Surface area estimation for application of wound care

Spińczyk, Dominik; Wideł, Monika

doi:10.1016/j.injury.2017.01.027

Cited by 6 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This presented a challenge to deep learning wound assessment model development, and prevented clinically usable classification performance from being performance achieved.Table II summarizes related work. Prior research on assessing PWAT wound attributes from images [20] , [21] , [22] , [23] , [24] , [25] , [26] , [27] , [28] , [29] typically only assessed a few wound attributes instead of assessing all clinically important attributes of wounds comprehensively. Prior research that explored data augmentation of wound images [30] , [31] , [32] , [33] , [34] , [35] applied both traditional data augmentation techniques or GAN-based methods.…”

Section: Introductionmentioning

confidence: 99%

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

Liu

Agu

Pedersen

et al. 2024

IEEE Open J. Eng. Med. Biol.

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionmentioning

confidence: 99%

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

Liu

Agu

Pedersen

et al. 2024

IEEE Open J. Eng. Med. Biol.

View full text Add to dashboard Cite

show abstract

“…Photo documentation having accurately measured wound size predicts wound healing and can be a valuable tool in communication between physicians concerning especially patients having chronic wounds. When taking normal pictures the reproducible lightning condition is essential for good-quality pictures [16]. Thermal imaging captures the normal heat radiation of the skin and is not dependent on lightning conditions.…”

Section: Introductionmentioning

confidence: 99%

CAT S60 smartphone as a portable wound care device in home care

Alametsä¹

2022

FinJeHeW

View full text Add to dashboard Cite

The purpose of this work is to study the suitability of the CAT S60 smartphone with built-in thermal camera to be used in self and home care to detect the risk level of wound appearance in advance. The purpose was to clarify different conditions where thermal imaging might act as a resource in detecting changes in limb circulation before visual signs even occur. The purpose is to detect early incipient tissue damage in foot usually occur in diabetic patients. Thermal images were acquired from voluntary domesticated elderly people. Thermal pictures from limbs of 3 persons were studied in order to find thermal differences indicating possible changes in limb circulation. Noteworthy thermal differences between limbs were found in elderly people. A smartphone having built-in thermal camera enables to detect plantar and limb thermal differences with a sufficient accuracy. This may support home monitoring for elderly people and thus reduce foot ulcers and possible foot amputations due to earlier detection and identification of harmful changes in limb circulation. Earlier detection of circulatory insufficiency via thermal imaging makes possible for nurses to intervene and enable medical assistance.

show abstract