Non-invasive medical imaging technology for the diagnosis of burn depth.

Currently, the clinical diagnosis of burn depth primarily relies on physicians' judgements based on patients' symptoms and physical signs, particularly the morphological characteristics of the wound. This method highly depends on individual doctors' clinical experience, proving challenging for less experienced or primary care physicians, with results often varying from one practitioner to another. Therefore, scholars have been exploring an objective and quantitative auxiliary examination technique to enhance the accuracy and consistency of burn depth diagnosis. Non-invasive medical imaging technology, with its significant advantages in examining tissue surface morphology, blood flow in deep and changes in structure and composition, has become a hot topic in burn diagnostic technology research in recent years. This paper reviews various non-invasive medical imaging technologies that have shown potential in burn depth diagnosis. These technologies are summarized and synthesized in terms of imaging principles, current research status, advantages and limitations, aiming to provide a reference for clinical application or research for burn specialists.

Adversarial attacks and adversarial training for burn image segmentation based on deep learning.

Deep learning has been widely applied in the fields of image classification and segmentation, while adversarial attacks can impact the model's results in image segmentation and classification. Especially in medical images, due to constraints from factors like shooting angles, environmental lighting, and diverse photography devices, medical images typically contain various forms of noise. In order to address the impact of these physically meaningful disturbances on existing deep learning models in the application of burn image segmentation, we simulate attack methods inspired by natural phenomena and propose an adversarial training approach specifically designed for burn image segmentation. The method is tested on our burn dataset. Through the defensive training using our approach, the segmentation accuracy of adversarial samples, initially at 54%, is elevated to 82.19%, exhibiting a 1.97% improvement compared to conventional adversarial training methods, while substantially reducing the training time. Ablation experiments validate the effectiveness of individual losses, and we assess and compare training results with different adversarial samples using various metrics.

Review of machine learning for optical imaging of burn wound severity assessment.

Significance: Over the past decade, machine learning (ML) algorithms have rapidly become much more widespread for numerous biomedical applications, including the diagnosis and categorization of disease and injury. Aim: Here, we seek to characterize the recent growth of ML techniques that use imaging data to classify burn wound severity and report on the accuracies of different approaches. Approach: To this end, we present a comprehensive literature review of preclinical and clinical studies using ML techniques to classify the severity of burn wounds. Results: The majority of these reports used digital color photographs as input data to the classification algorithms, but recently there has been an increasing prevalence of the use of ML approaches using input data from more advanced optical imaging modalities (e.g., multispectral and hyperspectral imaging, optical coherence tomography), in addition to multimodal techniques. The classification accuracy of the different methods is reported; it typically ranges from ∼70% to 90% relative to the current gold standard of clinical judgment. Conclusions: The field would benefit from systematic analysis of the effects of different input data modalities, training/testing sets, and ML classifiers on the reported accuracy. Despite this current limitation, ML-based algorithms show significant promise for assisting in objectively classifying burn wound severity.

In vivo visualization of burn depth in skin tissue of rats using hemoglobin parameters estimated by diffuse reflectance spectral imaging.

Significance: Burn injuries represent a global public health problem that kills an estimated 180,000 people annually. Non-fatal burns result in prolonged hospitalization, disfigurement, and disability. The most common, convenient, and widely used method for assessing burn depth is physical or visual examination, but the accuracy of this method is reportedly poor (60% to 75%). Rapid, correct assessment of burn depth is very important for the optimal management and treatment of burn patients. New methods of burn depth assessment that are inexpensive, simple, rapid, non-contact, and non-invasive are therefore needed. Aim: The aim of this study was to propose an approach to visualize the spatial distribution of burn depth using hemoglobin parameters estimated from spectral diffuse reflectance imaging and to demonstrate the feasibility of the proposed approach for differentiating burn depth in a rat model of scald burn injury. Approach: The new approach to creating a spatial map of burn depth was based on canonical discriminant analysis (CDA) of total hemoglobin concentration, tissue oxygen saturation, and methemoglobin saturation as estimated from spectral diffuse reflectance images. Burns of three different degrees of severity were created in rat dorsal skin by 10-s exposure to water maintained at 70°C, 78°C, and 98°C, respectively. Spectral images for dorsal regions were acquired under anesthesia immediately after burn injury and at 24 h, 48 h, and 72 h after injury. Results: Most areas of images in the group with skin exposed to 70°C water and 98°C water were classified as 70°C burn and 98°C burn, respectively. In contrast, no significant difference between areas classified as 78°C burn and 98°C burn from 24 h to 72 h was evident in the group with skin exposed to 78°C water, suggesting that burn depth was heterogeneous. Conclusions: The proposed approach combining diffuse reflectance spectral imaging and CDA appears promising for differentiating 70°C burns from 78°C burns and 98°C burns, and 98°C burns from 70°C burns and 78°C burns at 24 to 72 h after burn injury in a rat model of scald burn injury.

Segmentation and classification of skin burn images with artificial intelligence: Development of a mobile application.

AIM: This study was conducted to determine the segmentation, classification, object detection, and accuracy of skin burn images using artificial intelligence and a mobile application. With this study, individuals were able to determine the degree of burns and see how to intervene through the mobile application. METHODS: This research was conducted between 26.10.2021-01.09.2023. In this study, the dataset was handled in two stages. In the first stage, the open-access dataset was taken from https://universe.roboflow.com/, and the burn images dataset was created. In the second stage, in order to determine the accuracy of the developed system and artificial intelligence model, the patients admitted to the hospital were identified with our own design Burn Wound Detection Android application. RESULTS: In our study, YOLO V7 architecture was used for segmentation, classification, and object detection. There are 21018 data in this study, and 80% of them are used as training data, and 20% of them are used as test data. The YOLO V7 model achieved a success rate of 75.12% on the test data. The Burn Wound Detection Android mobile application that we developed in the study was used to accurately detect images of individuals. CONCLUSION: In this study, skin burn images were segmented, classified, object detected, and a mobile application was developed using artificial intelligence. First aid is crucial in burn cases, and it is an important development for public health that people living in the periphery can quickly determine the degree of burn through the mobile application and provide first aid according to the instructions of the mobile application.

Segmentation and quantitative analysis of optical coherence tomography (OCT) images of laser burned skin based on deep learning.

Evaluation of skin recovery is an important step in the treatment of burns. However, conventional methods only observe the surface of the skin and cannot quantify the injury volume. Optical coherence tomography (OCT) is a non-invasive, non-contact, real-time technique. Swept source OCT uses near infrared light and analyzes the intensity of light echo at different depths to generate images from optical interference signals. To quantify the dynamic recovery of skin burns over time, laser induced skin burns in mice were evaluated using deep learning of Swept source OCT images. A laser-induced mouse skin thermal injury model was established in thirty Kunming mice, and OCT images of normal and burned areas of mouse skin were acquired at day 0, day 1, day 3, day 7, and day 14 after laser irradiation. This resulted in 7000 normal and 1400 burn B-scan images which were divided into training, validation, and test sets at 8:1.5:0.5 ratio for the normal data and 8:1:1 for the burn data. Normal images were manually annotated, and the deep learning U-Net model (verified with PSPNe and HRNet models) was used to segment the skin into three layers: the dermal epidermal layer, subcutaneous fat layer, and muscle layer. For the burn images, the models were trained to segment just the damaged area. Three-dimensional reconstruction technology was then used to reconstruct the damaged tissue and calculate the damaged tissue volume. The average IoU value and f-score of the normal tissue layer U-Net segmentation model were 0.876 and 0.934 respectively. The IoU value of the burn area segmentation model reached 0.907 and f-score value reached 0.951. Compared with manual labeling, the U-Net model was faster with higher accuracy for skin stratification. OCT and U-Net segmentation can provide rapid and accurate analysis of tissue changes and clinical guidance in the treatment of burns.

Dynamic optical coherence elastography for skin burn assessment: A preliminary study on mice model.

Skin burns that include tissue coagulation necrosis imply variations in stiffness. Dynamic phase-sensitive optical coherence elastography (OCE) is used to evaluate the stiffness of burned skin nondestructively in this paper. The homemade dynamic OCE was initially verified through tissue-mimicking phantom experiments regarding Rayleigh wave speed. After being burned with a series of temperatures and durations, the corresponding structure and stiffness variations of mice skin were demonstrated by histological images, optical coherence tomography B-scans, and OCE elastic wave speed maps. The results clearly displayed the variation in elastic properties and stiffness of the scab edge extending in the lateral direction. Statistical analysis revealed that murine skin burned at temperatures exceeding 100°C typically exhibited greater stiffness than skin burned at temperatures below 100°C. The dynamic OCE technique shows potential application for incorporating elasticity properties as a biomechanical extension module to diagnose skin burn injuries.

High-frequency photoacoustic and ultrasound imaging for skin evaluation: Pilot study for the assessment of a chemical burn.

Skin architecture and its underlying vascular structure could be used to assess the health status of skin. A non-invasive, high resolution and deep imaging modality able to visualize skin subcutaneous layers and vasculature structures could be useful for determining and characterizing skin disease and trauma. In this study, a multispectral high-frequency, linear array-based photoacoustic/ultrasound (PAUS) probe is developed and implemented for the imaging of rat skin in vivo. The study seeks to demonstrate the probe capabilities for visualizing the skin and its underlying structures, and for monitoring changes in skin structure and composition during a 5-day course of a chemical burn. We analayze composition of lipids, water, oxy-hemoglobin, and deoxy-hemoglobin (for determination of oxygen saturation) in the skin tissue. The study successfully demonstrated the high-frequency PAUS imaging probe was able to provide 3D images of the rat skin architecture, underlying vasculature structures, and oxygen saturation, water, lipids and total hemoglobin.

Ultrasonografía cutánea: una herramienta objetiva para la toma de decisiones tras desbridamiento enzimático en pacientes quemados / Cutaneous ultrasonography: and objective tool for decision making after enzymatic debridement in burned patients

Introducción y Objetivo: El desbridamiento enzimático es hoy una herramienta útil en el tratamiento precoz de las quemaduras profundas. Tras el mismo, existen diferentes protocolos de manejo de la herida en las distintas unidades de quemados, consiguiendo en algunos casos la curación espontánea y en otros necesitando injertos de piel. A día de hoy no existe ninguna herramienta objetiva para asegurar el éxito del desbridamiento, ya que el lecho de herida que deja se asemeja a una escara que puede generar confusión sobre la eficacia del producto y el manejo del paciente. El desarrollo de una técnica fiable y objetiva para la medición de la dermis remanente podría ayudar en la toma de decisiones postdesbridamiento y en consecuencia a lograr mejores resultados. Material y Método: Realizamos ultrasonografía (US) cutánea a tiempo real con sondas de alta frecuencia en 15 pacientes, 12 horas tras desbridamiento enzimático con Nexobrid(R), proporcionando imágenes precisas del remanente dérmico. Medimos el grosor de la dermis en regiones que no han sufrido quemaduras y las comparamos con áreas similares desbridadas. Resultados: Todas las US de piel demostraron menor grosor dérmico en las áreas desbridadas que en las zonas no quemadas del mismo paciente. A pesar de que en todos los casos el diagnóstico visual del lecho fue similar a una escara, en un caso la US demostró la práctica ausencia de dermis y en otro persistencia de la escara. A los pocos días, ambos pacientes necesitaron injertos de piel. Todos los casos con suficiente dermis remanente curaron por epitelización espontánea. Conclusiones: La evaluación del lecho de la herida con ultrasonografía tras desbridamiento enzimático, es un método objetivo para valorar la respuesta al tratamiento. Asimismo, la medición de la dermis remanente podría proporcionar parámetros reales para predecir las oportunidades de epitelización espontánea o la necesidad de injertos de piel en pacientes quemados

Background and Objective: Enzymatic debridement is an important tool in early treatment of deep burns nowadays. After it, different protocols in management of the wound bed is done in burn care units getting in some cases spontaneous healing and in others needing skin grafts. To date, there is no objective tool to ensure the success of debridement, since the remaining wound bed resembles an eschar that can generate confusion about the efficacy of the product and patient's management. The development of a reliable and objective technique for the measurement of the remaining dermis could help in the postdebridement decision making and consequently, to achieve better results. Methods: Real-time ultrasonography (US) with high-frequency probes was performed in 15 patients 12 hours after enzymatic debridement with Nexobrid(R), providing accurate images of the dermal remnant. We measured dermis thickness in non-burned regions and compared them with similar debrided areas. Results: All the US skin showed less skin thickness in the debrided areas than in the non-burned areas of the same patient. Despite the fact that in all cases the visual diagnosis resembled an eschar, in one case the US showed the absence of dermis and in another persistence of the eschar. Within a few days, both patients needed skin grafts. All cases with enough remaining dermis healed by spontaneous epithelialization. Conclusions: The evaluation of the wound bed with ultrasonography after enzymatic debridement is an objective method to assess the response to treatment. Also, the measurement of the remaining dermis could provide real parameters to predict chances for spontaneous epithelialization or the need for skin grafts in burned patients

Respuesta al comentario del Dr. Cárdenas-Mejía / No disponible

No disponible