Real-time diabetic foot ulcer classification based on deep learning &amp; parallel hardware computational tools

Fadhel, Mohammed A.; Alzubaidi, Laith; Gu, Yuantong; Santamaría, Jose; Duan, Ye

doi:10.1007/s11042-024-18304-x

Cited by 5 publications

(1 citation statement)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, DL algorithms require a large dataset to improve the learning efficiency of a specific task [ 11 , 12 ]. This limits the utilisation of DL power in medical imaging applications when a large dataset is unavailable.…”

Section: Introductionmentioning

confidence: 99%

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

Alzubaidi,

Salhi,

A.Fadhel

et al. 2024

PLoS ONE

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionmentioning

confidence: 99%

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

Alzubaidi,

Salhi,

A.Fadhel

et al. 2024

PLoS ONE

Self Cite

View full text Add to dashboard Cite

show abstract

Navigating the metaverse: unraveling the impact of artificial intelligence—a comprehensive review and gap analysis

Fadhel,

Duhaim,

Albahri

et al. 2024

Artif Intell Rev

View full text Add to dashboard Cite

In response to the burgeoning interest in the Metaverse—a virtual reality-driven immersive digital world—this study delves into the pivotal role of AI in shaping its functionalities and elevating user engagement. Focused on recent advancements, prevailing challenges, and potential future developments, our research draws from a comprehensive analysis grounded in meticulous methodology. The study, informed by credible sources including SD, Scopus, IEEE, and WoS, encompasses 846 retrieved studies. Through a rigorous selection process, 54 research papers were identified as relevant, forming the basis for a specific taxonomy of AI in the Metaverse. Our examination spans diverse dimensions of the Metaverse, encompassing augmented reality, virtual reality, mixed reality, Blockchain, Agent Systems, Intelligent NPCs, Societal and Educational Impact, HCI and Systems Design, and Technical Aspects. Emphasizing the necessity of adopting trustworthy AI in the Metaverse, our findings underscore its potential to enhance user experience, safeguard privacy, and promote responsible technology use. This paper not only sheds light on the scholarly interest in the Metaverse but also explores its impact on human behavior, education, societal norms, and community dynamics. Serving as a foundation for future development and responsible implementation of the Metaverse concept, our research identifies and addresses seven open issues, providing indispensable insights for subsequent studies on the integration of AI in the Metaverse.

show abstract

DFootNet: A Domain Adaptive Classification Framework for Diabetic Foot Ulcers Using Dense Neural Network Architecture

Bansal,

Vidyarthi

2024

Cogn Comput

View full text Add to dashboard Cite

Real-time diabetic foot ulcer classification based on deep learning & parallel hardware computational tools

Cited by 5 publications

References 29 publications

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

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

Navigating the metaverse: unraveling the impact of artificial intelligence—a comprehensive review and gap analysis

DFootNet: A Domain Adaptive Classification Framework for Diabetic Foot Ulcers Using Dense Neural Network Architecture

Contact Info

Product

Resources

About