Search

Abstract Background Hip dysplasia is a condition where the acetabulum is too shallow to support the femoral head and is commonly considered a risk factor for hip osteoarthritis. The objective of this study was to develop a deep learning model to diagnose hip dysplasia from plain radiographs and classify dysplastic hips based on their severity. Methods We collected pelvic radiographs of 571 patients from two single-center cohorts and one multicenter cohort. The radiographs were split in half to create hip radiographs (n = 1022). One orthopaedic surgeon and one resident assessed the radiographs for hip dysplasia on either side. We used the center edge (CE) angle as the primary diagnostic criteria. Hips with a CE angle 25° were labeled as dysplastic, borderline, and normal, respectively. The dysplastic hips were also classified with both Crowe and Hartofilakidis classification of dysplasia. The dataset was divided into train, validation, and test subsets using 80:10:10 split-ratio that were used to train two deep learning models to classify images into normal, borderline and (1) Crowe grade 1–4 or (2) Hartofilakidis grade 1–3. A pre-trained on Imagenet VGG16 convolutional neural network (CNN) was utilized by performing layer-wise fine-turning. Results Both models struggled with distinguishing between normal and borderline hips. However, achieved high accuracy (Model 1: 92.2% and Model 2: 83.3%) in distinguishing between normal/borderline vs. dysplastic hips. The overall accuracy of Model 1 was 68% and for Model 2 73.5%. Most misclassifications for the Crowe and Hartofilakidis classifications were +/- 1 class from the correct class. Conclusions This pilot study shows promising results that a deep learning model distinguish between normal and dysplastic hips with high accuracy. Future research and external validation are warranted regarding the ability of deep learning models to perform complex tasks such as identifying and classifying disorders using plain radiographs. Level of Evidence Diagnostic level IV

Abstract Background BASHTI is an implant-less anterior cruciate ligament (ACL) reconstruction technique, which resolves the problems caused by implants such as interference screws. This study aims to investigate the effect of the drill bit and tendon’s diameter on the Core Bone Engaged Length (CBEL) and the fixation strength. CBEL is the length of core bone which has a full engagement with both tunnel and graft at the same time. Methods 60 in-vitro tests were conducted for 6, 7, 8, and 9 mm tendon sizes with a 10 mm bone tunnel. In this study bovine tendons and dummy bone blocks were used to model the fixation. Drill bits were used to extract the core bone for securing the auto-graft. A three-stage tensile test including a force-controlled cyclical preloading of 10–50 N with a frequency of 0.1 Hz for 10 cycles, followed by the main force-controlled cyclical loading of 50–200 N with a frequency of 0.5 Hz for 150 cycles, and immediately a displacement-controlled single cycle pull-out load with a rate of 20 mm/min were carried out to discover the fixation strength of each sample. Results The 6 mm group had the greatest CBEL. However, all cases in this group failed in loadings below 200 N, which is the minimum required strength after ACL reconstruction. The fixation strength of cases with more than 200 N fixation strength for 7, 8, and 9 mm tendon diameters were 275 ± 42, 330 ± 110, and 348 ± 93 N, respectively, showing insignificant difference between groups (P-value = 0.45). Nevertheless, CBELs for these groups were 16.6 ± 3.4, 9.6 ± 2.4, and 11.7 ± 3.8 mm, respectively, implying a significant increase in CBEL in the 7 mm group than that for 8 and 9 mm groups (P-value = 0.002 and 0.049, respectively). Conclusion Results showed that CBEL could assess the quality of BASHTI technique. However, CBEL was an inverse function of tendon compression, so it was not an independent parameter to determine BASHTI strength. Also, the CBEL of 7 mm group which fulfilled the 200 N threshold was higher than that of 8 and 9 mm groups, so its healing process speed may be higher, which is recommended for a future study in this field.

Highlights Developing an organic implant-less technique which has numerous clinical advantages Comparing this novel technique with interference screw technique Implementing synthetic Sawbones blocks to have a controlled study Selecting the best fixation condition for this novel technique