A Deep Learning Image-to-Image Translation Approach for a More Accessible Estimator of the Healing Time of Burns.

OBJECTIVE: An accurate and timely diagnosis of burn severity is critical to ensure a positive outcome. Laser Doppler imaging (LDI) has become a very useful tool for this task. It measures the perfusion of the burn and estimates its potential healing time. LDIs generate a 6-color palette image, with each color representing a healing time. This technique has very high costs associated. In resource-limited areas, such as low- and middle-income countries or remote locations like space, where access to specialized burn care is inadequate, more affordable and portable tools are required. This study proposes a novel image-to-image translation approach to estimate burn healing times, using a digital image to approximate the LDI. METHODS: This approach consists of a U-net architecture with a VGG-based encoder and applies the concept of ordinal classification. Paired digital and LDI images of burns were collected. The performance was evaluated with 10-fold cross-validation, mean absolute error (MAE), and color distribution differences between the ground truth and the estimated LDI. RESULTS: Results showed a satisfactory performance in terms of low MAE ( 0.2370 ±0.0086). However, the unbalanced distribution of colors in the data affects this performance. SIGNIFICANCE: This novel and unique approach serves as a basis for developing more accessible support tools in the burn care environment in resource-limited areas.

U-Net based Mapping from Digital Images to Laser Doppler Imaging for Burn Assessment.

The incidence of burn injuries is higher in low-and middle-income countries, and particularly in remote areas where the access to specialized burn assessment, care and recovery is limited. Given the high costs associated with one of the most used techniques to evaluate the severity of a burn, namely laser Doppler imaging (LDI), an alternative approach could be beneficial for remote locations. This study proposes a novel approach to estimate the LDI from digital images of a burn. The approach is a pixel-wise regression model based on convolutional neural networks. To minimize the dependency on the conditions in which the images are taken, the effect of two image normalization techniques is also studied. Results indicate that the model performs satisfactorily on average, presenting low mean absolute and squared errors and high structural similarity index. While no significant differences are found when changing the normalization of the images, the performance is affected by their quality. This suggests that changes in the intensity of the images do not alter the relevant information about the wound, whereas changes in brightness, contrast and sharpness do.

Partial Nephrogenic Diabetes Insipidus in a Burned Patient Receiving Sevoflurane Sedation With an Anesthetic Conserving Device-A Case Report.

OBJECTIVE: To describe a case of partial nephrogenic diabetes insipidus in a burned patient after prolonged delivery of low inspired concentrations of sevoflurane via an Anesthetic Conserving Device. DATA SOURCES: Clinical observation. STUDY SELECTION: Case report. DATA EXTRACTION: Relevant clinical information. DATA SYNTHESIS: A 34-year-old man was admitted with burns covering 52% of his total body surface area. Mechanical ventilation was provided during sedation with continuous infusions of sufentanil and midazolam. Sedation became increasingly difficult, and in order to limit administration of IV agents, sevoflurane was added to the inspiratory gas flow. This was provided using an Anesthetic Conserving Device and continued for 8 days. The patient rapidly developed polyuria and hypernatremia with an inappropriate decrease in urinary osmolality. Administration of desmopressin resulted in only a modest effect on renal concentrating ability. After cessation of sevoflurane, all variables returned to normal within 5 days. The results of further investigations (cerebral computed tomographic scan, cerebral magnetic resonance imaging, and serum arginine vasopressin concentration) were compatible with a diagnosis of partial nephrogenic diabetes insipidus. The temporal sequence of clinical findings in relation to sevoflurane administration suggests that the sevoflurane was the probable underlying cause. CONCLUSIONS: Clinicians should be aware of the possibility of sevoflurane-induced diabetes insipidus not only during general anesthesia but also in the intensive care setting of sedation in critically ill patients. This is especially important in patients, such as those with severe burns, in whom preserved renal concentrating ability is important to ensure compensation for extrarenal fluid losses.

Molecular Epidemiology and Clinical Impact of Acinetobacter calcoaceticus-baumannii Complex in a Belgian Burn Wound Center.

Multidrug resistant Acinetobacter baumannii and its closely related species A. pittii and A. nosocomialis, all members of the Acinetobacter calcoaceticus-baumannii (Acb) complex, are a major cause of hospital acquired infection. In the burn wound center of the Queen Astrid military hospital in Brussels, 48 patients were colonized or infected with Acb complex over a 52-month period. We report the molecular epidemiology of these organisms, their clinical impact and infection control measures taken. A representative set of 157 Acb complex isolates was analyzed using repetitive sequence-based PCR (rep-PCR) (DiversiLab) and a multiplex PCR targeting OXA-51-like and OXA-23-like genes. We identified 31 rep-PCR genotypes (strains). Representatives of each rep-type were identified to species by rpoB sequence analysis: 13 types to A. baumannii, 10 to A. pittii, and 3 to A. nosocomialis. It was assumed that isolates that belonged to the same rep-type also belonged to the same species. Thus, 83.4% of all isolates were identified to A. baumannii, 9.6% to A. pittii and 4.5% to A. nosocomialis. We observed 12 extensively drug resistant Acb strains (10 A. baumannii and 2 A. nosocomialis), all carbapenem-non-susceptible/colistin-susceptible and imported into the burn wound center through patients injured in North Africa. The two most prevalent rep-types 12 and 13 harbored an OXA-23-like gene. Multilocus sequence typing allocated them to clonal complex 1 corresponding to EU (international) clone I. Both strains caused consecutive outbreaks, interspersed with periods of apparent eradication. Patients infected with carbapenem resistant A. baumannii were successfully treated with colistin/rifampicin. Extensive infection control measures were required to eradicate the organisms. Acinetobacter infection and colonization was not associated with increased attributable mortality.