Artikel
Automatic classification of wound images showing healing complications: towards an optimised approach for detecting maceration
Suche in Medline nach
Autoren
-
Eric Dührkopp
- Universitätsklinikum Erlangen, Erlangen, Germany
-
Leila Malihi
- Forschungsgruppe Informatik im Gesundheitswesen - Hochschule Osnabrück, Osnabrück, Germany
-
Cornelia Erfurt-Berge
- Universitätsklinikum Erlangen, Erlangen, Germany
-
Gunther Heidemann
- Universität Osnabrück, Osnabrück, Germany
-
Mareike Przysucha
- Forschungsgruppe Informatik im Gesundheitswesen - Hochschule Osnabrück, Osnabrück, Germany
-
Dorothee Busch
- Forschungsgruppe Informatik im Gesundheitswesen - Hochschule Osnabrück, Osnabrück, Germany; Universitätsklinikum Erlangen, Erlangen, Germany
-
Ursula Hertha Hübner
- Forschungsgruppe Informatik im Gesundheitswesen - Hochschule Osnabrück, Osnabrück, Germany
| Veröffentlicht: | 6. September 2024 |
|---|
Gliederung
Text
Introduction: This study aims to advance the field of digital wound care by developing and evaluating convolutional neural network (CNN) architectures for the automatic classification of maceration, a significant wound healing complication. Detection and classification of maceration can improve patient outcomes.
Methods: Several CNN models were compared using 458 annotated wound images of different would types.
Results and discussion: MobileNetV2 emerged as the top-performing model, achieving the highest accuracy (0.77) despite having fewer parameters. This finding underscores the importance of considering model complexity relative to dataset size. The study also explored the role of image cropping, which resulted in better performance, and the use of Grad-CAM visualizations to understand the decision-making process of the CNN.
Conclusion: From a medical perspective, the results indicate that employing CNNs for classification of maceration may enhance diagnostic accuracy and reduce the clinicians’ time and effort.
The authors declare that they have no competing interests.
The authors declare that a positive ethics committee vote has been obtained.
