Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Explainable and clinically audited hybrid self-supervised framework for multi-class DFU classification and mobile

Abdullah Abdullah1,2, Muhammad Ateeb Ather1,2, Zulaikha Fatima3

  • 1Centro de Investigación en Computación (CIC), Instituto Politécnico Nacional (IPN), 07738, Mexico City, Mexico.

Scientific Reports
|June 28, 2026
PubMed
Summary

Related Concept Videos

Force Classification01:22

Force Classification

Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

EvoApneaFormer: an IoT and prognostic evolutionary deep learning-based framework for real-time multi-event sleep apnea disorder detection and remote monitoring.

Frontiers in bioengineering and biotechnology·2026
Same author

A Genomics-Guided Multimodal Contrastive Learning Framework for Clinically Significant Prostate Cancer Risk Stratification with Missing Clinical Data.

Cancers·2026
Same author

Integration of Machine Learning Techniques in ECG-Based Multiclass Arrhythmia Classification with Explainability Analysis.

Biosensors·2026
Same author

An Attention-Enhanced ViT-HLNN Hybrid Ensemble Framework for Multi-Class Gastrointestinal Disease Classification.

Scientific reports·2026
Same author

Olezarsen for Hypertriglyceridemia: A New Therapy Update with Systematic Review and Meta-Analysis.

Cardiology in review·2026
Same author

Demographic Confounding and Model Robustness in the Prognostic Evaluation of NMDAR Encephalitis Glycoprofiles.

Annals of neurology·2026
Same journal

Correction: A method for supervoxel-wise association studies of age and other non-imaging variables from coronary computed tomography angiograms.

Scientific reports·2026
Same journal

Poly(bromophenol blue)/CoSn(OH)<sub>6</sub> cubic particles modified pencil graphite electrode for electrochemical determination of diphenhydramine.

Scientific reports·2026
Same journal

Dietary Chlorella, Spirulina, and acidifier modulate jejunal cytokine-related gene expression in broiler chickens.

Scientific reports·2026
Same journal

Perceived physical activity barriers in university students: associations with fatigue and eating behaviours.

Scientific reports·2026
Same journal

Refuge limitation structures habitat use in agricultural landscapes: evidence from Sunda pangolins.

Scientific reports·2026
Same journal

Lightweight stateless transaction verification with outsourced witness updates for UTXO blockchains.

Scientific reports·2026
See all related articles
This summary is machine-generated.

A new AI framework accurately classifies diabetic foot ulcers (DFUs) using self-supervised learning and image refinement. This technology offers high precision and explainability for improved DFU diagnosis and management.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computer Vision

Background:

  • Diabetic foot ulcers (DFUs) require accurate classification for timely intervention.
  • Existing diagnostic methods may lack precision and explainability.
  • AI offers potential for enhanced DFU screening.

Purpose of the Study:

  • To develop and evaluate a Clinically Audited Hybrid Self-Supervised Framework for DFU classification.
  • To integrate domain-adaptive pretraining, spatial refinement, and classification for multi-class DFU diagnosis.
  • To assess the model's accuracy, explainability, and mobile deployment efficiency.

Main Methods:

  • Utilized SimCLR for self-supervised pretraining on DFU datasets.
  • Employed a U-Net refiner to enhance lesion boundary visibility.
Keywords:
Clinical validationDeep learningDiabetic foot ulcer (DFU)Edge computingEfficientNetExplainable artificial intelligence (XAI)Grad-CAMMobile healthSelf-supervised learning (SSL)SimCLRU-Net

Related Experiment Videos

  • Integrated an EfficientNet-B0 classifier for four-class DFU diagnosis (Normal, Abnormal, Ischemic, Infected).
  • Performed experiments on 24,000 DFU images with rigorous validation and testing splits.

    • Main Results:

    • Achieved high diagnostic performance: 99.98% accuracy, 99.91% precision, 99.92% recall, and 99.93% F1-score.
    • Demonstrated strong explainability with a mean IoU of 0.982 and 87.5% clinical interpretability.
    • Enabled efficient mobile deployment (TensorFlow Lite) with 180 ms/image inference and a ~150 MB app footprint.

    Conclusions:

    • The hybrid self-supervised framework provides high diagnostic precision and clinical interpretability for DFUs.
    • Efficient mobile deployment makes AI-driven DFU screening feasible for telemedicine and homecare.
    • This approach advances the potential of AI in managing diabetic foot complications.