EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Automated Classification of Second- and Third-Degree Burn Images Using Convolutional Neural Networks

Yamile Montecinos-Rodríguez iD, Francisco J Torres-Santana iD, Noureddine Lakouari iD, Lorena Díaz-González iD

European Burn Journal · 10.06.2026 · 7 (2) · 33

DOI: 10.3390/ebj7020033 ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Burn Journal, online erschienen am 10.06.2026. Verfasst von Yamile Montecinos-Rodríguez und 3 weiteren Autor:innen. Beteiligte Einrichtung: Licenciatura en Inteligencia Artificial, Instituto de Investigación en Ciencias Básicas y Aplicadas (IICBA), Universidad Autónoma del Estado de Morel…. Die Arbeit nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Burn severity assessment is clinically relevant and often requires timely decision-making. Visual classification of second- and third-degree burns remains subjective and prone to observer variability.

Methods

This study aimed to develop and evaluate a deep learning model for the automatic classification of second- and third-degree burn images. A dataset of clinical burn images from a private wound care clinic was used to train a convolutional neural network. Hyperparameter optimization and color channel sensitivity analysis were performed to identify the optimal model configuration. Model performance was evaluated using standard classification metrics on training, validation, and independent test datasets, and results were compared with transfer learning approaches.

Results

The best performance was achieved using a compact model trained exclusively with the green color channel, obtaining an accuracy of 0.94, precision of 0.96, recall of 0.92, and an F1-score of 0.94 on the independent test set. This model outperformed more complex transfer learning approaches while reducing computational complexity.

Conclusions

These findings indicate that using only the green color channel enables efficient and accurate burn classification. The proposed model was also integrated into a graphical user interface, supporting its potential application in clinical and educational environments.

Schlagwörter

Stichwörter der Autor:innen

burn degreeburn severity classificationclinical decision supportcomputer-assisted diagnosisconvolutional neural networksdeep learningmedical image analysis

Autor:innen und Institutionen

  • Licenciatura en Inteligencia Artificial, Instituto de Investigación en Ciencias Básicas y Aplicadas (IICBA), Universidad Autónoma del Estado de Morelos, Cuernavaca 62209, Morelos, Mexico.
  • Instituto Nacional de Astrofísica, Óptica y Electrónica, Luis Enrique Erro 1, Tonantzintla 72840, Puebla, Mexico.
  • Secretaría de Ciencia, Humanidades, Tecnología e Innovación (SECIHTI), Insurgentes Sur 1582, Ciudad de México 03940, Mexico.
  • Centro de Investigación en Ciencias, Universidad Autónoma del Estado de Morelos, Cuernavaca 62209, Morelos, Mexico.

ORCID-Profile: Yamile Montecinos-Rodríguez, Francisco J Torres-Santana, Noureddine Lakouari, Lorena Díaz-González

Zitieren

APA

Montecinos-Rodríguez, Y., Torres-Santana, F. J., Lakouari, N., & Díaz-González, L. (2026). Automated Classification of Second- and Third-Degree Burn Images Using Convolutional Neural Networks. European Burn Journal, 7(2), 33. https://doi.org/10.3390/ebj7020033

Vancouver

Montecinos-Rodríguez Y, Torres-Santana FJ, Lakouari N, Díaz-González L. Automated Classification of Second- and Third-Degree Burn Images Using Convolutional Neural Networks. European Burn Journal. 2026;7(2):33. doi:10.3390/ebj7020033

BibTeX
@article{MontecinosRodrguez2026,
  author = {Montecinos-Rodríguez, Yamile and Torres-Santana, Francisco J and Lakouari, Noureddine and Díaz-González, Lorena},
  title = {Automated Classification of Second- and Third-Degree Burn Images Using Convolutional Neural Networks},
  journal = {European Burn Journal},
  year = {2026},
  volume = {7},
  number = {2},
  pages = {33},
  doi = {10.3390/ebj7020033}
}
Kostenlos starten →