Medial Scapular Body (MSB) Goutallier Classification - MRI based reliability and validity of evaluation of the Goutallier classification for grading fatty infiltration of the rotator cuff.

INTRODUCTION: The degree of atrophy and fatty infiltration of rotator cuff muscle belly is a key predictor for cuff repairability. Traditionally, Goutallier grading of fatty infiltration is assessed at sagittal scapular Y-view. Massive rotator cuff tears are associated with tendon retraction and medial retraction of cuff musculature, resulting in medialization of the muscle bulk. Thus, standard Y-view can misrepresent the region of interest and may misguide clinicians when assessing repairability. It is hypothesized that by assessing the muscle belly with multiple medial sagittal MRI sections at medial scapular body, the Medial Scapular Body - Goutallier Classification (MSB-GC) will improve reliability and repeatability giving a more representative approximation to the degree of fatty infiltration, as compared with original Y-view. METHODS: Fatty infiltration of the rotator cuff muscles were classified based on the Goutallier grade (0 to 4) at three defined sections section 1: original Y-view; section 2: level of suprascapular notch; section 3: three cm medial to suprascapular notch on MRI scans. Six sub-specialist fellowship trained shoulder surgeons, and three musculoskeletal radiologists independently evaluated deidentified MRI scans of included patients. RESULTS: Out of 80 scans, 78% (n=62) were massive cuff tears involving supraspinatus, infraspinatus and subscapularis tendon. Inter-observer reliability (consistency between observers) for Goutallier grade was excellent for all three predefined sections (range:0.87-0.95). Intra-observer reliability (repeatability) for Goutallier grade was excellent for all three sections and four rotator cuff muscles (range:0.83-0.97). There was a moderate to strong positive correlation of Goutallier grades between sections 1 and 3 and between sections 2 and 3 and these were statistically significant (p<0.001). There was a reduction in the severity of fatty infiltration on the Goutallier classification from sections 1 to 3 across all muscles. 42.5% of both supraspinatus and infraspinatus were downgraded by one, 20% of supraspinatus and 3.8% of infraspinatus were downgraded by 2 and 2.5% of supraspinatus were downgraded by 3. CONCLUSION: This study found that applying the Goutallier classification to more medial MRI sections (MSB-GC) resulted in assignment of lower grades for all rotator cuff muscles. Additionally, this method demonstrated excellent test-retest reliability and repeatability. Inclusion of a more medial view or whole scapula on MRI, especially in advanced levels of tear retraction, could be more reliable and representative for assessment of the degree of fatty infiltration within the muscle bulk that could help predict tear repairability and therefore improve clinical decision-making which should be studied further in clinical studies.

Reinforcement Learning Algorithms and Applications in Healthcare and Robotics: A Comprehensive and Systematic Review.

Reinforcement learning (RL) has emerged as a dynamic and transformative paradigm in artificial intelligence, offering the promise of intelligent decision-making in complex and dynamic environments. This unique feature enables RL to address sequential decision-making problems with simultaneous sampling, evaluation, and feedback. As a result, RL techniques have become suitable candidates for developing powerful solutions in various domains. In this study, we present a comprehensive and systematic review of RL algorithms and applications. This review commences with an exploration of the foundations of RL and proceeds to examine each algorithm in detail, concluding with a comparative analysis of RL algorithms based on several criteria. This review then extends to two key applications of RL: robotics and healthcare. In robotics manipulation, RL enhances precision and adaptability in tasks such as object grasping and autonomous learning. In healthcare, this review turns its focus to the realm of cell growth problems, clarifying how RL has provided a data-driven approach for optimizing the growth of cell cultures and the development of therapeutic solutions. This review offers a comprehensive overview, shedding light on the evolving landscape of RL and its potential in two diverse yet interconnected fields.

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.

N2 reduction to NH3 on surfaces of Co-Al18P18, Ni-Al21N21, Fe-B24N24, Mn-B27P27, Ti-C60 and Cu-Si72 catalysts.

CONTEXT: The abilities of Co-Al18P18, Ni-Al21N21, Fe-B24N24, Mn-B27P27, Ti-C60 and Cu-Si72 as catalysts for N2-RR to create the NH3 are investigated by theoretical levels. The ∆Eadoption and ∆Eformation of Co-Al18P18, Ni-Al21N21, Fe-B24N24, Mn-B27P27, Ti-C60 and Cu-Si72 are investigated. The ∆Eadsorption of N2-RR intermediates and ΔGreaction of reaction steps of N2-RR on Co-Al18P18, Ni-Al21N21, Fe-B24N24, Mn-B27P27, Ti-C60 and Cu-Si72 are examined. In acceptable mechanisms, the *NN → *NNH step is potential limiting step and *NN → *NNH step in enzymatic mechanism is endothermic reaction. The ∆Greaction of *NHNH2 → *NH2NH2 step on Co-Al18P18, Ni-Al21N21, Fe-B24N24, Mn-B27P27, Ti-C60 and Cu-Si72 are -0.904, -0.928, -0.860, -0.882, -0.817 and -0.838 eV, respectively. The Co-Al18P18 and Ni-Al21N21 have the highest ∆Greaction values for reaction steps of N2-RR. Finally, it can be concluded that the Co-Al18P18, Ni-Al21N21, Fe-B24N24 and Mn-B27P2 have acceptable potential for N2-RR by acceptable pathways. METHODS: The structures of Co-Al18P18, Ni-Al21N21, Fe-B24N24, Mn-B27P27, Ti-C60 and Cu-Si72 and N2-RR intermediates are optimized by PW91PW91/6-311+G (2d, 2p) and M06-2X/cc-pVQZ as theoretical levels in GAMESS software. The convergence for force set displacement of Co-Al18P18, Ni-Al21N21, Fe-B24N24, Mn-B27P27, Ti-C60 and Cu-Si72 and N2-RR intermediates are 1.5 × 105 Hartree/Bohr and 6.0 × 10-5 Angstrom. The Opt = Tight and MaxStep = 30 are considered to optimize Co-Al18P18, Ni-Al21N21, Fe-B24N24, Mn-B27P27, Ti-C60 and Cu-Si72 and N2-RR intermediates. The frequencies of Co-Al18P18, Ni-Al21N21, Fe-B24N24, Mn-B27P27, Ti-C60 and Cu-Si72 and N2-RR intermediates are calculated.

Advances in electrochemical-optical dual-mode biosensors for detection of environmental pathogens.

Electrochemical techniques are commonly used to analyze and screen various environmental pathogens. When used in conjunction with other optical recognition methods, it can extend the sensing range, lower the detection limit, and offer mutual validation. Nowadays, electrochemical-optical dual-mode biosensors have ensured the accuracy of test results by integrating two signals into one, indicating their potential use in primary food safety quantitative assays and screening tests. Particularly, visible optical signals from electrochemical/colorimetric dual-mode biosensors could meet the demand for real-time screening of microbial pathogens. While electrochemical-optical dual-mode probes have been receiving increasing attention, there is limited emphasis on the design approaches for sensors intended for microbial pathogens. Here, we review the recent progress in the merging of optical and electrochemical techniques, including fluorescence, colorimetry, surface plasmon resonance (SPR), and surface enhanced Raman spectroscopy (SERS). This study particularly emphasizes the reporting of various sensing performances, including sensing principles, types, cutting-edge design approaches, and applications. Finally, some concerns and upcoming advancements in dual-mode probes are briefly outlined.

Advancing therapeutic efficacy: nanovesicular delivery systems for medicinal plant-based therapeutics.

The utilization of medicinal plant extracts in therapeutics has been hindered by various challenges, including poor bioavailability and stability issues. Nanovesicular delivery systems have emerged as promising tools to overcome these limitations by enhancing the solubility, bioavailability, and targeted delivery of bioactive compounds from medicinal plants. This review explores the applications of nanovesicular delivery systems in antibacterial and anticancer therapeutics using medicinal plant extracts. We provide an overview of the bioactive compounds present in medicinal plants and their therapeutic properties, emphasizing the challenges associated with their utilization. Various types of nanovesicular delivery systems, including liposomes, niosomes, ethosomes, and solid lipid nanoparticles, among others, are discussed in detail, along with their potential applications in combating bacterial infections and cancer. The review highlights specific examples of antibacterial and anticancer activities demonstrated by these delivery systems against a range of pathogens and cancer types. Furthermore, we address the challenges and limitations associated with the scale-up, stability, toxicity, and regulatory considerations of nanovesicular delivery systems. Finally, future perspectives are outlined, focusing on emerging technologies, integration with personalized medicine, and potential collaborations to drive forward research in this field. Overall, this review underscores the potential of nanovesicular delivery systems for enhancing the therapeutic efficacy of medicinal plant extracts in antibacterial and anticancer applications, while identifying avenues for further research and development.

Comprehensive review of deep learning in orthopaedics: Applications, challenges, trustworthiness, and fusion.

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.