Deep learning (DL) in orthopaedics has gained significant attention in recent years. Previous studies have shown that DL can be applied to a wide variety of orthopaedic tasks, including fracture detection, bone tumour diagnosis, implant recognition, and evaluation of osteoarthritis severity. The utilisation of DL is expected to increase, owing to its ability to present accurate diagnoses more efficiently than traditional methods in many scenarios. This reduces the time and cost of diagnosis for patients and orthopaedic surgeons. To our knowledge, no exclusive study has comprehensively reviewed all aspects of DL currently used in orthopaedic practice. This review addresses this knowledge gap using articles from Science Direct, Scopus, IEEE Xplore, and Web of Science between 2017 and 2023. The authors begin with the motivation for using DL in orthopaedics, including its ability to enhance diagnosis and treatment planning. The review then covers various applications of DL in orthopaedics, including fracture detection, detection of supraspinatus tears using MRI, osteoarthritis, prediction of types of arthroplasty implants, bone age assessment, and detection of joint-specific soft tissue disease. We also examine the challenges for implementing DL in orthopaedics, including the scarcity of data to train DL and the lack of interpretability, as well as possible solutions to these common pitfalls. Our work highlights the requirements to achieve trustworthiness in the outcomes generated by DL, including the need for accuracy, explainability, and fairness in the DL models. We pay particular attention to fusion techniques as one of the ways to increase trustworthiness, which have also been used to address the common multimodality in orthopaedics. Finally, we have reviewed the approval requirements set forth by the US Food and Drug Administration to enable the use of DL applications. As such, we aim to have this review function as a guide for researchers to develop a reliable DL application for orthopaedic tasks from scratch for use in the market.

Total shoulder arthroplasty (TSA) has been the gold standard of care for end-stage glenohumeral arthritis. Outcomes are varied and have been affected by both patient and implant characteristics. Patient factors, such as age, preoperative diagnosis, and preoperative glenoid morphology, can affect the outcomes after TSA. Similarly, the different glenoid and humeral component designs significantly affect the survivorship of TSA. Significant evolution has occurred in the design of the glenoid component with the aim of decreasing the glenoid-sided causes of failure in TSA. On the other hand, focus on the humeral component has been increasing as well, with a trend towards using shorter humeral stems. This article aims to look at the outcomes of TSA as affected by the various patient characteristics and design options for the glenoid and the humeral components. This review also aims to compare survivorship data from global literature and the Australian joint replacement registry, and to provide insights on the implant combination that may provide the best patient outcome.

Revision shoulder arthroplasty is increasing with the number of primary shoulder replacements rising globally. Complex primary and revisions of shoulder arthroplasties pose specific challenges for the surgeon, which must be addressed preoperatively and intraoperatively. This article aimed to present strategies for the management of revision of shoulder arthroplasties through a single-stage approach. Preoperatively, patient factors, such as age, comorbidities, and bone quality, should be considered. The use of planning software can aid in accurately evaluating implants in situ and predict bony anatomy that will remain after explantation during the revision surgery. The planning from such software can then be executed with the help of mixed reality technology to allow accurate implant placement. Single-stage revision is performed in two steps (debridement as first step, implantation and reconstruction as the second step), guided by the following principles: adequate debridement while preserving key soft tissue attachments (i.e., rotator cuff, pectoralis major, latissimus dorsi, deltoid), restoration of glenoid joint line using bone grafting, restoration of humeral length, reconstruction and/or reattachment of soft tissues, and strict compliance with the postoperative antibiotic regimen. Preliminary results of single-stage revision shoulder arthroplasty show improvement in patient outcomes (mean 1 year), successful treatment of infection for those diagnosed with periprosthetic joint infection, and improved cost–benefit parameters for the healthcare system.

Primary glenohumeral osteoarthritis in young patients poses challenging treatment decisions. Arthroplasty options have different failure profiles and implant survivorship patterns. This registry study aims to analyze the cumulative per cent revision rate (CPR) of different types of arthroplasties conducted for primary osteoarthritis in patients under 55 years of age. This comparative observational national registry study included all shoulder arthroplasty for osteoarthritis in patients under 55 years of age undertaken between January 1^st, 2005, and December 31^st, 2022. Partial hemi resurfacing and hemi stemless procedures were excluded. The cumulative percentage of revision (CPR) was determined using Kaplan-Meier estimates of survivorship and hazard ratios (HR) from Cox proportional hazard models adjusted for gender. Reasons for revision of each type of arthroplasty and cumulative incidence of revision diagnoses were analyzed. 2111 primary shoulder arthroplasties were compared. Glenoid erosion is the predominant cause of revision for humeral resurfacing (29.8%) and hemiarthroplasty (35.5%). Instability is the predominant cause of revision for stemmed anatomic total shoulder arthroplasty (ATSA) and reverse total shoulder arthroplasty (RTSA), while loosening is the predominant cause of revision for stemless ATSA. The 6-year CPR is 12.8% for humeral resurfacing (HRA), 14.1% for hemiarthroplasty (HA), 12.4% for stemmed (ATSA), 7.0% for stemless ATSA, and 6.5% for (RTSA). Stemmed ATSA had a higher revision rate than RTSA (entire period HR=2.04 (95% confidence interval (CI) 1.16, 3.57), p=0.012). In contrast, the revision rate of stemless ATSA was not different from RTSA (HR =1.05 (95% CI 0.51, 2.19), p=0.889). Males outnumber females for all shoulder arthroplasty categories. RTSA and stemless ATSA are viable options in young patients with primary osteoarthritis. Their short-to medium-term revision rates are comparable to those of older patients and lower than those associated with HRA, HA, and stemmed ATSA. In the predominantly male patient population under the age of 55, reverse shoulder arthroplasty and stemless ATSA have a lower short-term revision risk than stemmed ATSA.

Background: Component positioning affects clinical outcomes of reverse shoulder arthroplasty, which necessitates an implantation technique that is reproducible, consistent, and reliable. This study aims to assess the accuracy and precision of positioning the humeral component in planned retroversion using a forearm referencing guide. Methods: Computed tomography scans of 54 patients (27 males and 27 females) who underwent primary reverse shoulder arthroplasty for osteoarthritis or cuff tear arthropathy were evaluated. A standardized surgical technique was used to place the humeral stem in 15 degrees of retroversion. Version was assessed intraoperatively visualizing the retroversion guide from above and referencing the forearm axis. Metal subtraction techniques from postoperative computed tomography images allowed for the generation of 3D models of the humerus and for evaluation of the humeral component position. Anatomical humeral plane and implant planes were defined and the retroversion 3D angle between identified planes was recorded for each patient. Accuracy and precision were assessed. A subgroup analysis evaluated differences between male and female patients. Results: The humeral retroversion angle ranged from 0.9 degrees to 22.8 degrees. The majority (81%) of the measurements were less than 15 degrees. Mean retroversion angle (+/- SD) was 9.9 degrees +/- 5.8 degrees (95% CI 8.4 degrees-11.5 degrees) with a mean percent error with respect to 15 degrees of -34% +/- 38 (95% CI -23 to -44). In the male subgroup (n = 27, range 3.8 degrees-22.5 degrees), the mean retroversion angle was 11.9 degrees +/- 5.4 degrees (95% CI 9.8 degrees-14.1 degrees) with a mean percent error with respect to 15 degrees of - 21% +/- 36 (95% CI -6 to - 35). In the female subgroup (n = 27, range 0.9 degrees -22.8 degrees ), mean retroversion angle was 8.0 degrees +/- 5.5 degrees (95% CI 5.8 degrees -10.1 degrees ) and the mean percent error with respect to 15 degrees was - 47% +/- 36 (95% CI -32 to - 61). The differences between the 2 gender groups were statistically significant ( P = .006). Conclusion: Referencing the forearm using an extramedullary forearm referencing system to position the humeral stem in a desired retroversion is neither accurate nor precise. There is a nonnegligible tendency to achieve a lower retroversion than planned, and the error is more marked in females. Level of evidence: Level II; Study of a Diagnostic Test (c) 2023 The Author(s). This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).

Surgically repairing rotator cuff tears with a higher extent of fatty infiltration is controversial. Current evidence supports performing rotator cuff repair in patients exhibiting Goutallier stage 3-4 fatty infiltration. However, the presence of retraction complicates accurate assessment using the Goutallier Classification, particularly on the lateral Y-view. A shift towards classifying fatty infiltration in more medial regions may enhance the precision of tissue quality quantification. The objective of this study was to analyze the uniformity of fatty infiltration within the entire supraspinatus muscle using the Goutallier Classification across three scapular Y-view sections and to examine the association between Goutallier grade, tangent sign, and modified Patte stage. A retrospective evaluation was conducted on preoperative magnetic resonance imaging (MRI) scans from a consecutive series of 97 patients who had previously undergone arthroscopic rotator cuff repairs. Three supraspinatus sections on the MRI sagittal plane were identified: the lateral Y-view (section one), a medial section at the suprascapular notch anatomical landmark (section two), and a section 3 cm medial from the suprascapular notch Medial Scapular Body (section three). Goutallier grade, tangent sign, and modified Patte stage were used to evaluate fatty infiltration, muscle atrophy, and tendon retraction, respectively. Section one had the highest Goutallier grade, while section three had the lowest. Intra-observer rest retest reliability analysis showed excellent consistency in all sections with section one (ICC=0.920, 95% CI), section two (ICC=0.917, 95% CI), and section three (ICC=0.923, 95% CI) for Goutallier grade. Inter-observer reliability analysis also revealed excellent consistency in sections one (ICC=0.951, 95% CI), section two (ICC=0.949, 95% CI), and section three (ICC=0.922, 95% CI) for Goutallier grade. A strong correlation was observed between Goutallier grade and modified Patte stage (τb=0.43-0.56, p=0.001), and between Goutallier grade and tangent sign (τb=0.43-0.54, p=0.001) across all sections. The severity of fatty infiltration within the supraspinatus muscle belly is inconsistent, with the lateral portion being the most severe and the medial portion the least severe. Goutallier grade demonstrates a strong correlation with tangent sign and modified Patte stage. This suggests that tendon retraction results in a potential overestimation in the amount of fatty infiltration defining some tears unjustly irreparable when measuring at the traditionally described lateral Y-view position compared with 3cm medial.