Burn Depth Assessment Research Articles

Використання безконтактного термографа FLIR One для оцінювання глибини опікової рани

The treatment of burn injuries is complicated by the proper diagnosis of areas requiring immediate necrectomy (deep burn) and those that can heal on their own (superficial burn). Non-contact thermography using the FLIR One device may be a reliable, non-invasive, and cost-effective method for assessing the depth of thermal injury. Aim - to study the temperature of healthy skin, deep and superficial burns using the FLIR One non-contact thermograph, the temperature difference between them, and the diagnostic value of the method for assessing burn depth. Materials and methods. The study involved 22 patients with limb burns. Thermometry of the affected areas was performed using the FLIR One thermograph within the first 48 hours after injury, before and during wound sanitation, with images analyzed using the FLIR One application. Results. The temperature of healthy skin was 34.7°C (34.4-35.1°C), the temperature of superficial burns was 35.8°C (35.5-36.2°C), and the temperature of deep burns was 32.4°C (32.0-32.8°C). The difference between healthy skin and deep burns was 2.3°C (2.2-2.4°C), and between superficial and deep burns was 3.4°C (3.0-3.8°C). A temperature of 33.7°C with non-contact thermography indicated a deep burn with 95% sensitivity and specificity. A decrease in the temperature of the affected skin by more than 2.0°C compared to healthy skin (2.2-2.4°C) or superficial burns (3.0-3.8°C) also indicated deep thermal damage. Conclusions. Thermography using FLIR One is a reliable and accessible method for analyzing the depth of burn wounds. The temperature of healthy skin during thermography is 34.7°C (34.4; 35.1)°C and is lower than the temperature of superficial burns (35.8°C (35.5; 36.2)°C) but higher than the temperature of deep burns (32.4°C (32.0; 32.8)°C). A temperature of 33.7°C with high sensitivity and specificity indicates a deep burn. The study showed that a temperature decrease of more than 2.0°C compared to healthy skin or superficial burns indicates deep thermal damage. The research was carried out in accordance with the principles of the Declaration of Helsinki. Informed consent of the child and child's parents was obtained for the research. The authors declare no conflict of interest.

Comparing artificial intelligence guided image assessment to current methods of burn assessment.

Appropriate identification of burn depth and size is paramount. Despite the development of burn depth assessment aids [e.g., laser doppler imaging (LDI)], clinical assessment, which assesses partial thickness burn depth with 67% accuracy, currently remains the most consistent standard of practice. We sought to develop an image-based artificial intelligence system that predicts burn severity and wound margins for use as a triaging tool in thermal injury management. Modified EfficientNet architecture trained by 1684 mobile-device-captured images of different burn depths were previously utilized to create a convoluted neural network (CNN). The CNN was modified to a novel Boundary-Attention Mapping (BAM) algorithm using elements of saliency mapping, which was utilized to recognize the boundaries of burns. For validation, 144 patient charts that included clinical assessment, burn location, total body surface area, and LDI assessment were retrieved for a retrospective study. The clinical images underwent CNN-BAM assessment and were directly compared with the LDI assessment. CNN using a four-level burn severity classification achieved an accuracy of 85% (micro/macro-averaged ROC scores). The CNN-BAM system can successfully highlight burns from surrounding tissue with high confidence. CNN-BAM burn area segmentations attained a 91.6% accuracy, 78.2% sensitivity, and 93.4% specificity, when compared to LDI methodology. Results comparing the CNN-BAM outputs to clinical and LDI assessments have shown a high degree of correlation between the CNN-BAM burn severity predictions to those extrapolated from LDI healing potential (66% agreement). CNN-BAM algorithm gives equivalent burn-depth detection accuracy as LDI with a more economical and accessible application when embedded in a mobile device.

Depth of intact vascular plexus- visualized with optical coherence tomography- correlates to burn depth in thoracic thermic injuries in children.

Deep thermal injuries are among the most serious injuries in childhood, often resulting in scarring andfunctional impairment. However, accurate assessment of burn depth by clinical judgment is challenging. Optical coherence tomography (OCT) provides structural images of the skin and can detect blood flow within the papillary plexus. In this study, we determined the depth of the capillary network in healthy and thermally injured skin and compared it with clinical assessment. In 25 children between 7months and 15 years of age (mean age 3.5 years (SD±4.14)) with thermal injuries of the ventral thoracic wall, we determined the depth of the capillary network using OCT. Measurements were performed on healthy skin and at the center of the thermal injury (16 grade IIa, 9 grade IIb). Comparisons were made between healthy skin and thermal injury. The capillary network of the papillary plexus in healthy skin was detected at 0.33 mm (SD±0.06) from the surface. In grade IIb injuries, the depth of the capillary network was 0.36 mm (SD±0.06) and in grade IIa injuries 0.23 mm (SD±0.04) (Mann-Whitney U test: p<0.001). The overall prediction accuracy is 84 %. OCT can reliably detect and differentiate the depth of the capillary network in both healthy and burned skin. In clinical IIa wounds, the capillary network appears more superficial due to the loss of the epidermis, but it is still present in the upper layer, indicating a good prognosis forspontaneous healing. In clinical grade IIb wounds, the papillary plexus was visualized deeper, which is a sign of impaired blood flow.

The effect of anatomic location on porcine models of burn injury and wound healing.

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.

133 Early Assessment of Burn Depth in a Yucatan Minipig Model Using Resonance Raman Spectroscopy

133 Early Assessment of Burn Depth in a Yucatan Minipig Model Using Resonance Raman Spectroscopy

Accuracy of infrared thermography evaluation in burn wound healing: a systematic review and meta-analysis.

Accurate assessment of burn depth and burn wound healing potential is essential to determine early treatments. Infrared thermography (IRT) is a non-invasive and objective tool to do this. This systematic review evaluated the accuracy of IRT to determine burn wound healing potential. This systematic review and meta-analysis used MEDLINE, EMBASE, CINAHL, PEDro, DiTA and CENTRAL databases. IRT data were extracted from primary studies and categorised into four cells (i.e., true positives, false positives, true negatives and false negatives). Subgroup analysis was performed according to methods used to capture thermal images. The search strategy identified 2727 publications; however, 15 articles were selected for review and 11 for meta-analysis. In our meta-analysis, the accuracy of IRT was 84.8% (63% sensitivity and 81.9% specificity). IRT is a moderately accurate tool to identify burn depth and healing potential. Thus, IRT should be used carefully for evaluating burn wounds.

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

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. 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. 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 24h, 48h, and 72h after injury. 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 24h to 72h was evident in the group with skin exposed to 78°C water, suggesting that burn depth was heterogeneous. 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 72h after burn injury in a rat model of scald burn injury.

Medico-legal evaluation of burn trauma injuries. Epidemiological features and predictors of mortality and other adverse outcomes

Introduction: Burn trauma is a devastating, life-threatening public health issue responsible for significant morbidity and mortality. Developing countries suffer more from the medical, psychological, and economic consequences of burns. The current study aimed to investigate the medicolegal aspects of burn trauma by identifying the epidemiological factors and injury characteristics associated with increased risk of mortality, intentional infliction, and different types of complications. Methods: A prospective cross-sectional study was conducted enrolling the burn trauma patients admitted to Burn Unit, Tanta University Hospital, Egypt over one year. Results: The current study was conducted among 138 burn trauma patients with a case fatality rate of 13.8 %. Of them, 5.8 % were victims of intentional burns, 44.9 % were complicated, and the length of hospital stay ranged between one day and 52 days. Patients aged less than 10 years constituted about 33.3 %. The burn trauma was the highest in June, May and March. Intentionally exposed patients, patients with third-degree burns affecting the head, neck and trunk and those with burns involving a total body surface area (TBSA) of more than 33 % were at high mortality risk. Intentional burns were induced mainly by flame (100 %) and characterized by high severity (TBSA = 85 % and 87.5 % third-degree burns). Intentional burns involved mainly the trunk (p = 0.002) and external genitalia (p = 0.022). The involved TBSA and the highest burn degree were significant predictors of mortality with an excellent area under curves of 0.956 and 0.870, respectively and (p < 0.001). The TBSA of more than 17 % and the burn degrees above the second were significant predictors of in hospital complications (p < 0.001). Daytime intentional burns, burns involving the upper extremities and face, deep and widely distributed burns, and infected wounds were associated with a significant need for surgical treatments. The median length of hospital stay was ten days, primarily attributed to the in hospital complications (p = 0.02). Conclusion: A high degree of vigilance and accurate assessment of burn size, depth and distribution with meticulous interpretation of the mechanism of infliction are central not only for treatment interventions but from the medicolegal point of view.

Medical thermography as a method to assessment of burn depth and treatment effectiveness in patients with burn injury

In this revue discuss the usefulness of static and active dynamic thermography for burn depth assessment as well as for estimation of the effectiveness of the different treatment modalities (cell therapy, humid ambience, evaluation of the donor skin area).

Ultrasonography for Skin and Soft Tissue Infections, Noninfectious Cysts, Foreign Bodies, and Burns in the Critical Care Setting.

There are multiple opportunities for the use of ultrasonography in the diagnosis of skin and soft tissue differentials. Ultrasonography is inexpensive, easily reproducible, and able to provide real-time data in situations where condition changes and progression are common. Not only does bedside ultrasonography provide the clinician an in-depth look beyond epidermal structures into body cavities, it remains a safe, nonionizing radiating, effective, cost-efficient, reliable, and accessible tool for the emergency management of life- and limb-threatening integumentary infections. Unnecessary invasive procedures are minimized, providing improved patient outcomes. Integumentary abnormalities secondary to trauma, surgery, and hospitalization are common among critical care patients. This article provides a brief overview and evidence-based recommendations for the use of ultrasonography in the critical care setting for integumentary system conditions, including common skin and soft tissue differentials, foreign bodies, and burn depth assessment.

Photographic Evaluation of Burn Depth via Telemedicine: Insights from Iranian Surgeons.

The accurate assessment of burn depth is crucial for determining appropriate treatment. Telemedicine has emerged as a promising tool for supporting burn diagnosis and decision-making, as it allows for remote consultation with burn specialists and access to high-quality imaging. The aim of this study was to evaluate the diagnostic capabilities of telemedicine in diagnosing burn depth. A total of 15 Iranian surgeons participated in this study; they were presented with 13 images of partial thickness burn ulcers located on the extremities and trunk of patients. The participating surgeons were required to provide their diagnoses of burn type and depth, as well as the necessity of surgical intervention, and their responses were recorded. Data from 11 participants and 143 responses were analyzed. The average diagnostic accuracy for superficial burns was 79.3%, while for deep burns, it was 13.72%. The mean total diagnostic accuracy was 75.2%. The results of this study suggest that photographs can be a reliable diagnostic tool for evaluating superficial burns. However, photographs are neither valid nor reliable for assessing burn depth. These findings have important implications for the use of telemedicine in burn diagnosis and indicate that additional diagnostic tools may be necessary for accurate assessment of deep burns.

47 Burn Injury Assessment Study (BIAS): Is There Room To Improve?

Abstract Introduction The treatment of burn injured patients requires accurate wound assessment to determine appropriate interventions. Clinical assessment of burn depth, even by experts in the field, has an accuracy of only 60–80%. The purpose of this study is to estimate the performance of burn wound assessment by burn care professionals from still images. Methods This was an IRB-approved prospective cohort study in which burn care providers used a tablet-based digital interface to answer a 10-item questionnaire and to identify non-healing burn wounds from 5 patients scenarios. Each wound was evaluated using a polygon software interface to mark non-healing regions within the wound. Each wound had a ground truth determined by a consensus panel of study investigators using still photograph at 21-days post-injury to discern healing and non-healing regions. A power analysis and sample size of 100 participants produced a two-sided 95% confidence interval with a width equal to 0.20 when the sample proportion is 0.60. Continuous variables were analyzed by mean, standard deviations, median and quartiles while categorical data was analyzed as exact number and percentage. Burn wound assessment performance metrics for the providers were calculated for the whole cohort and then for subgroups using point estimate at a pixel level. Accuracy, sensitivity, specificity, area positive predictive value (APPV), and area negative predictive value (ANPV) were calculated from the ground truth and participants selected regions of non-healing wounds. Results One hundred fifty-six healthcare providers enrolled (50 physicians, 14 APPs, 63 nurses, 24 therapists, and 5 paramedics) with 9.96 ± 9.49 mean years of experience and 70% employed at a verified burn center. All five regions were represented in the analysis (Eastern Great Lakes (4%), Midwestern (6.5%), Northeastern (22%), Southern (53.5%), and Western (14%). 29.3% of the participants selected “schedule for surgery” when reviewing images of wounds that healed without surgery. 28.7% of the participants selected, “local wound care no surgery needed or, “local wound care, reassess in 7+ days for possible surgery.” Performance measures were not associated with years of experience. Overall performance is available in Table 1. Conclusions Improving burn wound assessment performance could improve our use of limited resources in burn care by optimizing patient transfers/treatments and avoiding unnecessary surgeries. Our study expands upon prior work in the field and demonstrates that burn wound assessment has significant room for improvement. These findings open the proverbial door for diagnostic devices found in other fields of medicine and our partnership with emergency room providers to advance burn care. Applicability of Research to Practice More accurate wound assessment will lead to improved treatment and triage by EM and Burn practitioners.

72 Multi-Spectral SWIR Imaging in Humans Reveals Correlations with Distinct Skin Burn Depths

Abstract Introduction Burn depth determination is a critical aspect of burn patient care but currently lacks accuracy in clinical practice. We have shown first in animal models and then in a two-patient characterization that Short Wave Infrared (SWIR) imaging, which penetrates tissue better than visual or near-infrared light and is very sensitive to water content, can distinguish between superficial and deep tissue necrosis. Here we present the findings from our pilot study of 10 patients showing the use of multi-spectral SWIR imaging of human burn injury as a potential technique for burn depth determination. Methods Ten patients admitted for mixed depth thermal injuries between 5-40% TBSA were analyzed using our SWIR assessment tool. Prior to burn excision the SWIR system was used to image burn areas and normal skin at 4 different SWIR wavelengths (Figure 1A). Standard photographs from imaged areas were collected and presented for 5 independent, blinded, surgeons’ assessments. Using the visual and SWIR images, 5-15 regions of interest (ROI) were selected from each of the burned areas and normalized to adjacent normal skin and the reflected light intensity in each ROI was averaged at each wavelength. Statistics were done using Mann-Whitney U tests. Results Visual and SWIR images were collected from burn areas in 10 patients for a total of 273 burn ROIs. The ROIs were assessed by the surgeons with ROIs being agreed upon as being superficial or superficial partial thickness (SPT) (n=47), deep partial thickness (DPT) (n=97), or full thickness (FT) (n=129) burns by a majority (60% or above) consensus. As seen in Figure 1B, the reflectance intensities (RIs) from superficial and SPT burns were significantly different than the DPT burns at the 1940 nm wavelength (p=0.05) and significantly different than FT burns at 1200 nm (p=0.008) and 1940 nm (p=0.009). When DPT and FT burns were compared there was a significant difference a 1200 nm (p=0.003) and 2250 nm (p=0.01). Conclusions Here we present a 10 patient SWIR pilot study demonstrating distinct ROIs of SWIR wavelengths for different burn depths based on consensus surgeon assessments. Overall, as burn depth increases, the 1200 and 2250 nm wavelengths show increasing RIs and 1940 nm show decreasing RIs. These results motivate further studies of SWIR imaging including pending histological analysis in the hope to non-invasively and accurately identify operative versus non-operative burns. Applicability of Research to Practice This new SWIR technology may enable us to more objectively assess burn depth, leading to improved surgical decision making and better patient outcomes.

A Hand-Held, Single-Sided NMR Sensor for Full-Thickness Skin Detection

To rapidly assess burn depth, a hand-held, single-sided NMR sensor was designed for full-thickness skin detection. The sensor is composed of a single-sided magnet, a radio frequency coil, a matching circuit, and an aluminum shell. The permanent magnet array was optimized using the sparrow search algorithm with low vertical gradient strength and each layer obtaining maximal uniformity in field of view. The actual measured magnetic field of the single-sided magnet is perfect match with the simulation results. Experimental results of depth–transverse relaxation time(T <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> ) map prove that this sensor has high sensitivity to distinguish deep dermal and full thickness burns and superficial partial-thickness burns.

Development and evaluation of deep learning algorithms for assessment of acute burns and the need for surgery

Assessment of burn extent and depth are critical and require very specialized diagnosis. Automated image-based algorithms could assist in performing wound detection and classification. We aimed to develop two deep-learning algorithms that respectively identify burns, and classify whether they require surgery. An additional aim assessed the performances in different Fitzpatrick skin types. Annotated burn (n = 1105) and background (n = 536) images were collected. Using a commercially available platform for deep learning algorithms, two models were trained and validated on 70% of the images and tested on the remaining 30%. Accuracy was measured for each image using the percentage of wound area correctly identified and F1 scores for the wound identifier; and area under the receiver operating characteristic (AUC) curve, sensitivity, and specificity for the wound classifier. The wound identifier algorithm detected an average of 87.2% of the wound areas accurately in the test set. For the wound classifier algorithm, the AUC was 0.885. The wound identifier algorithm was more accurate in patients with darker skin types; the wound classifier was more accurate in patients with lighter skin types. To conclude, image-based algorithms can support the assessment of acute burns with relatively good accuracy although larger and different datasets are needed.

Burn depth assessment by dual-wavelength light emitting diodes-excited photoacoustic imaging in rats.

Accurate burn depth assessment is crucial to determine treatment plans for burn patients. We have previously proposed a method for performing burn depth assessments based on photoacoustic (PA) imaging, and we have demonstrated the validity of this method, which allows the successful detection of PA signals originating from the blood under the bloodless burned tissue, using rat burn models. Based on these findings, we started a clinical study in which we faced two technical issues: (1) When the burn depth was shallow, PA signals due to skin contamination and/or melanin in the epidermis (surface signals) could not be distinguished from PA signals originating from the blood in the dermis; (2) the size of the system was too large. To solve these issues, we propose a burn depth diagnosis based on dual-wavelength light emitting diodes (LEDs)-excited PA imaging. The use of LEDs rendered the system compact compared to the previous one that used a conventional solid-state laser. We replicated human burned skin by applying a titrated synthetic melanin solution onto the wound surface in albino rat burn models and measured their burn depths by PA excitation at 690 and 850 nm, where melanin and haemoglobin show greatly different absorption coefficients. As a result, the surface signals were eliminated by subtracting the PA signals at 690 nm from those at 850 nm. The resultant estimated burn depths were strongly correlated with the histological assessment results. The validity of the proposed method was also examined using a burn model of rats with real melanin.

Evaluation of Bromelain-Based Enzymatic Debridement Combined with Laser Doppler Imaging and Healing of Burn Wounds.

BackgroundAccurate estimation of burn depth is crucial for correct treatment decision making. Bromelain-based enzymatic debridement (ED) may improve clinical assessment of burn depth. Laser Doppler imaging (LDI) provides a valuable indicator of burn depth by analyzing microcirculation within tissue beds. This study aimed to evaluate bromelain-based enzymatic debridement combined with laser Doppler imaging and healing of 42 wounds in 19 patients with mixed second- and third-degree thermal burns.Material/MethodsWe included 42 wounds in 19 patients with mixed deep dermal and full-thickness thermal burns. All patients were treated with eschar-specific removal agent for ED. The perfusion of each wound after ED was assessed using LDI. Healing time was estimated by 2 experienced burn surgeons and marked by the observation of epithelization. The usefulness of the LDI performed after ED in predicting healing time was estimated. The findings were analyzed to determine a cut-off value for LDI that indicates if a burn will heal spontaneously.ResultsWe observed that burn wounds with higher mean perfusion healed faster. The analysis showed a strong relationship between perfusion after ED and healing time (Spearman rank correlation coefficient=−0.803). A mean perfusion greater than 296.89 indicated that the wound could heal spontaneously and does not require skin grafting.ConclusionsLDI examination of an already debrided wound allows for a reliable assessment of perfusion at an early stage of treatment. The use of a safe and effective debridement method in conjunction with a non-invasive diagnostic tool could improve burn management.

732 Examining Staff Views and Perceptions After Implementation of a Laser Doppler Imaging Device Into Practice

IntroductionLaser doppler imaging (LDI) has been established as an accurate diagnostic tool to assess burn depth and measure healing potential. Despite this, its use in burn centers remain limited. While studies have examined challenges to LDI use, there is a paucity of literature factoring staff views and attitudes as a barrier to implementation into burn practice. The aim of this work was to assess and examine attitudes and perspectives following implementation of an LDI protocol into acute burn injury assessment.MethodsFollowing institutional approval, a 22-question survey was disseminated among staff involved with implementation of an LDI device as a point of care tool to assess acute burn injury at a single ABA verified burn center. The survey focused on questions examining device ease of use, understanding of the underlying LDI technology, interpretation of imaging generation from wounds, and perceptions of patients’ experience. Questions were answered on a standard 5-point Likert scale. All survey data was collected anonymously into an electronic database for assessment.ResultsOverall, there were 15 respondents to the survey questions. Five respondents found the LDI device difficult to use (33%). Barriers to device ease of use included difficulty with device movement (60%), incorporation of scanning into wound care and dressing placement (60%), and management of hardware or software issues that arise during use (60%). Challenges noted by respondents external to device use was mainly high patient census (80%). Despite this, 60% of respondents found the device easier to use after performing several scans in one or more patients and 60% found that scans generated matched their assessment of burn depth. Among respondents, 66% found patients amenable to the scanning process and 80% did not feel that that the scanning process worsened patients’ pain.ConclusionsChallenges in LDI device use, implementation with wound care and dressing placement, and high patient census were identified as barriers to LDI use. Despite this, ease of device use improved with more frequent use. Identification of views and perceptions such as these can lead to protocol changes and additional training that facilitate ease of LDI use. Further examination will be required to better elucidate this information.

55 Initial Experience Using Artificial Intelligence for the Assessment of Pediatric Burn Depth

IntroductionEstimation of burn depth, and hence severity, is critical for burn management. Burn depth estimates vary widely, and these inaccuracies can be compounded in pediatric burns. A reliable, objective, non-invasive device for the accurate assessment of burn depth is needed. A non-invasive imaging technology, using multispectral imaging (MSI) combined with a machine learning algorithm (MLA), is being developed as a tool for burn depth assessment. The results of the initial multi-center study using this artificial intelligence (AI) technology in pediatric burns are presented.MethodsThe MSI device was used to image subjects < 18y of age with thermal burns < 50% TBSA. It captured a set of images measuring the reflectance of visible and near-IR light, within a 23x23 cm field-of-view. Images were collected from up to 2 separate burned regions within 72 hours of injury that were then serially imaged for up to 7d post-injury. Burns that the investigator believed would heal spontaneously (superficial or superficial partial-thickness) were managed per institutional standard of care (SOC) and assessed at 21d post-injury for complete healing. Burns that the investigator felt would not heal by 21d post-injury (deep partial-thickness or full-thickness) were excised and grafted per institutional SOC, with multiple biopsies being taken prior to excision.Regions of non-healing burn within every MSI image were identified by a panel of 3 burn surgeons. To accurately identify these non-healing regions, the panel of surgeons was given access to 1 of 2 clinical reference standards: a) the 21-day healing assessments for burns allowed to heal spontaneously; or b) pathology reports detailing histologic analyses from the biopsies.This information was then used to develop a type of MLA called a convolutional neural network (CNN) that could automatically identify the regions of non-healing burn within an image. From these data, an ensemble of 8 separate CNN algorithms was used to automatically identify non-healing burn tissue. Training and test accuracies of the ensemble CNN were calculated using cross-validation at the level of the subject.ResultsTwenty-four (24) pediatric burn patients were enrolled, with 26 burned areas being serially imaged. The age range of the subjects was 7 months - 17y, with a mean age of 5.7y. Subjects had a mean burn size of 8.0 ± 4.2% TBSA, and 70% of the subjects were male. The AI performance results showed an accuracy of 88.2 ± 3.7%, sensitivity of 80.0 ± 14.6%, specificity of 88.0% ± 3.7%, and an area under the curve (AUC) of 0.92.ConclusionsOur study demonstrates an improvement in the accuracy of burn depth assessment over the traditional exam, which could lead to improved burn care.

Burn depth assessment in tattooed patients

Tattoos are commonly accepted as a lifestyle choice, with an estimated 10-20% of the global population having a tattoo. Burn injuries in tattooed skin can be challenging to assess, and incorrect management can lead to an unnecessary burden on resources. This may lead to preventable patient morbidity. We present a case series of patients presenting to our unit with burn injuries on tattooed skin, and discuss recommendations for assessing and optimising care in this cohort. Four male patients aged 23 to 50 years old are discussed in this study, with burn injuries to limb tattooed skin. One patient underwent surgical management and upon a test shave of the apparent full thickness burn with tattoo pigmentation, showed a bleeding dermis which would indicate a more superficial burn. A second patient had burn depth masked a colour tattoo that mimicked a mid to deep dermal burn. We highlight the difficulties in assessing patients with burn injuries in tattooed skin and the importance of ensuring the correct diagnosis in depth of burn. This is to allow optimal treatment and avoid potential complications that may occur as a result of misdiagnosis.