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

Search research articles

Related Experiment Video

Updated: Mar 21, 2026

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Comparing YOLO and U-net deep learning algorithms in chronic wound image segmentation.

Indrani Marchal¹, Zhara Ali², Haroun Ammi²

¹Department of Bio- Electro- and Mechanical Systems (BEAMS), Ecole Polytechnique de Bruxelles, Université Libre de Bruxelles, Avenue Franklin Roosevelt 50, Brussels, 1050, Belgium. indrani.marchal@ulb.be.

BMC Medical Imaging

|March 20, 2026

Summary

Related Concept Videos

You might also read

Related Articles

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

Sort by

Same author

Vagus Nerve Stimulation differentially modulates P3b in responders and non-responders: toward a biomarker of therapeutic efficacy.

Frontiers in neuroscience·2026

Same author

EEG functional connectivity methods for seizure-related disorders.

NeuroImage·2026

Same author

Development and content validation of WoundPilot: a clinical decision support system for structured wound assessment and decision-making.

Journal of tissue viability·2026

Same author

Prevalence of Early Rheumatic Heart Disease Among Asymptomatic Students in Underserved Communities in Ethiopia: Cross-Sectional Observational Study.

JMIR public health and surveillance·2026

Same author

Consciousness Monitoring and Outcome Prediction Using EEG Connectivity in Severe Traumatic Brain Injury.

Journal of neurotrauma·2026

Same author

Heart rate variability during wakefulness reflects sleep apnea indicators but remains context-dependent.

Frontiers in physiology·2026

Modern YOLO deep learning models excel at segmenting chronic wounds, outperforming U-Net in accuracy and speed. YOLOv8n and YOLO11s demonstrate robust, generalizable performance for AI-driven wound analysis.

Area of Science:

Medical Image Analysis
Artificial Intelligence in Healthcare
Computer Vision

Background:

Accurate chronic wound segmentation is vital for effective patient care.
Deep learning models like U-Net are benchmarks for medical image segmentation.
Limitations in current methods necessitate exploring advanced object detection algorithms.

Purpose of the Study:

To evaluate the efficacy of YOLOv8 and YOLO11 for chronic wound segmentation.
To compare YOLO models against the U-Net benchmark using diverse datasets.
To assess segmentation accuracy, generalization, and inference speed.

Main Methods:

Utilized YOLOv8 and YOLO11 deep learning architectures for medical image segmentation.
Employed the FUSeg and Wound Data databases for simultaneous training and testing.

Keywords:

AI tool Chronic wound Cross-dataset Deep learning U-net Wound segmentation YOLO

More Related Videos

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: Mar 21, 2026

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

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

Performed cross-dataset validation to ensure model robustness and generalizability.

Main Results:

YOLO models significantly outperformed U-Net in segmentation accuracy, generalization, and inference speed.
YOLOv8n achieved the highest performance (IoU 71.7%, DSC 79.3%).
YOLO11s demonstrated notable stability and cross-dataset robustness (IoU 70.1%, DSC 78.5%).

Conclusions:

Modern YOLO architectures provide fast, accurate, and robust automated wound segmentation solutions.
These findings support the advancement of AI-driven wound analysis and diagnosis.
Cross-dataset validation highlights the importance of diverse data for adaptable AI models.