Publications

Summary: Artificial intelligence is a booming area of research, with great potential for clinical implementation. One of the key limitations of artificial intelligence models is their propensity to be“confidently incorrect”. Furthermore, depending on how the model is designed, it can be very difficult to understand how a model generates an “confidently incorrect”result. This is particularly relevant in a clinical context, where mistakes may have serious repercussions for patients. This study explores ways in which AI models can be better designed and assessed, in order to understand how they generate the results that they do. This is particularly important, as it sheds light on ways to create more reliable AI models for clinical practice.  

Abstract: 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 onX-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 trustworthyDL framework has been proposed to detect shoulder abnormalities (such asfractures, deformities, and arthritis) using X-ray images. The framework consists of two parts: same-domain transfer learning (TL) tomitigate imageNet mismatch and feature fusion to reduce error rates and improve trust in the final result. Same-domain TL involves training pre-trained modelson 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 out performed 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.

Abstract: The purpose of this study was to evaluate the clinical and radiographic outcomes of an all-arthroscopic rotator cuff repair technique involving muscle advancement and double-layer lasso loop (DLLL) repair for massive, retracted posterosuperior cuff tears. 

Methods: This is a retrospective case series of patients with massive, retracted posterosuperior cuff tears who underwent the all-arthroscopic muscle advancement technique from March 2017 to September 2021, with minimum follow-up of 12 months. Key steps included suprascapular nerve release, advancement of supraspinatus and infraspinatus muscles, and DLLL repair. Pre-operative and post-operative visual analogue scale for pain, American Shoulder and Elbow Surgeons (ASES) score, Constant score, University of California Los Angeles (UCLA) shoulder score, active range of motion (ROM), and strength were compared. Preoperative and postoperative structural radiological characteristics were analysed.

Results: Forty-three shoulders in 38 patients were evaluated with mean follow-up of 18.8 months (range 12-55 months). Of the 43 shoulders, 4 repairs failed (9.3% re-tear rate). VAS, ASES, Constant, and UCLA scores significantly improved (p<0.001) in patients who demonstrated healing on postoperative MRI(n=39). ASES, Constant, and UCLA scores were significantly better in the healed group, with 100% exceeding MCIDs for ASES and UCLA scores, and 84.2% for Constant score. A lower proportion of patients in the re-tear group achieved MCIDs. Active ROM in all planes significantly improved for those who had healed repairs. (p<0.001). Relative strengths of abduction, supraspinatus, and infraspinatus were at least 90% of the contralateral side. Recovery rate of pseudoparalysis (7 patients) was 100%. 

Conclusion: All-arthroscopic muscle advancement, coupled with double-layer lasso loop repair, leads to a high healing rate with excellent clinical outcome. 

Abstract: A protocol is proposed to acquire a tomographic ultrasound(US) scan of the musculoskeletal (MSK) anatomy in the rotator cuff region.Current clinical US imaging techniques are hindered by occlusions and a narrow field of view and require expert acquisition and interpretation. There is limited literature on 3D US image registration of the shoulder or volumetric reconstruction of the full shoulder complex. We believe that a clinically accurate US volume reconstruction of the entire shoulder can aid in pre-operative surgical planning and reduce the complexity of US interpretation.  

The protocol was used in generating data for deep learning model training to automatically register US mosaics in real-time. An in vivo 3D US tomographic reconstruction of the entire rotator cuff region was produced by registering 53 sequential 3D US volumes acquired by an MSK sonographer. Anatomical surface thicknesses and distances in the US mosaic were compared to their corresponding MRI measurements as the ground truth.
 
The humeral head surface was marginally thicker in there constructed US mosaic than its original thickness observed in a single US volume by 0.65 mm. The humeral head diameter and acromiohumeral distance (ACHD) matched with their measured MRI distances with a reconstruction error of 0 mm and 1.2 mm, respectively. Furthermore, the demonstration of 20 relevant MSK structures was independently graded between 1 and 5 by two sonographers, with higher grades indicating poorer demonstration. The average demonstration grade for each anatomy was as follows: bones = 2, muscles = 3, tendons = 3, ligaments= 4–5 and labrum = 4–5.

There was a substantial agreement between sonographers (Cohen’s Weighted kappa of 0.71) on the demonstration of the structures, and they both independently deemed the mosaic clinically acceptable for the visualisation of the bony anatomy. Ligaments and the labrum were poorly observed due to anatomy size, location and inaccessibility in a static scan, and artefact build-up from the registration and compounding approaches.

‍Background: The accuracy of human pose tracking using a smartphone camera (2D-pose) to quantify shoulder range of motion (RoM) is not determined.  

Methods: Twenty healthy individuals were recruited and performed shoulder abduction, adduction, flexion, or extension, captured simultaneously using a smartphone-based human pose estimation algorithm(Apple’s vision framework) and using a skin marker-based 3D motion capture system. Validity was assessed by comparing the 2D-pose outcomes against a well-established 3D motion capture protocol. In addition, the impact of iPhone positioning was investigated using three smartphones in multiple vertical and horizontal positions. The relationship and validity were analysed using linear mixed models and Bland-Altman analysis.  

Results: We found that 2D-pose-based shoulder RoM was consistent with 3D motion capture (linear mixed model: R2 > 0.93) but was somewhat overestimated by the smartphone. Differences were dependent on shoulder movement type and RoM amplitude, with adduction the worst performer among all tested movements. All motion types were described using linear equations. Correction methods are provided to correct potential out-of-plane shoulder movements.  

Conclusions: Shoulder RoM estimated using a smartphone camera is consistent with 3D motion-capture-derived RoM; however, differences between the systems were observed and are likely explained by differences in thoracic frame definitions.

‍

 

‍

‍

‍

‍

‍

‍