Chronic Wound Image Augmentation and Assessment Using Semi-Supervised Progressive Multi-Granularity EfficientNet

Abstract

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.

Diyabetik Ayağın Derin Öğrenme Yöntemleriyle Ayırıcı Tanısı

“…Through a thorough evaluation of feature extractors and architectures, the researchers argue that an optimized combination of EfficientNetb3 and UNet for box detection has the potential to outperform the current. Liu et al (2023) introduced a novel DL architecture called Semi-Supervised PMG EfficientNet (SS-PMG-EfficientNet), which was utilized to estimate all eight sub-scores related to PWAT. The researchers employed transfer learning techniques on the SS-PMG-EfficientNet model in order to train individual models for each of the eight PWAT sub-scores.…”

Guest Editorial Introduction to the Special Section on Weakly-Supervised Deep Learning and Its Applications

“…The objective of the study from Liu, et al [7] is to enhance a small and imbalanced wound dataset by employing semi-supervised learning techniques with the assistance of a secondary dataset. Subsequently, the augmented wound dataset is utilized for deep learning-based wound assessment.…”