A comparative evaluation of spectrophotometric intracutaneous analysis and laser doppler imaging in the assessment of adult and paediatric burn injuries

Proceedings of the 2021 American Burn Association State and Future of Burn Science Meeting

Periodically, the American Burn Association (ABA) has convened a State of the Science meeting on various topics representing multiple disciplines within burn care and research. In 2021 at the request of the ABA President, meeting development was guided by the ABA's Burn Science Advisory Panel (BSAP) and a subgroup of meeting chairs. The goal of the meeting was to produce both an evaluation of the current literature and ongoing studies, and to produce a research agenda and/or define subject matter-relevant next steps to advance the field(s). Members of the BSAP defined the topics to be addressed and subsequently solicited for nominations of expert speakers and topic leaders from the ABA's Research Committee. Current background literature for each topic was compiled by the meeting chairs and the library then enhanced by the invited topic and breakout discussion leaders. The meeting was held in New Orleans, LA on November 2nd and 3rd and was formatted to allow for 12 different topics, each with two subtopics, to be addressed. Topic leaders provided a brief overview of each topic to approximately 100 attendees, followed by expert-lead breakout sessions for each topic that allowed for focused discussion among subject matter experts and interested participants. The breakout and topic group leaders worked with the participants to determine research needs and associated next steps including white papers, reviews and in some cases collaborative grant proposals. Here, summaries from each topic area will be presented to highlight the main foci of discussion and associated conclusions.

Intraoperative colon perfusion assessment using multispectral imaging

In colorectal surgery an anastomosis performed using poorly-perfused, ischaemic bowel segments may result in a leak and consequent morbidity. Traditional measures of perfusion assessment rely on clinical judgement and are mainly subjective, based on tissue appearance, leading to variability between clinicians. This paper describes a multispectral imaging (MSI) laparoscope that can derive quantitative measures of tissue oxygen saturation (SO₂ ). The system uses a xenon surgical light source and fast filter wheel camera to capture eight narrow waveband images across the visible range in approximately 0.3 s. Spectral validation measurements were performed by imaging standardised colour tiles and comparing reflectance with ground truth spectrometer data. Tissue spectra were decomposed into individual contributions from haemoglobin, adipose tissue and scattering, using a previously-developed regression approach. Initial clinical results from seven patients undergoing colorectal surgery are presented and used to characterise measurement stability and reproducibility in vivo. Strategies to improve signal-to-noise ratio and correct for motion are described. Images of healthy bowel tissue (in vivo) indicate that baseline SO₂ is approximately 75 ± 6%. The SO₂ profile along a bowel segment following ligation of the inferior mesenteric artery (IMA) shows a decrease from the proximal to distal end. In the clinical cases shown, imaging results concurred with clinical judgements of the location of well-perfused tissue. Adipose tissue, visibly yellow in the RGB images, is shown to surround the mesentery and cover some of the serosa. SO₂ in this tissue is consistently high, with mean value of 90%. These results show that MSI is a potential intraoperative guidance tool for assessment of perfusion. Mapping of SO₂ in the colon could be used by surgeons to guide choice of transection points and ensure that well-perfused tissue is used to form an anastomosis. The observation of high mesenteric SO₂ agrees with work in the literature and warrants further exploration. Larger studies incorporating with a wider cohort of clinicians will help to provide retrospective evidence of how this imaging technique may be able to reduce inter-operator variability.

Potential for Machine Learning in Burn Care

INTRODUCTION

Burn-related injuries are a leading cause of morbidity across the globe. Accurate assessment and treatment have been demonstrated to reduce the morbidity and mortality. This essay explores the forms of artificial intelligence to be implemented the field of burns management to optimise the care we deliver in the National Health Service (NHS) in the UK.

METHODS

Machine Learning methods which predict or classify are explored. This includes linear and logistic regression, artificial neural networks, deep learning, and decision tree analysis.

DISCUSSION

Utilizing Machine Learning in burns care holds potential from prevention, burns assessment, predicting mortality and critical care monitoring to healing time. Establishing a regional or national Machine Learning group would be the first step towards the development of these essential technologies.

CONCLUSION

The implementation of machine learning technologies will require buy-in from the NHS health boards, with significant implications with cost of investment, implementation, employment of machine learning teams and provision of training to medical professionals.

The LDI Enigma, Part I: So much proof, so little use

INTRODUCTION

Laser Doppler imaging (LDI) is still not an ubiquitous part of burn care worldwide despite reported accuracy rates of more than 95%, which is significantly higher than clinical assessment alone (50-75%). The aims of Part I of this survey study are: to identify the most important barriers for the use of LDI and to provide useful recommendations for efficient implementation in routine burn care. The actual interpretation and use of LDI measurements is discussed in the Enigma Part II article.

MATERIAL AND METHODS

1. Informative interviews with 15 representatives of burn centers without LDI. 2. A survey among 51 burn centers with LDI by means of an extensive questionnaire. 3. In-depth interviews with 21 of the participating centers.

RESULTS

1. All 15 centers without LDI indicated that cost of purchase in combination with maintenance of the LDI device, as well as personnel costs were the reason for not buying, while 12 (80%) also rated the current scientific evidence as insufficient. 2. Twenty-seven burn centers with an LDI (53%) participated and filled in almost the entire questionnaire. In 5 centers, cost delayed the purchase of LDI. The hospital/department paid for the LDI device in 62% of the burn centers and in 88% also for maintenance and salaries. The LDI operators were mainly surgeons (47%) or nurses (42%). In more than half of the burn centers (52%), between 2 and 5 people were trained and certified to use an LDI. In 50% of burn centers, the interpretation of the LDI scan was done by the same person doing the actual measurements. Eighty-nine percent of the burn centers considered the accuracy of the LDI scan as mainly to almost completely accurate. In case of real discrepancy between clinical diagnosis and LDI, in 48% of the burn centers (13/27) the surgeon still relied more on the clinical diagnosis despite reporting this high or almost complete accuracy rate of the LDI.

CONCLUSIONS

Barriers for the routine implementation of LDI were: 1. cost of purchasing and using an LDI combined with health care systems that inadequately reimburse non-surgical management; 2. lack of awareness of or ongoing skepticism towards the scientific evidence supporting LDI use; and 3. organizational constraints combined with logistical limitations. Our recommendations for wider use of LDI technology include: 1. a cost-effective reimbursement of LDI use combined with a more appropriate valuation of expert conservative management compared to surgical therapy; 2. increased use of LDI for every mixed depth burn and; 3. specialized LDI teams to improve burn procedural flexibility and to enable embedding LDI use in the burn care routine. Implementing these measures would promote the highest standards for LDI measurements and interpretation resulting in optimal care with mutual benefits for the hospital, for burn care teams and, most importantly, for the patients.

Assessment of Human Skin Burns: A Deep Transfer Learning Approach

Purpose

Accurate assessment of burns is increasingly sought due to diagnostic challenges faced with traditional visual assessment methods. While visual assessment is the most established means of evaluating burns globally, specialised dermatologists are not readily available in most locations and assessment is highly subjective. The use of other technical devices such as Laser Doppler Imaging is highly expensive while rate of occurrences is high in low- and middle-income countries. These necessitate the need for robust and cost-effective assessment techniques thereby acting as an affordable alternative to human expertise.

Method

In this paper, we present a technique to discriminate skin burns using deep transfer learning. This is due to deficient datasets to train a model from scratch, in which two dense and a classification layers were added to replace the existing top layers of pre-trained ResNet50 model.

Results

The proposed study was able to discriminate between burns and healthy skin in both ethnic subjects (Caucasians and Africans). We present an extensive analysis of the effect of using both homogeneous and heterogeneous datasets when training a machine learning algorithm. The findings show that using homogenous dataset during training process produces a biased diagnostic model towards minor racial subjects while using heterogeneous datasets produce a robust diagnostic model. Recognition accuracy of up to 97.1% and 99.3% using African and Caucasian datasets respectively were achieved.

Conclusion

We concluded that it is feasible to have a robust diagnostic machine learning model for burns assessment that can be deployed to remote locations faced with access to specialized burns specialists, thereby aiding in decision-making as quick as possible