Interactive AI assisted pediatric burn assessment based on smartphone images

Introduction Accurate burn assessment is crucial to prescribing appropriate treatment and is dependent upon the experience of the provider and the timing of diagnosis relative to the burn injury evaluation. Differentiating between a deep partial thickness and full thickness burn may not be easily discernible. To augment the clinical diagnosis of burn depth, a laser doppler image measures the microvascular blood flow of injured tissue to predict burn wound healing. The aim of this study is to evaluate the clinical assessment of burn wounds by experienced burn providers compared to the laser doppler image assessment in predicting which burn wounds should heal spontaneously in 3 weeks. Methods A retrospective chart review from 2012–2016, included 54 subjects. The clinical assessment included a description of burn variables relevant to the determination of spontaneous burn wound healing (burn depth, total body surface area, mechanism of injury, anatomical location, clinical burn depth diagnosis, and laser doppler image). A chi-square analysis compared the clinical diagnosis and the laser doppler assessment of burn wound depth, as well as the correlation between clinical diagnosis versus laser doppler image in predicting spontaneous burn wound healing. Results Comparing partial thickness burn injuries, there were 38 clinically diagnosed partial thickness injuries (by experienced burn providers) and 38 partial thickness burn injures diagnosed via LDI. Deep partial thickness burn injuries were diagnosed clinically in 9 subjects, compared to 10 via LDI. Full thickness burn injuries were diagnosed clinically in 7 subjects and 6 via LDI. A chi-square test was performed to examine the relationship between clinical diagnosis of burn depth and laser doppler image. The relation between these variables was significant,X2= 26.884, p< .000. Comparing clinically diagnosed burn depth to LDI, each approach (clinical or LDI) diagnosed 42 subjects with partial thickness or deep partial thickness burn injuries and all healed spontaneously. Two of the clinically diagnosed full thickness burn injuries required skin grafting. Six patients were lost to follow-up (X2= 17.745, p < .001). Conclusions This study confirms there is no difference between an experienced burn provider’s clinical diagnosis of burn wound depth and prognosis for spontaneous healing compared to a laser doppler image prognosis of burn wound healing. Applicability of Research to Practice In an era of advanced technologies, expert clinical bedside assessment is the standard of care.

Human beings learn efficiently from limited information, whereas supervised machine learning requires vast data. One of the reasons is that humans have acquired prior knowledge about the world, which provides the person with a head-start to learn quickly. In machine learning, we are also faced with the problem of having limited data in the medical domain. Annotated medical data is scarce and costly to acquire. We address data insufficiency in a specific domain for medical imaging, such as brain imaging, by relying on the strength of unsupervised deep learning. This thesis applies brain tumour and lesion segmentation obtained from various brain imaging sources. It is a crucial task in neuroimaging analysis, but supervised methods require large, annotated datasets, which are often limited in acquisition. This work established several approaches to address this limitation. Firstly, we introduced a novel Hybrid UNet Transformer (HUT) network that combines the UNet and the Transformer models. The Convolutional Neural Network (CNN) in the UNet has distinct inductive biases such as local correlation, spatial relationship, and invariance to translation. The Transformer, on the other hand, was originally applied to natural language processing (NLP). It is primarily constructed for sequence-to-sequence tasks. It uses self-attention mechanisms to correlate the importance of the embeddings in the sequence. In addition, it is designed to handle long-range dependencies between the embeddings. In the Vision Transformer, the images are sliced into smaller patches represented as the embeddings via an encoder. The ViT is not data efficient and, therefore, relies on the efficacy of the UNet for more efficient training. Both architectures in the HUT system run in tandem. The Transformer produces the output of different resolutions and fuses it with the UNet at part of its decoder stage. We established a data-efficient system that helps with training when the dataset is smaller. Experimental results on benchmark datasets demonstrate the superiority of HUT over the state-of-the-art methods, which achieves a 0.96% improvement in the Dice score and a 4.1% reduction in the Hausdorff Distance score on the BraTS20 dataset for the brain tumour segmentation. It attains a 4.84% improvement in Dice score and 40.7% reduction in Hausdorff Distance score on the ATLAS dataset for the brain lesion segmentation. HUT gains a 3.3% improvement in Dice score and a 12.5% reduction in Hausdorff Distance score on the ISLES2018 dataset. Secondly, we extend the HUT system with a novel Noise-induced Self-Supervised (NSS) method, also known as an unsupervised approach, introduced in this work using a noise anchor and assumes the model is an energy spectral density model. The method is applied in the pre-training process of the HUT system to address the challenge of small datasets. With the proposed method, the pre-trained network achieves better separation of clusters, as shown in a simple MNIST experiment. This approach improves the network's ability to learn from limited data and increases the system's robustness by preventing overfitting during the training when the data is scarce. The pre-trained network can be deployed on downstream tasks like brain lesion segmentation. We experimented on the smaller ISLES2018 dataset to demonstrate the method's effectiveness. The self-supervised HUT-NSS version outperforms its supervised counterpart and state-of-the-art networks, even with limited annotated data, and achieves a 2.4% improvement in Dice score on average. It produces a 7.2% improvement in Dice score and 28.1% reduction in Hausdorff Distance score on the ISLES2018 dataset with 50% annotated data. The method acquires a 7.87% improvement in Dice score with 10% annotated data and 5.34% improvement in Dice score with 1% annotated data. To put it concisely, the work paves the way for improving learning efficiency on brain image segmentation when the dataset is limited.

The clinical assessment of depth of burns misdiagnosed in up to 35% of cases, especially in the early stages of thermal trauma to the 5th postoperative day. The correct determination of the depth of burns is crucial for planning the adequate therapeutic approach, ie, conservative or surgical treatment of burn wounds. Four basic grades of burn depth are distinguished cliniccaly. Grade I, IIa, IIb can be treated conservatively. Grade III and IV, but also some deeper grade IIb should be operated. Burns IIb cause the most diagnostic difficulties and the indications for surgical treatment is determind by depth of corium affection, which correlates with blood circulation in the dermis and the length of healing. Clinically, it is very difficult to estimate the depth of the affected dermis. LDI, laserdoppler imaging is the one of the ways to objectively and non-invasively assess the depth of the burns. LDI is an imaging technique that uses a laser radiation and the Doppler effect to detect blood flow in the skin capillaries. When thermal trauma directly damages the walls of capillaries, the subsequent tissue necrosis occures. Specificity and sensitivity of LDI in determining of the burn depth states 95% [1]. In our work, we propose a diagnostic algorithm for evaluation of capillary perfusion measured by LDI. Testing can be done up to 9th posttraumatic day, taking into account the current day after the accident. LDI is a suitable tool for the indication of surgical treatment. The following procedures should facilitate this process.

The main technique for assessing the depth of burn lesions in the majority of specialized medical facilities is still the visual examination of a lesion and the assessment of the condition of its floor. The accuracy of currently available techniques for the objective assessment of the depth of burns is not more than 70%. Modern approaches to the treatment of large dermal burns imply that surgery is performed within 24 h and thus require accurate estimates of the depth of a thermal lesion. The aim of the present work was to assess the accuracy of estimating the depth of burn wounds based on laser doppler flowmetry data. Burn wounds were examined in operation rooms according to «Protocol for the Diagnostics of the Depth of Burns in Victims of Explosions of Methane-and-Coal Dust Mixtures» suggested by the present authors. The results of treatment of 115 miners admitted to the Department of Burns in 2004-2012 were analyzed. The suggested technique for estimating the depth of burn wounds is based on the use of laser doppler flowmetry for assessing capillary blood flow in the upper layers of derma. The technique made it possible to increase the accuracy of diagnostics of surface burns and deep burns by more than 1% and by 0,7% of whole body area, respectively, compared with the cases where the depth of burns was assesses based on clinical cues only. Thus, the use of laser doppler flowmetry makes it possible to significantly reduce inaccuracies in the determination of burn wound depth and to optimise treatment regimens.

Burn injuries are a significant challenge in clinical and military settings, requiring accurate and timely assessment to guide treatment. Traditional methods for determining burn depth, a key factor in severity, rely heavily on subjective evaluation, leading to variability and delays in decision-making. Advances in Artificial Intelligence (AI) offer solutions to improve diagnostic accuracy and standardization. This study aims to evaluate the diagnostic performance of an AI model for burn depth assessment by comparing its outputs against a gold standard-focusing on image-based diagnosis of burn type and depth. This study analyzed 29 burn patients, under an Institutional Review Board-approved protocol (IRB# 12,689) at the Eskenazi Burn Center, Indianapolis. Digital images of burns were collected and classified into 3 burn depth categories: first-degree, second-degree, and third-degree. The AI model was fine-tuned on 131 annotated digital images, augmented to 1,200 using techniques such as rotation, flipping, and brightness adjustment. Style transfer using a machine learning models (called GAN) was used to further enhance the dataset by simulating burn variations. Zero-shot (meaning no previous training) segmentation, employing pretrained foundation models, was used to localize burn regions without task-specific training. The proposed AI prediction model achieved 79% accuracy in classifying 3 burn depth categories. Data augmentation improved performance, while segmentation demonstrated strong utility, particularly in identifying burn regions effectively in diverse scenarios. Style transfer augmented the dataset by simulating realistic burn appearances, further enhancing model robustness. Zero-shot segmentation, meaning it identified burn areas without any prior training on similar images, successfully localized burn regions, aligning with clinical expectations. This study highlights the potential of AI in improving burn depth classification and segmentation. The results demonstrate that integrating AI-driven models into clinical care can enhance diagnostic accuracy, efficiency, and scalability, offering transformative tools for clinical and military applications in burn care. These methods provide a foundation for automated and standardized burn assessment, improving outcomes across diverse settings.

Burn Wound Infection (BWI) is primarily caused by aerobic bacteria followed by fungi, anaerobes and viruses. There has been a worldwide decrease in incidence of bacterial infections in burns due to better patient care and availability of effective antibiotics. Consequently, the fungal burn wound infection has shown an increasing trend. The aim of study was to assess the frequency of fungal infections in thermal burn wounds with respect to age of wounds, total body surface involved, depth of burns and to assess common fungal pathogens. The study was conducted on 50 patients admitted with thermal burn wounds having 20-60% burns in the surgical unit. Pus swab and scrapings were taken under local anaesthesia from each burn patient. Scrapings were put in a sterile container and sent to Mycology section of Microbiology department and were examined by direct microscopy and culture studies on Sabouraud's Dextrose Agar medium in the Mycology section of Microbiology department. In our study, the incidence of fungal infection in burn wound patients came out to be 26%. The incidence of fungal infection increased with increase in Total Body Surface Area, (TBSA) increase in depth and age of burn. In our study, the maximum positive fungal cultures were seen in the third week of post-burn period. No positive culture was seen in the first week and 30.76% positive fugal cultures were seen in second post-burn week. Candida albicans was found to be the most common organism followed by Non-albicans Candida and Aspergillus. It was concluded from the study that incidence of fungal infections in thermal burns increased with increase in post-burn period and with increasing depth and TBSA of burns. Candida albicans was found to be the most common fungus.

Objective: To establish an artificial intelligence burn depth recognition model based on convolutional neural network, and to test its effectiveness. Methods: In this evaluation study on diagnostic test, 484 wound photos of 221 burn patients in Xiangya Hospital of Central South University (hereinafter referred to as the author's unit) from January 2010 to December 2019 taken within 48 hours after injury which met the inclusion criteria were collected and numbered randomly. The target wounds were delineated by image viewing software, and the burn depth was judged by 3 attending doctors with more than 5-year professional experience in Department of Burns and Plastic Surgery of the author's unit. After marking the superficial partial-thickness burn, deep partial-thickness burn, or full-thickness burn in different colors, the burn wounds were cut according to 224×224 pixels to obtain 5 637 complete wound images. The image data generator was used to expand images of each burn depth to 10 000 images, after which, images of each burn depth were divided into training set, verification set, and test set according to the ratio of 7.0∶1.5∶1.5. Under Keras 2.2.4 Python 2.8.0 version, the residual network ResNet-50 of convolutional neural network was used to establish the artificial intelligence burn depth recognition model. The training set was input for training, and the verification set was used to adjust and optimize the model. The judging accuracy rate of various burn depths by the established model was tested by the test set, and precision, recall, and F1_score were calculated. The test results were visualized to generate two-dimensional tSNE cloud chart through the dimensionality reduction tool tSNE, and the distribution of various burn depths was observed. According to the sensitivity and specificity of the model for the recognition of 3 kinds of burn depths, the corresponding receiver operator characteristics (ROC) curve was drawn, and the area under the ROC curve was calculated. Results: (1) After the testing of the test set, the precisions of the artificial intelligence burn depth recognition model for the recognition of superficial partial-thickness burn, deep partial-thickness burn, or full-thickness burn were 84% (1 095/1 301), 81% (1 215/1 499) and 82% (1 395/1 700) respectively, the recall were 73% (1 095/1 500), 81% (1 215/1 500) and 93% (1 395/1 500) respectively, and the F1_scores were 0.78, 0.81, and 0.87 respectively. (2) tSNE cloud chart showed that there was small overlapping among different burn depths in the test results for the test set of artificial intelligence burn depth recognition model, among which the overlapping between superficial partial-thickness burn and deep partial-thickness burn and that between deep partial-thickness burn and full-thickness burn were relatively more, while the overlapping between superficial partial-thickness burn and full-thickness burn was relatively less. (3) The area under the ROC curve for 3 kinds of burn depths recognized by the artificial intelligence burn depth recognition model was ≥0.94. Conclusions: The artificial intelligence burn depth recognition model established by ResNet-50 network can rather accurately identify the burn depth in the early wound photos of burn patients, especially superficial partial-thickness burn and full-thickness burn. It is expected to be used clinically to assist the diagnosis of burn depth and improve the diagnostic accuracy.

Wound area segmentation really progressed with the emergence of deep learning, due to its robustness in uncontrolled lighting and no need to design hand-crafted features but two limits have still to be overcome: firstly, its performance relies on the size and quality of the training dataset in the medical field, where data annotation is costly and time-consuming; secondly the accuracy of the segmentation depends highly on the camera distance and angle and moreover perspective effects prevent measuring real surfaces in single views. To address concurrently these two issues, we propose to apply multi-view modeling: an image sequence is acquired around the wound site and enables wound 3D reconstruction. Then, a segmentation step is run to extract roughly the wound from the background in each view and to select the best view with an original strategy. This view provides the most accurate segmentation and the real wound bed area even on non planar wounds. Finally, this segmentation is backprojected in each view to generate a complete set of well annotated real images to reinforce the learning step of the neural network. In our experiments, we compare several strategies to select the best view in the image sequence. The proposed method, tested on a dataset of 270 images, outperforms standard deep learning approach based on a single view, as recorded with DICE index and IoU score which rise respectively from 36.53% to 86.3% and 29.48% to 77.09% for the wound class to achieve an overall DICE and IoU score of 93.04% and 86.61% including background class. These results attest to the robustness of our method and its improved accuracy in the wound segmentation task.

Burn wound depth assessments are an important component of determining patient prognosis and making appropriate management decisions. Clinical appraisal of the burn wound by an experienced burn surgeon is standard of care but has limitations. IR thermography is a technology in burn care that can provide a non-invasive, quantitative method of evaluating burn wound depth. IR thermography utilizes a specialized camera that can capture the infrared emissivity of the skin, and the resulting images can be analyzed to determine burn depth and healing potential of a burn wound. Though IR thermography has great potential for burn wound assessment, its use for this has not been well documented. Thus, we have conducted a systematic review of the current use of IR thermography to assess burn depth and healing potential. A systematic review and meta-analysis of the literature was performed on PubMed and Google Scholar between June 2020-December 2020 using the following keywords: FLIR, FLIR ONE, thermography, forward looking infrared, thermal imaging + burn*, burn wound assessment, burn depth, burn wound depth, burn depth assessment, healing potential, burn healing potential. A meta-analysis was performed on the mean sensitivity and specificity of the ability of IR thermography for predicting healing potential. Inclusion criteria were articles investigating the use of IR thermography for burn wound assessments in adults and pediatric patients. Reviews and non-English articles were excluded. A total of 19 articles were included in the final review. Statistically significant correlations were found between IR thermography and laser doppler imaging (LDI) in 4/4 clinical studies. A case report of a single patient found that IR thermography was more accurate than LDI for assessing burn depth. Five articles investigated the ability of IR thermography to predict healing time, with four reporting statistically significant results. Temperature differences between burnt and unburnt skin were found in 2/2 articles. IR thermography was compared to clinical assessment in five articles, with varying results regarding accuracy of clinical assessment compared to thermography. Mean sensitivity and specificity of the ability of IR thermography to determine healing potential <15 days was 44.5 and 98.8 respectively. Mean sensitivity and specificity of the ability of FLIR to determine healing potential <21 days was 51.2 and 77.9 respectively. IR thermography is an accurate, simple, and cost-effective method of burn wound assessment. FLIR has been demonstrated to have significant correlations with other methods of assessing burns such as LDI and can be utilized to accurately assess burn depth and healing potential.

Introduction Accurate assessment and early interventions in the field are crucial to the prognosis of burn injuries. Studies have indicated that up to 35% of burn patients are inappropriately transferred to hospitals. In some pediatric burns, reports have suggested the total burn surface area (TBSA) has been overestimated as much as 44%. First responders play a pivotal role in the assessment and management of burn injuries, especially in remote areas. An intuitive mobile application that incorporates the standardized practices of Advanced Burn Life Support (ABLS) with integrated artificial intelligence (AI) to assist in burn size, depth, and management is needed. Methods The mobile application was designed with an experienced team of burn specialists, physicians, and software engineers to identify the gaps in first responder burn care and to standardize methods for initial burn assessment. Previously assessed burn photos were characterized based on their depth into split partial thickness, deep partial thickness, and full thickness burns. Laser doppler imaging taken at the time of clinical assessment confirmed the burn depth. These images were used to build a convolutional neural network from to predict burn depth and boundaries. Results An AI-integrated mobile application was developed encompassing a primary survey with management solutions with the fundamentals based on ABLS. The application ensures the collection of pertinent information for burns, such as the patient's weight for calculating fluid resuscitation and provides recommendations based on burn depth and surface area. Photos taken using the mobile device can be analyzed by the AI in real time to aid in burn assessment. The accuracy of the prototype AI model can in distinguish severity assessment with an F1 accuracy score of 78% with a receiver operating characteristic of 85%. Furthermore, the model has a 92% accuracy for determining the boundaries of the burn. Conclusions A smartphone burn application provides an integrated way to improve the efficiency and accuracy of first responders to assess, manage, and triage burns before reaching the hospital. Through the application, management recommendations are tailored to the extent of the injury and provides a detailed report to secondary healthcare providers. Applicability of Research to Practice A state-of-the-art burn application can be a tool that can be used by first responders to capture essential data while ensuring the accuracy of the initial assessment. The integration of artificial intelligence will help personalize and streamline the management pathway improving communication between field and hospital care providers and improving patient care.

Early excision and grafting of full thickness burns has been shown to decrease morbidity and mortality. Errors made in assessing acute burn depth are common and result in prolonged hospitalization in expectant healing of full-thickness burns and in unnecessary excision and grafting of potentially regenerative partial-thickness burns. High-frequency ultrasonic imaging may be a noninvasive, convenient means of quantitating burn depth. A depth analysis system for imaging burned skin was developed using a high-frequency 18.5 MHz (nominal 25 MHz) pulse-echo ultrasound system with a longitudinal resolution of 86 mu. Five adult mini-swine (15 kg) were burned with a temperature-(190 degrees C) and pressure-controlled (236 g/cm2) burning iron. A series of burn durations (1-45 seconds) was used to inflict partial- and full-thickness burns of various depths. Ultrasonic scans of the acutely excised burns were performed across the lateral margin of the burn, including adjacent normal skin to serve as control. Direct histologic comparison was made with each scan plane. Average burn and normal skin depth measurements were made by independent observers for 34 scans and corresponding histologic sections. A significant correlation was achieved between burn depth and percent burn (burn depth/adjacent normal skin depth) as measured by ultrasound and histology (R = 0.90, t = 11.2, P less than .001).

Introduction Early determination of burn depth is essential for guiding proper treatment of burn injuries. The primary technique used to evaluate burn depth is visual assessment, relying heavily on subjective interpretation while risking over-excision. Second window indocyanine green (SWIG) is a novel method of delayed fluorescence imaging with possible utility in burn surgery, as indocyanine green (ICG) persists in burn wounds 24 hours after intravenous injection. The objective of this study is to correlate intraoperative SWIG florescence with burn depth as evaluated by lactate dehydrogenase (LDH) staining. Additionally, given inflammation is thought to impact the progression of a burn, we investigated the relationship between SWIG florescence signal and reactive inflammation. Methods Consented patients with indeterminate depth burns received a 5 mg/kg ICG infusion during their third daily burn care after admission or 24-hours prior to surgery. SWIG was performed 24 hours after ICG injection on a region of interest (ROI) during wound care or during burn excision. A full thickness skin biopsy was taken from the center of the ROI and processed for ICG microscopy and staining. Burn depths were scored using LDH-stained sections. To investigate the relationship between SWIG and inflammation, nude mice underwent a full thickness contact burn or received endotoxin to induce inflammation. Mice were injected with ICG at 5mg/kg and SWIG signal was captured at the non-burned control, burned, and inflamed ROIs 24 hours after injection. Signal-background ratio (SBR) was calculated using the ratio between the averaged ICG intensity in the burned or inflamed ROI and the control ROI. GraphPad Prism 8.0 was used for statistical analyses. Results There was no correlation between the raw SWIG fluorescence value of the ROI in vivo and burn depth as determined by LDH staining. Furthermore, when the fluorescence value of the ROI was normalized to the SWIG intensity of the overall image and the SWIG intensity of non-burn control skin, there was no correlation to burn depth. In mice, SWIG SBR was significantly higher in the burned region (3.2±0.5) compared to the endotoxin induced inflamed regions (1.6±0.1). Conclusions There is heterogeneity in the intraoperative fluorescence signal when compared to burn depth. This variability in fluorescence signal could be attributed to the effects of local inflammation on the burn wound microenvironment as animal studies have shown that ICG signal is present in non-burn inflamed tissue. Further studies are warranted to discern the role of inflammation on burn wound progression and fluorescence signal in humans. Applicability of Research to Practice This data supports the potential utility of perioperative ICG fluorescence imaging for guidance of surgical excision in patients with indeterminate depth burns.

Hand burns are common in the pediatric population. Optimal hand function is a crucial component of a high-quality survival after burn injury. This can only be achieved with a coordinated approach to the injuries. The aim of this study was to review the management algorithm and outcomes of pediatric hand burns at our institution. In total, 70 children fulfilling our study criteria were treated for a burn hand injury in our Burn Care Center between January 2008 and May 2013. 14 of the 70 pediatric patients underwent surgery because of the depth of the hand burns. The management algorithm depending on the depth of the burn is described. Two patients underwent correction surgery due to burn contractures later. For a successful outcome of the burned hand, the interdisciplinary involvement and cooperation of the plastic and pediatric surgeon, hand therapist, burn team, patient and their parents are crucial.

Introduction:Laser Doppler imaging (LDI) is the ‘gold standard’ tool for the assessment of burn depth. However, it is costly. The FLIR ONE is a novel, mobile-attached, thermal imaging camera used to assess burn wound temperature. This study compares the FLIR ONE and LDI in assessing burn depth and predicting healing times.Methods:Forty-five adult patients with burn wounds, presenting at 1–5 days, were imaged with the FLIR ONE and LDI. Infected, chemical and electrical burns were excluded. Healing potential was determined by comparing wound and normal skin temperature for the FLIR ONE and blood flow changes with the LDI. Healing potential was categorised into wounds healing in less than and over 21 days. Pearson’s test was used to determine the correlation between changes in wound temperature and healing potential.Results:Percent total body surface area (%TBSA) was in the range of 0.5–45. FLIR demonstrated a sensitivity of 66.67% and specificity of 76.67% in predicting healing within 21 days, while LDI demonstrated a sensitivity of 93.33% and specificity of 40%. The FLIR ONE showed a significant difference in the mean temperature changes between burns that healed in less than (0.1933 ± 0.3554) and over 21 days (–1 ± 0.4329) (P = 0.04904). Pearson’s test showed a significant correlation between the difference in wound and normal skin temperature with healing times (P = 0.04517).Conclusion:The inexpensive FLIR ONE shows a significant correlation between changes in wound temperature and healing times. It is useful in predicting healing within 21 days. However, evaporative cooling at the wound surface can lead to overprediction of healing times and overtreatment.Lay Summary Background Laser Doppler imaging is currently the main tool for burn depth assessment. It works by analysing the blood flow in a burn wound. Based on these findings, it can predict the depth of the burn injury and predict if it will heal in less than or over 21 days. The main problem is that it is costly. The FLIR ONE is a novel, mobile-attached, thermal imaging camera. It can be used to assess burn depth by comparing the temperature of the burn wound to the surrounding normal skin. This information can then be used to predict healing times into less than and over 21 days. The issue being explored The usefulness of the FLIR ONE in assessing burn depth and predicting healing time when compared to the LDI. How was the work conducted? Forty-five adult patients who sustained a burn injury within the last five days were imaged with both the FLIR ONE and LDI. Those with infected, electrical or chemical burns were excluded. Healing potential was determined by comparing the temperature of the burn wound with normal skin for the FLIR ONE and by changes in wound blood flow with the LDI. Healing potential was categorised into wounds healing in less than and over 21 days. The correlation between the temperature changes of the burn wound and healing time was evaluated for the FLIR ONE. What we learned from the study This study was able to demonstrate that the FLIR ONE showed a significant correlation between the temperature difference between the burn wound and normal skin with healing times. When compared with the LDI, the FLIR ONE was useful in predicting if a burn wound will heal in less than 21 days. The FLIR ONE has advantages over the LDI, it is low cost, portable and produces instantaneous images. Ultimately, this developing technology may increase access to higher standard burn care in centres where LDI is not affordable.

Porcine models are frequently used for burn healing studies; however, factors including anatomic location and lack of standardised wound methods can impact the interpretation of wound data. The objectives of this study are to examine the influence of anatomical locations on the uniformity of burn creation and healing in porcine burn models. To optimise burn parameters on dorsal and ventral surfaces, ex vivo and in situ euthanized animals were first used to examine the location-dependence of the burn depth and contact time relationship. The location-dependent healing in vivo was then examined using burn and excisional wounds at dorsal, ventral, caudal and cranial locations. Lactate dehydrogenase (LDH) and H&E were used to assess burn depth and wound re-epithelialization. We found that burn depth on the ventral skin was significantly deeper than that of the dorsal skin at identical thermal conditions. Compared with burns created ex vivo, burns created in situ immediately post-mortem were significantly deeper in the ventral location. In live animals, 2 out of 12 burn wounds were fully re-epithelialized after 14 days in contrast to complete re-epithelialization of all excisional wounds. Among the burn wounds, those at the cranial-dorsal site exhibited faster healing than at the caudal-dorsal site. This study showed that anatomical location is an important consideration for the consistency of burn depth creation and healing. These data support symmetric localization of treatment and control for comparative assessment of burn healing in porcine models to prevent misinterpretation of results and increase the translatability of findings to humans.