Programa del congreso
Resúmenes y datos de las sesiones para este congreso. Seleccione una fecha o ubicación para mostrar solo las sesiones en ese día o ubicación. Seleccione una sola sesión para obtener una vista detallada (con resúmenes y descargas, si están disponibles).
|
Resumen diario |
| Sesión | |
|
Vi-S6.3-RVVA: Realidad virtual, visión artificial y tecnologías 3D Lugar: Aula 0.02 Presidente de la sesión: Carmen Serrano Gotarredona Presidente de la sesión: Oscar Camara | |
    | |
9:00 - 9:15
Application of YOLOv12 for Diabetic Foot Ulcer Detection in Clinical Images 1: Computer Vision and Robotics Institute, Universitat de Girona, Girona, Spain; 2: Institut d’Informàtica i Aplicacions, Universitat de Girona, Girona, Spain Diabetic foot ulcers (DFUs) are among the most serious and costly complications of diabetes. Early and precise detection is essential to improve patient outcomes and reduce healthcare burden. Although YOLOv12 has shown strong performance in medical imaging tasks, its effectiveness for DFU detection remains untested. In this paper, we present a comprehensive study of YOLOv12n for DFU detection using the DFUC2020 dataset. We perform 5-fold cross-validation strategy to assess the impact of different preprocessing methods, data augmentation techniques, and multi-label training based on ulcer size. Our best-performing configuration (strong data augmentation, multi labeling based on ulcer size, and no preprocessing) achieved a mAP@0.5 of 73.2% on the DFUC2020 test set. These results demonstrate that a streamlined YOLOv12n-based model achieves strong performance, outperforming more elaborate strategies while maintaining simplicity.
| |