Automatic Wound Type Classification with Convolutional Neural Networks

Malihi, Leila; Hüsers, Jens; Richter, Mats L.; Moelleken, Maurice; Przysucha, Mareike; Busch, Dorothee; Heggemann, Jan; Hafer, Guido; Wiemeyer, Stefan; Heidemann, Gunther; Dissemond, Joachim; Erfurt‐Berge, Cornelia; Hübner, Ursula

doi:10.3233/shti220717

Cited by 3 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… 14 In this study, noninvasive biotechnological devices were used to obtain measurement results on skin parameters, which were used to train the AI. In the study by Malihi et al., 15 neural networks were used to classify wound types, and in the Gibstein et al. study, 16 neural networks were applied to assess surgical outcomes after face lift surgery.…”

Section: Discussionmentioning

confidence: 99%

“…A possible more objective system for skin type classification was applied by Seo et al 14 In this study, noninvasive biotechnological devices were used to obtain measurement results on skin parameters, which were used to train the AI. In the study by Malihi et al, 15 neural networks were used to classify wound types, and in the Gibstein et al…”

Section: F I G U R Ementioning

confidence: 99%

See 1 more Smart Citation

Differences in the annotation between facial images and videos for training an artificial intelligence for skin type determination

Lehner,

Gockeln,

Naber

et al. 2024

Skin Research and Technology

View full text Add to dashboard Cite

BackgroundThe Grand‐AID research project, consisting of GRANDEL‐The Beautyness Company, the dermatology department of Augsburg University Hospital and the Chair of IT Infrastructure for Translational Medical Research at Augsburg University, is currently researching the development of a digital skin consultation tool that uses artificial intelligence (AI) to analyze the user's skin and ultimately perform a personalized skin analysis and a customized skin care routine. Training the AI requires annotation of various skin features on facial images. The central question is whether videos are better suited than static images for assessing dynamic parameters such as wrinkles and elasticity. For this purpose, a pilot study was carried out in which the annotations on images and videos were compared.Materials and MethodsStandardized image sequences as well as a video with facial expressions were taken from 25 healthy volunteers. Four raters with dermatological expertise annotated eight features (wrinkles, redness, shine, pores, pigmentation spots, dark circles, skin sagging, and blemished skin) with a semi‐quantitative and a linear scale in a cross‐over design to evaluate differences between the image modalities and between the raters.ResultsIn the videos, most parameters tended to be assessed with higher scores than in the images, and in some cases significantly. Furthermore, there were significant differences between the raters.ConclusionThe present study shows significant differences between the two evaluation methods using image or video analysis. In addition, the evaluation of the skin analysis depends on subjective criteria. Therefore, when training the AI, we recommend regular training of the annotating individuals and cross‐validation of the annotation.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: F I G U R Ementioning

confidence: 99%

Differences in the annotation between facial images and videos for training an artificial intelligence for skin type determination

Lehner,

Gockeln,

Naber

et al. 2024

Skin Research and Technology

View full text Add to dashboard Cite

show abstract

“…They trained a CNN algorithm model on 863 cropped wound images and evaluated its performance using a test set. The study reported an F1-score of 0.85 for cropped test images and an F1-score of 0.70 for complete images in the trained deep CNN model [33]. Furthermore, CNNs have demonstrated utility in segmenting wounds in microscopic imaging.…”

Section: Related Workmentioning

confidence: 97%

Nursing Intervention of Children’s Lower Limb Chronic Wound Healing Under Artificial Intelligence

Hao,

Sun

2023

IEEE Access

View full text Add to dashboard Cite

This work aimed to compare the effect of family-centered nursing and routine nursing on the treatment of children with chronic lower limb wounds. A total of 112 children with chronic wounds of the lower limbs were divided into a test group (56 cases) and a control group (56 cases). The children in the test group were given a family-centered nursing intervention, while those in the control group were given a routine nursing intervention. Additionally, an image segmentation algorithm based on a deep convolutional neural network was proposed to segment chronic wound images. The results showed that there were no significant differences in sex, injury site (left or right limb), age, height, weight, and cause of disease (scald, blow, fall) between the test group and the control group (P > 0.05). The wound pain score of the test group was 3.38 ± 0.75 and that of the control group was 6.24 ± 1.48. Compared with the control group, the wound pain score of the test group was lower (P < 0.05). The total effective rate of the test group (92.86%) was significantly higher than that of the control group (78.57%) (P < 0.05). The accuracy of the DCNN model in both the training and test datasets was significantly higher than that of the FCM model (P < 0.05). The results showed that, compared with routine nursing, family-centered nursing intervention had a more significant effect on children with chronic wounds of the lower extremities and had clinical promotion value.INDEX TERMS Deep convolutional neural networks; family-centered nursing; chronic wounds in children's lower limbs; image segmentation; wound pain

show abstract

“…Similarly, in Ref. [21], the Xception model with pre-trained weights was employed to classify diabetic and venous ulcers. The model was evaluated on a private wound image dataset (909 wound images), and 83% and 67% accuracy were achieved for cropped and full wound images, respectively.…”

Section: Literature Reviewmentioning

confidence: 99%

A Novel Fused Multi-Class Deep Learning Approach for Chronic Wounds Classification

Aldoulah,

Malik,

Molyet

2023

Applied Sciences

View full text Add to dashboard Cite

Chronic wounds affect the lives of millions of individuals globally, and due to substantial medical costs, treating chronic injuries is very challenging for the healthcare system. The classification of regular wound type is essential in wound care management and diagnosis since it can assist clinicians in deciding on the appropriate treatment method. Hence, an effective wound diagnostic tool would enable clinicians to classify the different types of chronic wounds in less time. The majority of the existing chronic wound classification methods are mainly focused on the binary classification of the wound types. A few approaches exist that classify chronic wounds into multiple classes, but these achieved lower performances for pressure and diabetic wound classification. Furthermore, cross-corpus evaluation is absent in chronic wound type classification, in order to better evaluate the efficacy of existing methods on real-time wound images. To address the limitations of the current studies, we propose a novel Swish-ELU EfficientNet-B4 (SEEN-B4) deep learning framework that can effectively identify and classify chronic wounds into multiple classes. Moreover, we also extend the existing Medetec and Advancing the Zenith of Healthcare (AZH) datasets to deal with the class imbalance problem of these datasets. Our proposed model is evaluated on publicly available AZH and Medetec datasets and their extended versions. Our experimental results indicate that the proposed SEEN-B4 model has attained an accuracy of 87.32%, 88.17%, 88%, and 89.34% on the AZH, Extended AZH, Medetec, and Extended Medetec datasets, respectively. We also show the effectiveness of our method against the existing state-of-the-art (SOTA) methods. Furthermore, we evaluated the proposed model for the cross-corpora scenario to demonstrate the model generalization aptitude, and interpret the model’s result through explainable AI techniques. The experimental results show the proposed model’s effectiveness for classifying chronic wound types.

show abstract

Automatic Wound Type Classification with Convolutional Neural Networks

Cited by 3 publications

References 7 publications

Differences in the annotation between facial images and videos for training an artificial intelligence for skin type determination

Differences in the annotation between facial images and videos for training an artificial intelligence for skin type determination

Nursing Intervention of Children’s Lower Limb Chronic Wound Healing Under Artificial Intelligence

A Novel Fused Multi-Class Deep Learning Approach for Chronic Wounds Classification

Contact Info

Product

Resources

About