Role of Critical Shoulder Angle in Degenerative Type Rotator Cuff Tears: A Turkish Cohort Study.

BACKGROUND This retrospective study investigated the association between the critical shoulder angle (CSA) and the development of full-thickness rotator cuff tears (FTRCTs) in the Turkish population. The CSA is an imaging parameter that quantifies the relationship between the inclination of the glenoid and the lateral extension of the acromion in the coronal plane. The CSA is an anatomical measurement, and higher CSA values have been associated with an increased incidence of FTRCTs. However, there is a lack of data on CSA regarding the Turkish population. MATERIAL AND METHODS In this study, CSA measurements were recorded in 2 groups: 50 patients with FTRCT who had arthroscopic repair (group 1) and 50 age- and sex-matched individuals with no FTRCT detected by magnetic resonance imaging (group 2). Sex, age, affected side, dominant side, and smoking status were recorded for each patient. The CSA measurements of the affected sides were performed on true anterior-posterior view radiographs. RESULTS The results showed a statistically significant difference between the mean CSA values of group 1 (37.48°) and group 2 (33.53°), P<0.001. CSA values of 36 and above had a sensitivity of 73.58%, specificity of 74.47%, positive predictive value of 75%, and negative predictive value of 74.47% for detecting FTRCT. CONCLUSIONS CSA measurement on radiographs is a useful diagnostic tool in the Turkish population, and an above-average CSA value is associated with a significantly increased incidence of degenerative-type FTRCT.

Comparison study of the MRI shoulder PROPELLER technique with differential image quality by variation of shoulder coils.

INTRODUCTION: Motion and pulsation artifacts are the most prominent types of artifacts in Magnetic Resonance Imaging (MRI) of the shoulder. Therefore, this study examined the Periodically Rotating Overlapping Parallel Lines with Enhanced Reconstruction (PROPELLER) technique with small flex coil (SFC) and dedicated shoulder coil (DSC) for the reduction of motion and pulsation artifacts. The signalto- noise ratio (SNR) and contrast-to-noise ratio (CNR) of the standard proton density fat saturation (PDFS) pulse sequence and the PROPELLER proton density fat saturation (PROPELLER PDFS) pulse sequence were also evaluated. MATERIALS AND METHODS: Eighteen (18) participants who met the inclusion and exclusion criteria were scanned using a standard non-contrast MRI shoulder protocol including the PDFS pulse sequence and the PROPELLER PDFS pulse sequence using a small flex coil and a dedicated shoulder coil. Two experienced musculoskeletal (MSK) radiologists evaluated and graded the presence of artifacts on the MR images and the SNR and CNR were measured quantitatively. RESULTS: The non-parametric Wilcoxon Signed Rank test revealed a significant reduction in motion and pulsation artifacts between the PROPELLER PDFS pulse sequence and the standard PDFS pulse sequence. In addition, the nonparametric Mann-Whitney U test revealed that the mean rank of SNR for the standard sequence was statistically significant when compared to the PROPELLER sequence for both coil types. The CNR of the PROPELLER sequence was statistically significant between fat-fluid, bone-fluid, bonetendon, bone-muscle, and muscle-fluid when using SFC and DSC. CONCLUSION: This study proved that the PROPELLER-PDFS pulse sequence effectively eliminates motion and pulsation artifacts, regardless of the coils utilised. The PROPELLERPDFS pulse sequence can therefore be implemented into the standard MRI shoulder procedure.

Differences in Osseous Shoulder Morphology, Scapulothoracic Orientation, and Muscle Volume in Patients With Constitutional Static Posterior Shoulder Instability (Type C1) Compared With Healthy Controls.

BACKGROUND: Constitutional static posterior humeral decentering (type C1 according to ABC Classification) has been recognized as a pre-osteoarthritic deformity that may lead to early-onset posterior decentering osteoarthritis at a young age. Therefore, it is important to identify possible associations of this pathologic shoulder condition to find more effective treatment options. PURPOSE: To perform a comprehensive analysis of all parameters reported to be associated with a C1 shoulder-including the osseous shoulder morphology, scapulothoracic orientation, and the muscle volume of the shoulder girdle in a single patient cohort. STUDY DESIGN: Cross-sectional study; Level of evidence, 3. METHODS: A retrospective, comparative study was conducted analyzing 17 C1 shoulders in 10 patients who underwent magnetic resonance imaging (MRI) with the complete depiction of the trunk from the base of the skull to the iliac crest, including both humeri. The mean age of the patients was 33.5 years, and all patients were men. To measure and compare the osseous shoulder morphology (glenoid version, glenoid offset, humeral torsion, anterior acromial coverage, posterior acromial coverage, posterior acromial height, and posterior acromial tilt) and scapulothoracic orientation (scapular protraction, scapular internal rotation, scapular upward rotation, scapular translation, scapular tilt, and thoracic kyphosis), these patients were matched 1 to 4 according their age, sex, and affected side with shoulder-healthy patients who had received positron emission tomography (PET)-computed tomography. To measure and compare the muscle volume of the shoulder girdle (subscapularis, infraspinatus/teres minor, supraspinatus, trapezius, deltoid, latissimus dorsi/teres major, pectoralis major, and pectoralis minor), patients were matched 1 to 2 with patients who had received PET-MRI. Patients with visible pathologies of the upper extremities were excluded. RESULTS: The C1 group had a significantly higher glenoid retroversion, increased anterior glenoid offset, reduced humeral retrotorsion, increased anterior acromial coverage, reduced posterior acromial coverage, increased posterior acromial height, and increased posterior acromial tilt compared with controls (P < .05). Decreased humeral retrotorsion showed significant correlation with higher glenoid retroversion (r = -0.742; P < .001) and higher anterior glenoid offset (r = -0.757; P < .001). Significant differences were found regarding less scapular upward rotation, less scapular tilt, and less thoracic kyphosis in the C1 group (P < .05). The muscle volume of the trapezius and deltoid was significantly higher in the C1 group (P < .05). CONCLUSION: Patients with C1 shoulders differ from healthy controls regarding osseous scapular and humeral morphology, scapulothoracic orientation, and shoulder girdle muscle distribution. These differences may be crucial in understanding the delicate balance of glenohumeral centering.

Trustworthy deep learning framework for the detection of abnormalities in X-ray shoulder images.

Musculoskeletal conditions affect an estimated 1.7 billion people worldwide, causing intense pain and disability. These conditions lead to 30 million emergency room visits yearly, and the numbers are only increasing. However, diagnosing musculoskeletal issues can be challenging, especially in emergencies where quick decisions are necessary. Deep learning (DL) has shown promise in various medical applications. However, previous methods had poor performance and a lack of transparency in detecting shoulder abnormalities on X-ray images due to a lack of training data and better representation of features. This often resulted in overfitting, poor generalisation, and potential bias in decision-making. To address these issues, a new trustworthy DL framework has been proposed to detect shoulder abnormalities (such as fractures, deformities, and arthritis) using X-ray images. The framework consists of two parts: same-domain transfer learning (TL) to mitigate imageNet mismatch and feature fusion to reduce error rates and improve trust in the final result. Same-domain TL involves training pre-trained models on a large number of labelled X-ray images from various body parts and fine-tuning them on the target dataset of shoulder X-ray images. Feature fusion combines the extracted features with seven DL models to train several ML classifiers. The proposed framework achieved an excellent accuracy rate of 99.2%, F1Score of 99.2%, and Cohen's kappa of 98.5%. Furthermore, the accuracy of the results was validated using three visualisation tools, including gradient-based class activation heat map (Grad CAM), activation visualisation, and locally interpretable model-independent explanations (LIME). The proposed framework outperformed previous DL methods and three orthopaedic surgeons invited to classify the test set, who obtained an average accuracy of 79.1%. The proposed framework has proven effective and robust, improving generalisation and increasing trust in the final results.

Posterior deltoid-sparing approach for displaced inferior or posterior glenoid fossa fractures: technical note and case series.

Scapular surgery has usually been performed through the posterior Judet approach. This approach allows access to the entire posterior scapular body, but causes significant soft tissue damage and detaches the deltoid muscle. To date, there has been no clinical study of a deltoid-preserving approach to access the joint for displaced postero-inferior glenoid fractures (Ideberg type II or Ib). We describe an easy and less invasive approach to the postero-inferior glenoid fossa.

Prospective Comparison of Standard and Deep Learning-reconstructed Turbo Spin-Echo MRI of the Shoulder.

Background Deep learning (DL)-based MRI reconstructions can reduce imaging times for turbo spin-echo (TSE) examinations. However, studies that prospectively use DL-based reconstructions of rapidly acquired, undersampled MRI in the shoulder are lacking. Purpose To compare the acquisition time, image quality, and diagnostic confidence of DL-reconstructed TSE (TSEDL) with standard TSE in patients indicated for shoulder MRI. Materials and Methods This prospective single-center study included consecutive adult patients with various shoulder abnormalities who were clinically referred for shoulder MRI between February and March 2023. Each participant underwent standard TSE MRI (proton density- and T1-weighted imaging; conventional TSE sequence was used as reference for comparison), followed by a prospectively undersampled accelerated TSEDL examination. Six musculoskeletal radiologists evaluated images using a four-point Likert scale (1, poor; 4, excellent) for overall image quality, perceived signal-to-noise ratio, sharpness, artifacts, and diagnostic confidence. The frequency of major pathologic features and acquisition times were also compared between the acquisition protocols. The intergroup comparisons were performed using the Wilcoxon signed rank test. Results Overall, 135 shoulders in 133 participants were evaluated (mean age, 47.9 years ± 17.1 [SD]; 73 female participants). The median acquisition time of the TSEDL protocol was lower than that of the standard TSE protocol (288 seconds [IQR, 288-288 seconds] vs 926 seconds [IQR, 926-950 seconds], respectively; P < .001), achieving a 69% lower acquisition time. TSEDL images were given higher scores for overall image quality, perceived signal-to-noise ratio, and artifacts (all P < .001). Similar frequency of pathologic features (P = .48 to > .99), sharpness (P = .06), or diagnostic confidence (P = .05) were noted between images from the two protocols. Conclusion In a clinical setting, TSEDL led to reduced examination time and higher image quality with similar diagnostic confidence compared with standard TSE MRI in the shoulder. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Chang and Chow in this issue.

Diagnostic Implications of Ultrasound Evaluation in Patients With Shoulder Impingement Syndrome.

OBJECTIVE: To evaluate the diagnostic value of musculoskeletal ultrasound measurements of subacromial bursa (SAB) thickness, supraspinatus tendon (SUP) thickness, acromiohumeral distance (AHD), and SUP-to-AHD ratio (AHD%) in patients with shoulder impingement syndrome (SIS). METHODS: This was a prospective cross-sectional observational study. Thirty patients with SIS (60 shoulders) admitted between January 2019 and January 2020 were enrolled. The SUP thickness, SAB thickness, AHD, and AHD% (calculated as AHD% = [(SUP / AHD) × 100%]) were measured in 60 shoulders using musculoskeletal ultrasound. RESULTS: The affected shoulder displayed thicker SUP and SAB (t = 7.838), narrower AHD (t = 2.324), and larger AHD% (t = 6.875) than the unaffected shoulder (P < .05). The SUP thickness showed a linear positive correlation with AHD (r = .503) and AHD% (r = .792) in the affected shoulder (P < .05). On receiver operating characteristic analysis, AHD*AHD% showed the best diagnostic performance in both measurements (area under the curve: 0.877). CONCLUSION: This study revealed that SIS symptoms may be related to a larger AHD% with SUP thickening. As diagnostic criteria, the cut-off values of AHD% (65.6%) and AHD*AHD% (0.504) have good sensitivity and specificity and can help improve the differential diagnosis of patients with SIS.

Magnetic Resonance Imaging of the Shoulder: Interpretation of Common Orthopaedic Injuries.

Magnetic resonance imaging (MRI) is frequently obtained to assess for pathology in the setting of shoulder pain and dysfunction. MRI of the shoulder provides diagnostic information that helps optimize patient management and surgical planning. Both general and subspecialized orthopaedic surgeons routinely order and review shoulder MRIs in practice. Therefore, familiarity with the MRI appearance of common shoulder pathologies is important. This document reviews the most common shoulder pathologies using a standardized MRI interpretative approach. Instructional videos demonstrating a musculoskeletal radiologist interpreting normal and abnormal shoulder MRIs are also provided.

Preliminary exploration of deep learning-assisted recognition of superior labrum anterior and posterior lesions in shoulder MR arthrography.

PURPOSE: MR arthrography (MRA) is the most accurate method for preoperatively diagnosing superior labrum anterior-posterior (SLAP) lesions, but diagnostic results can vary considerably due to factors such as experience. In this study, deep learning was used to facilitate the preliminary identification of SLAP lesions and compared with radiologists of different seniority. METHODS: MRA data from 636 patients were retrospectively collected, and all patients were classified as having/not having SLAP lesions according to shoulder arthroscopy. The SLAP-Net model was built and tested on 514 patients (dataset 1) and independently tested on data from two other MRI devices (122 patients, dataset 2). Manual diagnosis was performed by three radiologists with different seniority levels and compared with SLAP-Net outputs. Model performance was evaluated by the receiver operating characteristic (ROC) curve, area under the ROC curve (AUC), etc. McNemar's test was used to compare performance among models and between radiologists' models. The intraclass correlation coefficient (ICC) was used to assess the radiologists' reliability. p < 0.05 was considered statistically significant. RESULTS: SLAP-Net had AUC = 0.98 and accuracy = 0.96 for classification in dataset 1 and AUC = 0.92 and accuracy = 0.85 in dataset 2. In dataset 1, SLAP-Net had diagnostic performance similar to that of senior radiologists (p = 0.055) but higher than that of early- and mid-career radiologists (p = 0.025 and 0.011). In dataset 2, SLAP-Net had similar diagnostic performance to radiologists of all three seniority levels (p = 0.468, 0.289, and 0.495, respectively). CONCLUSIONS: Deep learning can be used to identify SLAP lesions upon initial MR arthrography examination. SLAP-Net performs comparably to senior radiologists.

Imaging in an academic orthopedic shoulder service: a report on incidental lung pathology findings.

INTRODUCTION: Computed tomography (CT) is often utilized for both diagnostic and pre-operative planning purposes in shoulder arthroplasty. Our study reports on the incidence of pulmonary findings in our pre-operative shoulder arthroplasty population over 14 years at our institution. METHODS: We conducted a retrospective review of all "shoulder CT" exams ordered by two orthopedic upper extremity surgeons between the years of 2008 and 2021. These exams were then further analyzed to include only those ordered for the purpose of pre-operative "shoulder arthroplasty" planning. All incidental findings were documented and those with pulmonary findings were then further analyzed. A detailed chart review was then performed on these patients to determine the impact on their planned shoulder arthroplasty. RESULTS: A total of 363 shoulder pre-operative CTs were ordered by our two upper extremity orthopedic surgeons at our institution between the years of 2008 and 2021. Primary lung cancer in the form of adenocarcinoma (n = 3) had an incidence of 0.8% of all CT scans and 1.4% of all pulmonary incidental findings. Fifteen patients (4% of all CT scans and 7% of all pulmonary incidental findings) had no concern for malignancy and were appropriately evaluated with further imaging based on their initial shoulder CT. CONCLUSION: While shoulder arthroplasty and pre-operative planning with CT imaging continue to become more common, so too is the incidence of reported pulmonary findings. From a patient care standpoint, it is important that these findings are accurately identified, appropriately triaged, and communicated clearly to our patients.

Shoulder structures and strength in competitive preadolescent swimmers: A longitudinal ultrasonographic study.

BACKGROUND: Repetitive shoulder movements during competitive training may cause changes in the strength of periarticular shoulder structures in preadolescent swimmers. OBJECTIVE: To prospectively determine the effects of training on shoulder periarticular structures and muscle strength in preadolescent swimmers. DESIGN: Prospective cohort study. SETTING: Community-based natatorium. PARTICIPANTS: Twenty-four preadolescent swimmers aged 10-12 years. INTERVENTIONS: Not applicable. MAIN OUTCOME MEASURES: Measurements were repeated in three periods as preseason, midseason, and postseason. Ultrasonographic measurements (supraspinatus tendon thickness, humeral head cartilage thickness, deltoid muscle thickness, and acromiohumeral distance) were performed using a portable device and a linear probe. Shoulder (flexion, extension, abduction, internal and external rotation) and back (serratus anterior, lower, and middle trapezius) isometric muscle strength were measured with a handheld dynamometer. RESULTS: Supraspinatus tendon thickness and acromiohumeral distance were similar in all periods (all p > .05); however, deltoid muscle and humeral head cartilage thicknesses increased throughout the season (p = .002, p = .008, respectively). Likewise, whereas shoulder muscle strength increased (all p < .05), back muscle strength was similar in all periods (all p > .05). CONCLUSIONS: In preadolescent swimmers, acromiohumeral distance and supraspinatus tendon thickness seem to not change; but humeral head cartilage and deltoid muscle thicknesses as well as shoulder muscle strength increase throughout the season.

[Shoulder-clinical introduction]. / Schultergelenk ­ klinische Einführung.

BACKGROUND: Radiological imaging plays a significant role in the diagnostics of shoulder pathologies. Based on a patient's medical history, physical examination and radiological imaging, it is possible to plan the further conservative or surgical treatment. OBJECTIVES: Common pathologies of the shoulder and the correct radiological imaging are presented. CONCLUSIONS: A rational and targeted use of radiological imaging, together with the medical history and physical examination allows correct diagnosis of pathologies of the shoulder joint.

SSR white paper: guidelines for utilization and performance of direct MR arthrography.

OBJECTIVE: Direct magnetic resonance arthrography (dMRA) is often considered the most accurate imaging modality for the evaluation of intra-articular structures, but utilization and performance vary widely without consensus. The purpose of this white paper is to develop consensus recommendations on behalf of the Society of Skeletal Radiology (SSR) based on published literature and expert opinion. MATERIALS AND METHODS: The Standards and Guidelines Committee of the SSR identified guidelines for utilization and performance of dMRA as an important topic for study and invited all SSR members with expertise and interest to volunteer for the white paper panel. This panel was tasked with determining an outline, reviewing the relevant literature, preparing a written document summarizing the issues and controversies, and providing recommendations. RESULTS: Twelve SSR members with expertise in dMRA formed the ad hoc white paper authorship committee. The published literature on dMRA was reviewed and summarized, focusing on clinical indications, technical considerations, safety, imaging protocols, complications, controversies, and gaps in knowledge. Recommendations for the utilization and performance of dMRA in the shoulder, elbow, wrist, hip, knee, and ankle/foot regions were developed in group consensus. CONCLUSION: Although direct MR arthrography has been previously used for a wide variety of clinical indications, the authorship panel recommends more selective application of this minimally invasive procedure. At present, direct MR arthrography remains an important procedure in the armamentarium of the musculoskeletal radiologist and is especially valuable when conventional MRI is indeterminant or results are discrepant with clinical evaluation.

[Pathologies of the shoulder joint : Anatomy and examination techniques]. / Pathologien des Schultergelenks : Anatomie und Untersuchungstechniken.

CLINICAL ISSUE: The movements and stability of the human shoulder are a complex dynamic interaction between several joints, muscles and ligaments, which on the one hand enable extensive mobility and on the other hand must provide the necessary stability. Furthermore, the complexity of the shoulder is increased by a large number of normal variants. This article aims to explain the relevant anatomical structures and the radiological examination techniques necessary to visualize them. STANDARD RADIOLOGICAL PROCEDURES: Various modalities contribute to the examination of the shoulder. These include X­rays, computed tomography (CT), magnetic resonance imaging (MRI) and ultrasound. METHODOLOGICAL INNOVATION: It is important to use the various procedures appropriately. Especially with MRI arthrography, it is necessary to pay attention to suitable sequences and possibly additional examination positions. PRACTICAL RECOMMENDATION: The multimodal examination of the shoulder can contribute to the diagnosis of numerous clinical pictures. Anatomical and methodological foundations are essential for this.

Can We Control Lateral Shoulder Balance Through Proximal Thoracic Curve Correction in Lenke Type 2 Adolescent Idiopathic Scoliosis?

BACKGROUND: Proximal thoracic curve (PTC) correction has been considered to prevent lateral shoulder imbalance in Lenke Type 2 adolescent idiopathic scoliosis (AIS) patients; however, postoperative shoulder imbalance (PSI) commonly occurs despite these strategies with PTC correction. We investigated the hypothesis that PTC correction would not directly affect PSI in the majority of Lenke type 2 AIS cases. Furthermore, we investigated the risk factors for lateral PSI after corrective surgery. METHODS: This study examined the records for AIS patients with Lenke type 2 who underwent corrective surgery and followed up for >2 years. Patients were categorized into PSI (-); radiologic shoulder height (RSH)<15 mm, and PSI (+); RSH≥15 mm. Repeated measures analysis of variance was performed at preoperatively, postoperatively, 1 month, and final follow-up. Postoperative lateral shoulder imbalance was predicted by the identification of univariate analysis and multivariate analysis. RESULTS: Among the 151 patients reviewed, 29 (19.2%) showed PSI at final follow-up. Lateral shoulder balance parameters showed different directionalities between PSI (-) and (+) groups at postoperatively, 1 month, and final follow-up ( P <0.01 each). Preoperative PTC, middle thoracic curve (MTC) curve and MTC correction showed strong correlations with the RSH ( P =0.01, 0.03, and 0.04, respectively). However, PTC correction did not show a significant correlation with the RSH. Moreover, only a smaller MTC curve and larger MTC correction rate were related to lateral PSI in multivariate analysis. CONCLUSIONS: In Lenke type 2 AIS curves, the MTC curve and its correction predominantly influence lateral shoulder imbalance after corrective surgery, irrespective of the PTC correction extent. Consequently, overemphasizing the correction of the PTC curve may not necessarily lead to an improved lateral shoulder balance. When MTC curve is smaller, surgeons should be more careful for MCT overcorrection leading to a lateral shoulder imbalance. LEVEL OF EVIDENCE: Level III.

Quantifying changes in shoulder orientation between the prone and supine positions from magnetic resonance imaging.

BACKGROUND: Predicting breast tissue motion using biomechanical models can provide navigational guidance during breast cancer treatment procedures. These models typically do not account for changes in posture between procedures. Difference in shoulder position can alter the shape of the pectoral muscles and breast. A greater understanding of the differences in the shoulder orientation between prone and supine could improve the accuracy of breast biomechanical models. METHODS: 19 landmarks were placed on the sternum, clavicle, scapula, and humerus of the shoulder girdle in prone and supine breast MRIs (N = 10). These landmarks were used in an optimization framework to fit subject-specific skeletal models and compare joint angles of the shoulder girdle between these positions. FINDINGS: The mean Euclidean distance between joint locations from the fitted skeletal model and the manually identified joint locations was 15.7 mm ± 2.7 mm. Significant differences were observed between prone and supine. Compared to supine position, the shoulder girdle in the prone position had the lateral end of the clavicle in more anterior translation (i.e., scapula more protracted) (P < 0.05), the scapula in more protraction (P < 0.01), the scapula in more upward rotation (associated with humerus elevation) (P < 0.05); and the humerus more elevated (P < 0.05) for both the left and right sides. INTERPRETATION: Shoulder girdle orientation was found to be different between prone and supine. These differences would affect the shape of multiple pectoral muscles, which would affect breast shape and the accuracy of biomechanical models.

Multi-Task Learning U-Net for Functional Shoulder Sub-Task Segmentation.

The assessment of a frozen shoulder (FS) is critical for evaluating outcomes and medical treatment. Analysis of functional shoulder sub-tasks provides more crucial information, but current manual labeling methods are time-consuming and prone to errors. To address this challenge, we propose a deep multi-task learning (MTL) U-Net to provide an automatic and reliable functional shoulder sub-task segmentation (STS) tool for clinical evaluation in FS. The proposed approach contains the main task of STS and the auxiliary task of transition point detection (TPD). For the main STS task, a U-Net architecture including an encoder-decoder with skip connection is presented to perform shoulder sub-task classification for each time point. The auxiliary TPD task uses lightweight convolutional neural networks architecture to detect the boundary between shoulder sub-tasks. A shared structure is implemented between two tasks and their objective functions of them are optimized jointly. The fine-grained transition-related information from the auxiliary TPD task is expected to help the main STS task better detect boundaries between functional shoulder sub-tasks. We conduct the experiments using wearable inertial measurement units to record 815 shoulder task sequences collected from 20 healthy subjects and 43 patients with FS. The experimental results present that the deep MTL U-Net can achieve superior performance compared to using single-task models. It shows the effectiveness of the proposed method for functional shoulder STS. The code has been made publicly available at https://github.com/RobinChu9890/MTL-U-Net-for-Functional-Shoulder-STS.Clinical Relevance- This work provides an automatic and reliable functional shoulder sub-task segmentation tool for clinical evaluation in frozen shoulder.

Automated Shoulder Implant Manufacturer Detection using Encoder Decoder based Classifier from X-ray Images.

Total shoulder arthroplasty is the process of replacing the damaged ball and socket joint in the shoulder with a prosthesis made with polyethylene and metal components. The prosthesis helps to restore the normal range of motion and reduce pain, enabling the patient to return to their daily activities. These implants may need to be replaced over the years due to damage or wear and tear. It is a tedious and time-consuming process to identify the type of implant if medical records are not properly maintained. Artificial intelligence systems can speed up the treatment process by classifying the manufacturer and model of the prosthesis. We have proposed an encoder-decoder based classifier along with the supervised contrastive loss function that can identify the implant manufacturer effectively with increased accuracy of 92% from X-ray images overcoming the class imbalance problem.