Features identification for automatic burn classification

Serrano, Carmen; Boloix-Tortosa, Rafael; Gómez-Cía, Tomás; Acha, Begoña

doi:10.1016/j.burns.2015.05.011

Cited by 44 publications

(37 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The CIELab extracts the luminance and the chromatic information of an image utilizing three coordinates: the L * coordinate ( L * = 0 encloses black and L * = 100 encloses white) that describes the luminance, the a * and b * coordinates that represent the pure colours from green to red ( a * = −127 encloses green, a * = +128 yields red) and from blue to yellow ( b * = −127 encloses blue, b * = +128 encloses yellow), respectively. Another important characteristic of this model is its uniformity, where the distance between two different colours corresponds to the Euclidean one and it coincides to the perceptual difference detected by the human visual system 25–27 . For all these reasons, the CIELab colour model was therefore chosen in this study.…”

Section: Materials and Proposed Methodsmentioning

confidence: 79%

Tensor Decomposition for Colour Image Segmentation of Burn Wounds

Cirillo

Mirdell

Sjöberg

et al. 2019

Sci Rep

View full text Add to dashboard Cite

Research in burns has been a continuing demand over the past few decades, and important advancements are still needed to facilitate more effective patient stabilization and reduce mortality rate. Burn wound assessment, which is an important task for surgical management, largely depends on the accuracy of burn area and burn depth estimates. Automated quantification of these burn parameters plays an essential role for reducing these estimate errors conventionally carried out by clinicians. The task for automated burn area calculation is known as image segmentation. In this paper, a new segmentation method for burn wound images is proposed. The proposed methods utilizes a method of tensor decomposition of colour images, based on which effective texture features can be extracted for classification. Experimental results showed that the proposed method outperforms other methods not only in terms of segmentation accuracy but also computational speed.

show abstract

Section: Materials and Proposed Methodsmentioning

confidence: 79%

Tensor Decomposition for Colour Image Segmentation of Burn Wounds

Cirillo

Mirdell

Sjöberg

et al. 2019

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Accuracies of 66.2% and 83.8% were achieved using SVM when classifying burn images into three types of burn depths and two types of burns respectively [6]. In another research work, an accuracy of 79.73% was achieved using SVM for classification of burn images into two types of burns [7].…”

Section: Introductionmentioning

confidence: 93%

“…The colour-thermal camera is expensive to acquire as compared to the regular digital camera. Besides that, there were two related works focusing on classifying burn images into two types of burns (burn that needed grafts and burns that did not need grafts) [6], [7] and three types of burns depths (superficial dermal, deep dermal and full thickness) [6]. They conducted experiments to translate the physical features that were unconsciously observed by experts when diagnosing a burn into mathematical features.…”

Section: Introductionmentioning

confidence: 99%

“…Most of them used the colour feature as the main characteristic to differentiate between different burn depths. There were some related work focusing on extracting both colour and texture features [6], [7], [9]- [11]. Their extracted colour features were mostly statistical moment of common colour features such as variance of hue, mean of h-space, mean of lightness and so on.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Extracting Novel Features for Skin Burn Image Classification

Nei*,

Chua,

Safawi

et al. 2019

IJRTE

View full text Add to dashboard Cite

In this paper, the objective is to propose a set of novel features for the classification of different burn depths by using an image mining approach. Both colour and texture features were studied on skin burn dataset comprising skin burn images categorized into three burn depths by the burn specialist. The performance of the proposed feature set was evaluated using linear SVM on 10-fold cross validation method. The empirical results showed that the six proposed novel features, when used together with the common image features, was the best set of features that was able to classify most of the burn depths in terms of accuracy, precision and recall measures with the values of 96.8750%, 96.9697% and 96.6667% respectively. Automated classification of skin burn depths is essential because the initial burn treatment provided to patients are usually based on the first evaluation of the skin burn injuries by determining the burn depths. However, the burn specialist may not always be available at the accident site. In conclusion, the features extracted that represent the burn characteristics specifically in terms of colour and texture were able to effectively characterise the depth of burns in accordance to burn depth classification.

show abstract

“…Considering this, burns induced by liquids at high temperatures are usually first-degree lesions. In such cases, the primary symptoms observed are edema and pain, with intense inflammation and possible skin T desquamation (3 to 7 days after the induction of the lesion) (Monstrey et al, 2008;Piccolo et al, 2008;Serrano et al, 2015).…”

Section: Introductionmentioning

confidence: 99%

Topical treatment with a transient receptor potential ankyrin 1 (TRPA1) antagonist reduced nociception and inflammation in a thermal lesion model in rats

Antoniazzi

Prá

Ferro

et al. 2018

European Journal of Pharmaceutical Sciences

View full text Add to dashboard Cite

Thermal injury promotes tissue inflammation and pain, which is difficult to control. Different peripheral mechanisms seem to be involved in burn pain, such as free radical-induced damage, but further study is still needed to understand how oxidant substances induced nociceptor sensitization. The transient receptor potential ankyrin 1 (TRPA1) is an ion channel activated by oxidants substances, and it could be sensitized after tissue inflammation. This study evaluated the TRPA1 involvement in nociception and inflammation produced by a thermal injury model. Male Wistar rats were used. The concentration of the TRPA1 antagonist (HC-030031, 0.05%) on base cream was chosen using allyl isothiocyanate intraplantar test. Then, the base cream containing HC-030031 was tested on the thermal injury model (induced by warm water immersion of hind paw, under anesthesia), and silver sulfadiazine (1%) was used as a positive control. Cream treatments on the hind paw were done daily (200 mg/paw) for 6 days after thermal injury. Also, nociception (static and dynamic mechanical allodynia, heat allodynia, and spontaneous pain) or edema were evaluated. On day 6, inflammatory and oxidative parameters were assessed. The base cream containing HC-030031 produced antinociceptive and anti-inflammatory effects (reduced the edema and inflammatory cells infiltration) and decreased the levels of hydrogen peroxide, or superoxide dismutase and NADPH oxidase activities after thermal injury. Thus, this study showed the involvement of the TRPA1 receptor in the nociception and inflammation caused by thermal injury and suggested that TRPA1 antagonists might be useful as novel treatments for pain and inflammation by topical application.

show abstract

Features identification for automatic burn classification

Cited by 44 publications

References 30 publications

Tensor Decomposition for Colour Image Segmentation of Burn Wounds

Tensor Decomposition for Colour Image Segmentation of Burn Wounds

Extracting Novel Features for Skin Burn Image Classification

Topical treatment with a transient receptor potential ankyrin 1 (TRPA1) antagonist reduced nociception and inflammation in a thermal lesion model in rats

Contact Info

Product

Resources

About