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, in 458 annotated wound images. Detection and classification of maceration can improve patient outcomes. Several CNN models were compared and MobileNetV2 emerged as the top-performing model, achieving the highest accuracy 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 and the use of Grad-CAM visualizations to understand the decision-making process of the CNN. From a medical perspective, results indicate that employing CNNs for classification of maceration may enhance diagnostic accuracy and reduce the clinicians' time and effort.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.3233/SHTI240877 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Aeration promotes Proteobacteria over Firmicutes in macerated food waste, resulting in superior anaerobic digestion efficiency.
FEMS Microbiol Lett
January 2025
School of Civil and Environmental Engineering, UNSW Sydney, Sydney, NSW 2052, Australia.
Aeration is a common pretreatment method to enhance biogas production via anaerobic digestion of waste organic feedstocks such as unused food. While impacts on downstream anaerobic digestion have been intensively investigated, the consequence of aeration on the microbial community in food waste has not been characterized. Food waste has a low pH resulting from the dominance of lactic acid bacteria within the Firmicutes phylum.
View Article and Find Full Text PDFThe spoon-tipped (ST) setae coverage and their abundance on the second maxillipeds as well as the morphology of the urocardiac and zygocardiac ossicles from the gastric mills of the four ocypodid species, viz., Austruca annulipes (H. Milne Edwards, 1837), Gelasimus vocans (Linnaeus), 1758, two typical deposit-feeding fiddler crabs, Petruca panamensis (Stimpson, 1859), an atypical herbivorous-cum-'sediment swallower' fiddler crab, and Ocypode ceratophthalmus (Pallas, 1772), an omnivorous ghost crab, were described and compared in relation to their respective trophic habits.
View Article and Find Full Text PDFFlies as Carriers of Gastrointestinal Protozoa of Interest in Public Health in the Northeast of Brazil.
Acta Parasitol
December 2024
Department of Veterinary Medicine, Federal University of Sergipe, Nossa Senhora da Glória, SE, Brazil.
Purpouse: This study aimed to assess the influence of the presence of synanthropic flies in food preparation environments on the transmission of potentially zoonotic gastrointestinal protozoa.
Methods: Flies were captured using a glass containing water, fruits, and pieces of protein.
Results: Approximately 260 flies from four different species were captured: Musca domestica (76.
The First Isolation of Insect-Specific Alphavirus () in Culex (Melanoconion) Mosquitoes in the Brazilian Amazon.
Viruses
August 2024
Department of Arbovirology and Hemorrhagic Fevers, Evandro Chagas Institute, BR 316, Km 07, s/n, Ananindeua 67030-000, PA, Brazil.
Article Synopsis
- Advances in diagnostic techniques and environmental changes have led to heightened surveillance of arboviruses in the Amazon, revealing more insect-specific viruses in blood-feeding arthropods.
- The study documented the first isolation of a specific virus from mosquitoes in the Brazilian Amazon by collecting specimens from a forested area and using cell cultures for viral isolation.
- The research identified a mosquito batch positive for a particular genus, marking the first report of insect-specific alphavirus isolation in Brazil and within Amazon Forest remnants.
Automatic Classification of Wound Images Showing Healing Complications: Towards an Optimised Approach for Detecting Maceration.
Stud Health Technol Inform
August 2024
Health Informatics Research Group, Osnabrück University of AS., Germany.
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, in 458 annotated wound images. Detection and classification of maceration can improve patient outcomes. Several CNN models were compared and MobileNetV2 emerged as the top-performing model, achieving the highest accuracy despite having fewer parameters.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!