Chronic Wound Image Augmentation and Assessment Using Semi-Supervised Progressive Multi-Granularity EfficientNet
IEEE Open Journal of Engineering in Medicine and Biology · 2024 · 5 · 404-420
DOI: 10.1109/ojemb.2023.3248307 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Open Journal of Engineering in Medicine and Biology, 2024. Verfasst von Ziyang Liu und 5 weiteren Autor:innen. Beteiligte Einrichtung: Computer Science DepartmentWorcester Polytechnic Institute Worcester MA 01609 USA. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Institutes of Health, SCH: INT: Smartphone Wound Image Parameter Analysis and Decision Support in Mobile Environments, Emmanuel Agu.
Abstract (Originalsprache)
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.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Computer Science DepartmentWorcester Polytechnic Institute Worcester MA 01609 USA.
- Electrical and Computer Engineering DepartmentWorcester Polytechnic Institute Worcester MA 01609 USA.
- Department of RadiologyUniversity of Massachusetts Medical School Worcester MA 01609 USA.
- Foisie Business SchoolWorcester Polytechnic Institute Worcester MA 01609 USA.
ORCID-Profile: Ziyang Liu, Emmanuel Agu, Peder Pedersen, Bengisu Tulu, Diane Strong
Förderung
- National Institutes of Health
- SCH: INT: Smartphone Wound Image Parameter Analysis and Decision Support in Mobile Environments
- Emmanuel Agu
- Diane Strong
- Bengisu Tulu
- National Science Foundation
- Smart and Connected Health Program/NIH NIBIB
Zitieren
APA
Liu, Z., Agu, E., Pedersen, P., Lindsay, C., Tulu, B., & Strong, D. (2024). Chronic Wound Image Augmentation and Assessment Using Semi-Supervised Progressive Multi-Granularity EfficientNet. IEEE Open Journal of Engineering in Medicine and Biology, 5, 404-420. https://doi.org/10.1109/ojemb.2023.3248307
Vancouver
Liu Z, Agu E, Pedersen P, Lindsay C, Tulu B, Strong D. Chronic Wound Image Augmentation and Assessment Using Semi-Supervised Progressive Multi-Granularity EfficientNet. IEEE Open Journal of Engineering in Medicine and Biology. 2024;5:404-420. doi:10.1109/ojemb.2023.3248307
BibTeX
@article{Liu2024,
author = {Liu, Ziyang and Agu, Emmanuel and Pedersen, Peder and Lindsay, Clifford and Tulu, Bengisu and Strong, Diane},
title = {Chronic Wound Image Augmentation and Assessment Using Semi-Supervised Progressive Multi-Granularity EfficientNet},
journal = {IEEE Open Journal of Engineering in Medicine and Biology},
year = {2024},
volume = {5},
pages = {404--420},
doi = {10.1109/ojemb.2023.3248307}
}
EUVIMED