Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Diabetic Foot Ulcer

Diabetic Foot Ulcer

Definition A diabetic foot ulcer (DFU) is a chronic, non-healing wound that develops in individuals with diabetes. It typically occurs on pressure-bearing areas such as the heel, metatarsal heads, or hallux, and carries a high risk of infection and amputation.Pathophysiology • The development of DFUs can be explained by four interconnected mechanisms: neuropathy, ischemia, infection, and impaired wound healing. • Neuropathy is the most common factor. Sensory neuropathy reduces pain perception,...

You might also read

Related Articles

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

Sort by

Same author

Sources and characteristics of water and methanol soluble brown carbon over a megacity: Insights from EEM-PARAFAC approach.

Environmental pollution (Barking, Essex : 1987)·2026

Same author

Interpretable hybrid deep learning model for Parkinson's disease screening using hand-drawn spiral and waveform images.

Polish journal of radiology·2026

Same author

Effectiveness and Safety of Saroglitazar in Patients With Metabolic Disease in India Stratified by Estimated Glomerular Filtration Rate (eGFR): A Retrospective, Observational, Electronic Medical Record (EMR)-Based Real-World Evidence Study.

Cureus·2026

Same author

Health Prediction Using Hybrid Deep Learning Models: A Transparent and Interpretable Approach.

The International journal of health planning and management·2026

Same author

A lightweight and explainable cardiac signal framework for screening-oriented cardiometabolic risk assessment.

Computers in biology and medicine·2026

Same author

Retrospective Observational Electronic Medical Records-based Real World Study to Assess the Prevalence and Treatment of Dyslipidemia in Indian Patients.

The Journal of the Association of Physicians of India·2025

Search research articles

Related Experiment Video

Updated: May 12, 2026

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Leveraging smart image processing techniques for early detection of foot ulcers using a deep learning network.

¹School of Computing, DIT University, Dehradun, India.

Polish Journal of Radiology

|August 14, 2024

Summary

This study developed a deep learning model for detecting diabetic foot ulcers using thermal imaging. The proposed model achieved high accuracy, offering a practical solution for early diagnosis and management of diabetic foot complications.

Keywords:

canny edge detection deep learning model diabetes watershed segmentation

More Related Videos

High-Resolution Three-Dimensional Imaging of the Footpad Vasculature in a Murine Hindlimb Gangrene Model

High-Resolution Three-Dimensional Imaging of the Footpad Vasculature in a Murine Hindlimb Gangrene Model

Published on: March 16, 2022

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Related Experiment Videos

Last Updated: May 12, 2026

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

High-Resolution Three-Dimensional Imaging of the Footpad Vasculature in a Murine Hindlimb Gangrene Model

High-Resolution Three-Dimensional Imaging of the Footpad Vasculature in a Murine Hindlimb Gangrene Model

Published on: March 16, 2022

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Area of Science:

Medical imaging
Artificial intelligence
Diabetology

Background:

Diabetic foot ulcers are a significant complication of diabetes, leading to severe morbidity.
Early detection is crucial for effective management and prevention of amputation.
Thermal imaging offers a non-invasive method for assessing foot health.

Purpose of the Study:

To develop and evaluate a deep learning model for detecting diabetic foot ulcers using thermal images.
To compare the performance of the proposed model against existing methods.

Main Methods:

A dataset of 1055 thermal foot images (normal and abnormal) was utilized.
Images were pre-processed using Canny edge detection and watershed segmentation.
Data augmentation was applied to balance and enlarge the dataset.
Deep learning models (ResNet50 and EfficientNetB0) were trained and tested.

Main Results:

The EfficientNetB0 model achieved 96.1% accuracy on the original dataset and 99.4% on the pre-processed dataset.
ResNet50 achieved 89% and 89.1% accuracy on the original and pre-processed datasets, respectively.
Pre-processing enhanced model performance and reduced computational cost.

Conclusions:

The developed deep learning models demonstrate high efficacy in detecting diabetic foot ulcers from thermal images.
The models provide a practical, automated solution for early ulcer detection, especially where expert analysis is limited.
The proposed approach shows significant potential for real-world clinical application in diabetes care.