Deep Learning Assisted Burn Wound Diagnosis (Preprint)

2020 ◽  
Author(s):  
Che Wei Chang ◽  
Feipei Lai ◽  
Mesakh Christian ◽  
Yu Chun Chen ◽  
Ching Hsu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Total Body Surface Area ◽  
Ground Truth ◽  
Burn Patients ◽  
Burn Wound ◽  
Burn Wounds ◽  
Burn Victims ◽  
Step Procedure ◽  
Resuscitation Fluid ◽  
Total Body

BACKGROUND Accurate assessment of the percentage of total body surface area (%TBSA) of burn wounds is crucial in the management of burn patients. The resuscitation fluid and nutritional needs of burn patients, their need for intensive unit care, and probability of mortality are all directly related to %TBSA. It is difficult to estimate a burn area of irregular shape by inspection. Many articles have reported discrepancy in estimating %TBSA by different doctors. OBJECTIVE We propose a method, based on deep learning, for burn wound detection, segmentation and calculation of % TBSA on a pixel-to-pixel basis. METHODS A two-step procedure was used to convert burn wound diagnosis into %TBSA. In the first step, images of burn wounds were collected and labeled by burn surgeons and the dataset was then input into two deep learning architectures, U-Net and Mask R-CNN, each configured with two different backbones, to segment the burn wounds. In the second step, we collected and labeled images of hands to create another dataset, which was also input into U-Net and Mask R-CNN to segment the hands. The percentage of TBSA of the burn wounds was then calculated by comparing the pixels of mask areas on the images of the burn wound and hand of the same patient according to the rule of hand, which says that one’s hand accounts for 0.8% of TBSA. RESULTS A total of 2591 images of burn wounds were collected and labeled to form the burn-wound dataset. The dataset was randomly split into a ratio of 8:1:1 to form the training, validation, and testing sets. Four hundred images of volar hands were collected and labeled to form the hand dataset, which was also split into three sets using the same method. For the images of burn wounds, Mask R-CNN with ResNet101 had the best segmentation result with a Dice coefficient (DC) of 0.9496, while U-Net with ResNet101 had a DC of 0.8545. For the hand images, U-Net and Mask R-CNN had similar performance with a DC of 0.9920 and 0.9910, respectively. Lastly, we conducted a test diagnosis in a burn patient. Mask R-CNN with ResNet-101 had on average less deviation (0.115% TBSA) from the ground truth than burn surgeons. CONCLUSIONS This is one of the first studies to diagnose all depths of burn wounds and convert the segmentation results into %TBSA using different deep learning models. We aimed to assist medical staff in estimating burn size more accurately and thereby helping to provide precise care to burn victims.

scholarly journals A Framework for Automatic Burn Image Segmentation and Burn Depth Diagnosis Using Deep Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Hao Liu ◽  
Keqiang Yue ◽  
Siyi Cheng ◽  
Wenjun Li ◽  
Zhihui Fu
Keyword(s):  
Deep Learning ◽  
Total Body Surface Area ◽  
High Morbidity ◽  
Learning Technology ◽  
Human Errors ◽  
Burn Wounds ◽  
Output Structure ◽  
Network Output ◽  
Total Body ◽  
Burn Depth

Burn is a common traumatic disease with high morbidity and mortality. The treatment of burns requires accurate and reliable diagnosis of burn wounds and burn depth, which can save lives in some cases. However, due to the complexity of burn wounds, the early diagnosis of burns lacks accuracy and difference. Therefore, we use deep learning technology to automate and standardize burn diagnosis to reduce human errors and improve burn diagnosis. First, the burn dataset with detailed burn area segmentation and burn depth labelling is created. Then, an end-to-end framework based on deep learning method for advanced burn area segmentation and burn depth diagnosis is proposed. The framework is firstly used to segment the burn area in the burn images. On this basis, the calculation of the percentage of the burn area in the total body surface area (TBSA) can be realized by extending the network output structure and the labels of the burn dataset. Then, the framework is used to segment multiple burn depth areas. Finally, the network achieves the best result with IOU of 0.8467 for the segmentation of burn and no burn area. And for multiple burn depth areas segmentation, the best average IOU is 0.5144.

564 Managing California’s Creek Fire Mass Casualty’s Incident

2021 ◽  
Vol 42 (Supplement_1) ◽  
pp. S132-S132
Author(s):  
Shana M Henry ◽  
Nicole M Kopari ◽  
Mary Wolfe
Keyword(s):  
Operating Room ◽  
Disaster Response ◽  
Total Body Surface Area ◽  
Burn Patients ◽  
Rescue Operation ◽  
Burn Victims ◽  
Burn Center ◽  
Response Planning ◽  
Response Team ◽  
Total Body

Abstract Introduction California’s Creek Fire is not only the largest single wildfire in a state known for huge and destructive blazes, it spawned two rare fire tornados with winds over 100mph, a day after the fire started in early September. Huntington Lake and Mammoth Pool were the sites of these rare events leading to hundreds of trapped campers. An air rescue operation airlifted hundreds of trapped people to safety. Twenty days after the start of the fire, it had burned >300,000 acres with only 36% containment by fire crews. This review is an evaluation of our hospitals response team and the events surrounding that night. Methods Our on-call surgeon had called in the back-up surgeon to run a second trauma operating room. It was at this time, the news had reported trapped campers near Mammoth Pool. The burn surgeon was notified and reported to the emergency department (ED) as word of 65 possible victims spread. Local disaster response planning was initiated with an ED physician triaging patients at the regional airport. Initial calls were made to the division chief and burn medical director. The nursing director was notified along with any available nursing staff with 8 ICU nurses volunteering to report. Immediately, lateral transfer orders were placed for all burn patients housed in the burn center which has 10 ICU bed capabilities. Results The first helicopter landed with 5 of the burn victims presenting to our hospital. 4 of the victims were male and 1 female with ages ranging from 17 to 27. Total body surface area burn was estimated on each with 2 minor burns < 10% and 3 moderate sized burns of roughly 25%. These patients were quickly triaged in the ED and traumatic injuries evaluated. 3 of the patients were placed in ICU level care with the 2 remaining patients housed in the ED as word trickled in about another rescue effort with an additional 95 people. By morning, an additional 2 patients were transferred to our burn center from the surrounding hospitals and another 2 patients evaluated for burns sustained in separate events. All patients were taken to the operating room over the next 24–48 hours for excision and autologous spray on skin cells (ASCS) in combination with widely meshed skin grafts or ASCS alone. Conclusions Communication, teamwork, and personnel that are dedicated to the care of burn patients made this tragic incident manageable. The Creek Fire hit home for many of the burn staff not only because of the patients that were cared for, but because this area of California was a beloved respite for many. A debriefing with a chaplain, grief counselor, and psychotherapist, was held within 2 weeks of the incident to provide support to the staff during this devastating time.

524 Effectiveness of Burns Wound Cleansing by Comparison of Prewash and Post Wash Swab Reports

2021 ◽  
Vol 108 (Supplement_6) ◽  
Author(s):  
M A Sayed ◽  
S Jabeen ◽  
A Soueid
Keyword(s):  
Bacterial Load ◽  
Total Body Surface Area ◽  
Wound Management ◽  
Burn Patients ◽  
Burn Wound ◽  
Staph Aureus ◽  
Sex Type ◽  
Total Body ◽  
Burns Unit ◽  
Type Of Injury

Abstract Aim The main aim and objective were to optimise wound healing through infection prevention. This clinical audit aimed to investigate the effectiveness of burn wound cleansing in decreasing bacterial load by comparing pre-wash and post-wash swab results against local burn wound management and aseptic non touch technique (ANTT) guidelines. Method The audit was conducted retrospectively on children admitted to Burns Unit during August 2019, excluding resuscitation burn patients. Pre- and post-wash swabs taken on admission were included and the results obtained from Chameleon database. Data were collected on excel spread sheets including demographic variables such as age, sex, type of injury, percentage total body surface area (TBSA) and mechanism of injury. Data were analysed and results compiled. Results Fifty patients were admitted over a month period; amongst those 60% were male and 40% female of ages ranging from 5 months to 14 years. Scald (50%) was found to be the most common mode of injury followed by contact burn (36%) involving 0.30 to 9% TBSA. Among 50 patients, 30 (60%) showed no growth in pre-wash and 36 (72%) in post-wash swabs. However, 6% post-wash swabs that were initially negative later showed bacillus cereus, staph aureus, Enterobacter, and Acinetobacter. Similarly, another 4% post-wash swabs developed new microorganisms as compared to pre-wash swabs. Conclusions The most common bacteria colonising both pre- and post-wash swabs was staph aureus. Overall, cleansing had reduced the bacterial load significantly around 82% very effective. It is imperative to stick to local guidelines to reduce morbidity and mortality in burn patients.

scholarly journals Epidemiological studies of burn patients in a burn center in Ghana: any clues for prevention?

2016 ◽  
Vol 4 ◽  
pp. 1-4 ◽  
Author(s):  
P. Agbenorku ◽  
K. Aboah ◽  
J. Akpaloo ◽  
R. Amankwa ◽  
B. Farhat ◽  
...  
Keyword(s):  
Total Body Surface Area ◽  
Epidemiological Studies ◽  
Burn Injuries ◽  
Burn Patients ◽  
Middle Income ◽  
Burn Victims ◽  
Middle Income Countries ◽  
Burn Prevention ◽  
Working Environments ◽  
Total Body

Abstract Background Burn injuries are a serious problem worldwide, with most occurrences in low- and middle-income countries. Depending on the extent of injury, burn victims are faced with the challenges of fitting into society due to complications such as extensive scarring and contractures. The current study seeks to determine whether epidemiological studies of burn patients can provide guidelines to enhance burn prevention among the Ghanaian population. Methods Data from the Burns Registry of the Burns Intensive Care Unit (BICU) of Komfo Anokye Teaching Hospital (KATH) was obtained. Data on sex, age, aetiology, % total body surface area (TBSA), and admission outcomes from May 1, 2009, to April 30, 2013, were retrieved for a total of 487 patients during this period. Results Data on burn admissions comprising 263 (54.0 %) males and 224 (46.0 %) females were obtained from the Burns Registry. Children 0–10 years were the most affected age group. The yearly mean % TBSA ranged from 24.74 % to 35.07 %. The majority of burns was caused by scalding. Mortality rates ranged from 8.4 % to 32.0 % during the period under review. Conclusions The study shows that children of 10 years old and below are the most affected group; this may be due to inattention to these children by parents/caretakers. Safety and safe working environments should be provided at home and workplaces, and promotion of education on burn prevention should be intensified.

scholarly journals Divulging the Complexities of Deep Partial- and Full-Thickness Burn Wounds Afflicted by Staphylococcus Aureus Biofilms in a Rat Burn Model

2021 ◽  
Vol 2 (3) ◽  
pp. 106-124
Author(s):  
Alan J. Weaver Jr. ◽  
Kenneth S. Brandenburg ◽  
S. L. Rajasekhar Karna ◽  
Christopher Olverson ◽  
Kai P. Leung
Keyword(s):  
Staphylococcus Aureus ◽  
Total Body Surface Area ◽  
Complement C3 ◽  
Full Thickness ◽  
Sprague Dawley ◽  
Burn Wound ◽  
Burn Wounds ◽  
Gm Csf ◽  
Aureus Infection ◽  
Total Body

Every year, thousands of soldiers and civilians succumb to burn wound trauma with highly unfavorable outcomes. We previously established a modified Walker-Mason rat scald model exhibiting a P. aeruginosa infection. Here we characterize deep partial- (DPT) and full-thickness (FT) burn wounds inoculated with Staphylococcus aureus. Male Sprague-Dawley rats (350–450 g) inflicted with 10% total body surface area burn inoculated with S. aureus (103–5 CFU/wound) were monitored over an 11-day period. S. aureus rapidly dominated the wound bed, with bacterial loads reaching at least 1 × 109 CFU/g tissue in all wounds. Within 3 days, S. aureus biofilm formation occurred based on genetic transcripts and Giemsa staining of the tissue. S. aureus infection resulted in a slightly faster recruitment of neutrophils in FT wounds, which was related to necrotic neutrophils. The extent of the inflammatory response in S. aureus infected burn wounds correlated with elevated G-CSF, GM-CSF, GRO/KC and/or TNF-α levels, but a majority of pro- and anti-inflammatory cytokines (IL-1β, IL-6, IFN-γ, IL-10, and IL-13) were found to be suppressed, compared to burn-only controls. S. aureus infection resulted in dynamic changes in DAMPs, including elevated HMGB-1 and reduced levels of circulating hyaluronan within FT wounds. S. aureus also reduced complement C3 at all time points in DPT and FT wounds. These changes in DAMPs are believed to be correlated with burn severity and S. aureus specific bioburden. Collectively, this model showcases the evasiveness of S. aureus through dampening the immune response to flourish in the burn wound.

scholarly journals Arginine Is a Critical Substrate for the Pathogenesis of Pseudomonas aeruginosa in Burn Wound Infections

mBio ◽  
2017 ◽  
Vol 8 (2) ◽  
Author(s):  
Jake Everett ◽  
Keith Turner ◽  
Qiuxian Cai ◽  
Vernita Gordon ◽  
Marvin Whiteley ◽  
...  
Keyword(s):  
Antimicrobial Agents ◽  
Hospital Setting ◽  
Multidrug Resistant ◽  
Burn Patients ◽  
Burn Wound ◽  
Burn Wounds ◽  
Resistant Strains ◽  
High Doses ◽  
Ubiquitous Presence

ABSTRACT Environmental conditions affect bacterial behavior and can greatly influence the course of an infection. However, the environmental cues that elicit bacterial responses in specific infection sites are relatively unknown. Pseudomonas aeruginosa is ubiquitous in nature and typically innocuous. However, it is also one of the most prevalent causes of fatal sepsis in burn wound patients. The aim of this study was to determine the impact of environmental factors, specifically the availability of arginine, on the pathogenesis of P. aeruginosa in burn wound infections. Comparison of burned versus noninjured tissue revealed that l-arginine (l-Arg) was significantly depleted in burn wounds as a consequence of elevated arginase produced by myeloid-derived suppressor cells. We also observed that l-Arg was a potent chemoattractant for P. aeruginosa, and while low concentrations of l-Arg increased P. aeruginosa’s swimming motility, high concentrations resulted in diminished swimming. Based on these observations, we tested whether the administration of exogenous l-Arg into the burn wound could attenuate the virulence of P. aeruginosa in thermally injured mice. Administration of l-Arg resulted in decreased P. aeruginosa spread and sepsis and increased animal survival. Taken together, these data demonstrate that the availability of environmental arginine greatly influences the virulence of P. aeruginosa in vivo and may represent a promising phenotype-modulating tool for future therapeutic avenues. IMPORTANCE Despite our growing understanding of the pathophysiology of burn wounds and the evolution of techniques and practices to manage infections, sepsis remains a significant medical concern for burn patients. P. aeruginosa continues to be a leader among all causes of bacteremic infections due to its tendency to cause complications in immunocompromised patients and its ubiquitous presence in the hospital setting. With the unforgiving emergence of multidrug-resistant strains, it is critical that alternative strategies to control or prevent septic infections in burn patients be developed in parallel with novel antimicrobial agents. In this study, we observed that administration of l-Arg significantly reduced bacterial spread and sepsis in burned mice infected with P. aeruginosa. Given the safety of l-Arg in high doses and its potential wound-healing benefits, this conditionally essential amino acid may represent a useful tool to modulate bacterial behavior in vivo and prevent sepsis in burn patients. IMPORTANCE Despite our growing understanding of the pathophysiology of burn wounds and the evolution of techniques and practices to manage infections, sepsis remains a significant medical concern for burn patients. P. aeruginosa continues to be a leader among all causes of bacteremic infections due to its tendency to cause complications in immunocompromised patients and its ubiquitous presence in the hospital setting. With the unforgiving emergence of multidrug-resistant strains, it is critical that alternative strategies to control or prevent septic infections in burn patients be developed in parallel with novel antimicrobial agents. In this study, we observed that administration of l-Arg significantly reduced bacterial spread and sepsis in burned mice infected with P. aeruginosa. Given the safety of l-Arg in high doses and its potential wound-healing benefits, this conditionally essential amino acid may represent a useful tool to modulate bacterial behavior in vivo and prevent sepsis in burn patients.

Deep learning for automated detection and numbering of permanent teeth on panoramic images

2021 ◽  
Author(s):  
Mohamed Estai ◽  
Marc Tennant ◽  
Dieter Gebauer ◽  
Andrew Brostek ◽  
Janardhan Vignarajan ◽  
...  
Keyword(s):  
Deep Learning ◽  
High Performance ◽  
Detection System ◽  
Ground Truth ◽  
Automated Detection ◽  
Permanent Teeth ◽  
Automated Method ◽  
Step Procedure ◽  
Panoramic Images ◽  
Tooth Number

Objective: This study aimed to evaluate an automated detection system to detect and classify permanent teeth on orthopantomogram (OPG) images using convolutional neural networks (CNNs). Methods: In total, 591 digital OPGs were collected from patients older than 18 years. Three qualified dentists performed individual teeth labelling on images to generate the ground truth annotations. A three-step procedure, relying upon CNNs, was proposed for automated detection and classification of teeth. Firstly, U-Net, a type of CNN, performed preliminary segmentation of tooth regions or detecting regions of interest (ROIs) on panoramic images. Secondly, the Faster R-CNN, an advanced object detection architecture, identified each tooth within the ROI determined by the U-Net. Thirdly, VGG-16 architecture classified each tooth into 32 categories, and a tooth number was assigned. A total of 17,135 teeth cropped from 591 radiographs were used to train and validate the tooth detection and tooth numbering modules. 90% of OPG images were used for training, and the remaining 10% were used for validation. 10-folds cross-validation was performed for measuring the performance. The intersection over union (IoU), F1 score, precision, and recall (i.e. sensitivity) were used as metrics to evaluate the performance of resultant CNNs. Results: The ROI detection module had an IoU of 0.70. The tooth detection module achieved a recall of 0.99 and a precision of 0.99. The tooth numbering module had a recall, precision and F1 score of 0.98. Conclusion: The resultant automated method achieved high performance for automated tooth detection and numbering from OPG images. Deep learning can be helpful in the automatic filing of dental charts in general dentistry and forensic medicine.

5 -Year Retrospective Analysis of a Vented Mobility Algorithm in the Burn ICU

2022 ◽  
Author(s):  
Audrey Marie O'Neil ◽  
Cassandra Rush ◽  
Laura Griffard ◽  
David Roggy ◽  
Allison Boyd ◽  
...  
Keyword(s):  
Retrospective Analysis ◽  
Recent Literature ◽  
Total Body Surface Area ◽  
Early Mobilization ◽  
Burn Patients ◽  
Mechanically Ventilated ◽  
Line Placement ◽  
Total Body ◽  
Stage 1 ◽  
Significant Attention

Abstract Early mobilization with mechanically ventilated patients has received significant attention within recent literature, however limited research has focused specifically on the burn population. The purpose of this single center, retrospective analysis was to review the use of a burn critical care mobility algorithm, to determine safety and feasibility of a burn vented mobility program, share limitations preventing mobility progression at our facility, and discuss unique challenges to vented mobility with intubated burn patients. A retrospective review was completed for all intubated burn center admissions between January 2015 to December 2019. Burn Therapy notes were then reviewed for data collection, during the intubation period, using stages of the mobility algorithm. In 5 years following initial implementation, the vented mobility algorithm was utilized on 127 patients with an average total body surface area of 22.8%. No adverse events occurred. Stage 1 (Range of motion) was completed with 100% of patients (n=127). Chair mode of bed, stage 2a, was utilized in 39.4%(n=50) of patients, while 15.8% (n=20) of patients were dependently transferred to the cardiac chair in stage 2b. Stage 3 (sitting on the edge-of-bed) was completed with 25% (n=32) of patients, with 11% (n=14) progressing to stage 5 (standing), and 3.9% (n=5) actively transferring to a chair. In 5 years, only 4.7% (n=6) reached stage 6 (ambulation). The most common treatment limitations were medical complications (33%) and line placement (21%). Early mobilization during mechanical ventilation is safe and feasible within the burn population, despite challenges including airway stability, sedation, and line limitations.

scholarly journals A Comparative Study between C-Reactive Protein and Procalcitonin in Iraqi Burn Patients

2017 ◽  
Vol 28 (1) ◽  
pp. 41
Author(s):  
Alia E. Al-Ubadi
Keyword(s):  
Burn Injury ◽  
Total Body Surface Area ◽  
Latex Agglutination ◽  
Burn Patients ◽  
C Reactive Protein ◽  
Reactive Protein ◽  
Survivor Group ◽  
Significant Difference ◽  
The Mean ◽  
Total Body

Association between Procalcitonin (PCT) and C-reactive protein (CRP) and burn injury was evaluated in 80 burned patients from Al-Kindy and Imam Ali hospitals in Baghdad-Iraq. Patients were divided into two groups, survivor group 56 (70%) and non-survivor group 24 (30%). PCT was estimated using (Human Procalcitonin ELISA kit) provided by RayBio/USA while CRP was performed using a latex agglutination kit from Chromatest (Spain). Our results declared that the mean of Total Body Surface Area (TBSA %) affected were 63.5% range (36%–95%) in non-survivor patients, while 26.5% range (10%–70%) in survivor patients. There is a significant difference between the two groups (P = 0.00), the higher mean percentage of TBSA has a significant association with mortality. Serum PCT and CRP were measured at the three times of sampling (within the first 48hr following admission, after 5thdays and after 10th days). The mean of PCT serum concentrations in non-survivor group (2638 ± 3013pg/ml) were higher than that of survivor group (588 ± 364pg/ml). Significantly high levels of CRP were found between the survivor and non-survivor groups especially in the 10th day of admission P=0.000, present study show that significant differences is found within the non-survivor group through the three times P= 0.01, while results were near to significant differences within survivor group through the three times (P= 0.05).

scholarly journals Initial assessment of mortality rates of burn patients in a tertiary care hospital by total body surface area, depth and facial burns, and its correlation with serial total leucocyte count

2020 ◽  
Vol 7 (10) ◽  
pp. 3280
Author(s):  
Kavitha Jayanthi Balachandran ◽  
Manoj Kumar Nirmalanandan
Keyword(s):  
Surface Area ◽  
Body Surface ◽  
Leucocyte Count ◽  
Total Body Surface Area ◽  
Total Leucocyte Count ◽  
Burn Victims ◽  
Facial Burns ◽  
Inhalational Injury ◽  
Total Body ◽  
Wbc Count

Background: The pattern of burns in victims varies with the manner of infliction of burns. Age plays an important role in deciding the mortality and morbidity of burn victims. Other factors that decide the prognosis of burn victims are the total body surface area (TBSA), Depth of burns, and inhalational injury as evidenced by facial burns. Assessment of these epidemiological factors and inhalational injury can be done as a part of the initial evaluation. Such an assessment aid in resuscitation including emergent airway and decision making regarding the need for skin grafts or escharotomy. Serial measurement of total leucocyte count also helps in identifying the onset of infection and progress to septicaemia and increased mortality rates.Methods: As a part of the initial evaluation, we attempt to study the relation between TBSA, Depth of burns, facial burns, and total WBC count with mortality. A background of septicaemia was also noticed in the majority of patients.Results: For analysis, patients were divided into two groups- Survivors and Non-survivors. A fall in total WBC count coincided with the onset of sepsis and mortality. The other three factors also had a direct correlation with mortality rates.Conclusions: A scoring system constituting all the factors is essential as an initial diagnostic step and it will help in deciding early intubation, escharotomy, and aggressive fluid resuscitation.

Sign in / Sign up

Export Citation Format

Share Document