Your browser doesn't support javascript.
loading
Chronic Wound Image Augmentation and Assessment Using Semi-Supervised Progressive Multi-Granularity EfficientNet.
Liu, Ziyang; Agu, Emmanuel; Pedersen, Peder; Lindsay, Clifford; Tulu, Bengisu; Strong, Diane.
Afiliación
  • Liu Z; Computer Science DepartmentWorcester Polytechnic Institute Worcester MA 01609 USA.
  • Agu E; Computer Science DepartmentWorcester Polytechnic Institute Worcester MA 01609 USA.
  • Pedersen P; Electrical and Computer Engineering DepartmentWorcester Polytechnic Institute Worcester MA 01609 USA.
  • Lindsay C; Department of RadiologyUniversity of Massachusetts Medical School Worcester MA 01609 USA.
  • Tulu B; Foisie Business SchoolWorcester Polytechnic Institute Worcester MA 01609 USA.
  • Strong D; Foisie Business SchoolWorcester Polytechnic Institute Worcester MA 01609 USA.
IEEE Open J Eng Med Biol ; 5: 404-420, 2024.
Article en En | MEDLINE | ID: mdl-38899014
ABSTRACT
Goal Augment a small, imbalanced, wound dataset by using semi-supervised learning with a secondary dataset. Then utilize the augmented wound dataset for deep learning-based wound assessment.

Methods:

The clinically-validated Photographic Wound Assessment Tool (PWAT) scores eight wound attributes Size, Depth, Necrotic Tissue Type, Necrotic Tissue Amount, Granulation Tissue type, Granulation Tissue Amount, Edges, Periulcer Skin Viability to comprehensively assess chronic wound images. A small corpus of 1639 wound images labeled with ground truth PWAT scores was used as reference. A Semi-Supervised learning and Progressive Multi-Granularity training mechanism were used to leverage a secondary corpus of 9870 unlabeled wound images. Wound scoring utilized the EfficientNet Convolutional Neural Network on the augmented wound corpus.

Results:

Our proposed Semi-Supervised PMG EfficientNet (SS-PMG-EfficientNet) approach estimated all 8 PWAT sub-scores with classification accuracies and F1 scores of about 90% on average, and outperformed a comprehensive list of baseline models and had a 7% improvement over the prior state-of-the-art (without data augmentation). We also demonstrate that synthetic wound image generation using Generative Adversarial Networks (GANs) did not improve wound assessment.

Conclusions:

Semi-supervised learning on unlabeled wound images in a secondary dataset achieved impressive performance for deep learning-based wound grading.
Palabras clave

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Idioma: En Revista: IEEE Open J Eng Med Biol Año: 2024 Tipo del documento: Article Pais de publicación: Estados Unidos

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Idioma: En Revista: IEEE Open J Eng Med Biol Año: 2024 Tipo del documento: Article Pais de publicación: Estados Unidos