from the end of the osteotomy cut to the lateral tibial cortical was measured in mm. RESULTS: The maximum load to hinge breakage in the K-wires PsCG knees compared to the control group (48.3 N vs 5.5 N, p = 0.004), the maximum permissible displacement (19.8 mm vs 7.5 mm, p = 0.005) and the maximal angulation of the osteotomy before hinge breakage (9.9° vs 2.9°, p = 0.002) were all statistically superior in the K-wires PsCG knees compared to the control group. A mean distance of 10 ± 1 mm between cut-bone (saw-print) and lateral hinge cortical bone was found post-performing the osteotomy and the hinge failing. CONCLUSION: The maximum load to breakage and the maximum permissible displacement were, respectively, 880% and 260% higher during the opening of the OWHTO in using K-wires compared to the non-K-wire control group. This confirms the mechanical advantage of using a K-wire for both stabilization and protecting the Hinge during OWHTO. This comparative cadaveric study shows an improvement of the lateral hinges resistance to failing during the opening of the osteotomy. This can be achieved by the placement of a K-wire intersecting the cutting plane at the theoretical location of the lateral hinge.

Articular-surface-based automatic anatomical coordinate systems for the knee bones.

Increasing use of patient-specific surgical procedures in orthopaedics means that patient-specific anatomical coordinate systems (ACSs) need to be determined. For knee bones, automatic algorithms constructing ACSs exist and are assumed to be more reliable than manual methods, although both approaches are based on non-unique numerical reconstructions of true bone geometries. Furthermore, determining the best algorithms is difficult, as algorithms are evaluated on different datasets. Thus, in this study, we developed 3 algorithms, each with 3 variants, and compared them with 5 from the literature on a dataset comprising 24 lower-limb CT-scans. To evaluate algorithms' sensitivity to the operator-dependent reconstruction procedure, the tibia, patella and femur of each CT-scan were each reconstructed once by three different operators. Our algorithms use principal inertia axis (PIA), cross-sectional area, surface normal orientations and curvature data to identify the bone region underneath articular surfaces (ASs). Then geometric primitives are fitted to ASs, and the ACSs are constructed from the geometric primitive points and/or axes. For each bone type, the algorithm displaying the least inter-operator variability is identified. The best femur algorithm fits a cylinder to posterior condyle ASs and a sphere to the femoral head, average axis deviations: 0.12°, position differences: 0.20 mm. The best patella algorithm identifies the AS PIAs, average axis deviations: 0.91°, position differences: 0.19 mm. The best tibia algorithm finds the ankle AS center and the 1st PIA of a layer around a plane fitted to condyle ASs, average axis deviations: 0.38°, position differences: 0.27 mm.

Are three-dimensional patient-specific cutting guides for open wedge high tibial osteotomy accurate? An in vitro study.

BACKGROUND: The aim of this in vitro study was to assess the accuracy of three-dimensional patient-specific cutting guides for open wedge high tibial osteotomy (OWHTO) to provide the planned correction in both frontal and sagittal planes. METHODS: Ten cadaveric tibias underwent OWHTO performed using a patient-specific cutting guide based on 3D preoperative planning. An initial CT scan of the tibias was performed, and after segmentation, 3D geometrical models of the pre-OWHTO tibias were obtained. Reference planes were defined, and OWHTO virtually planned to then design patient-specific cutting guides. OWHTO were performed using the patient-specific cutting guides. The patient-specific cutting guide controls the cut and the correction of the OWHTO in both planes. 3D models of post-OWHTO tibias were created after a postoperative CT scan. Geometrical post-OWHTO 3D models were superimposed on pre-OWHTO 3D models. Mechanical medial proximal tibial angle (mMPTA) in the frontal plane and posterior tibial slope (PTS) in the sagittal plane were compared between planned-OWHTO and post-OWHTO 3D reconstructions relative to the pre-OWHTO reference planes and axis. Pearson's and Lin's correlation tests were performed to assess precision and accuracy of patient-specific cutting guides. RESULTS: The mean difference between post-OWHTO and planned-OWHTO was 0.2° (max 0.5°, SD 0.3°) in the frontal plane and - 0.1° (max 0.8°, SD 0.5°) in the sagittal plane. Statistically significant correlations were found between the planned-OWHTO and post-OWHTO configurations for the mMPTA (p < 0.0001) and PTS (p < 0.0001) measurements, and the bias correction factor was 0.99 in both planes. CONCLUSIONS: 3D patient-specific cutting guides for OWHTO-based 3D virtual planning is a reliable and accurate method of achieving multiplanar correction in both frontal and sagittal planes.