Comparison of Laser Doppler Imaging (LDI) and clinical assessment in differentiating between superficial and deep partial thickness burn wounds

Jan, Saadia Nosheen; Khan, Farid Ahmed; Bashir, Muhammad Mustehsan; Nasir, Muneeb; Ansari, Hamid Hussain; Shami, Hussan Birkhez; Nazir, Umer; Hanif, Asif; Sohail, Muhammad

doi:10.1016/j.burns.2017.08.020

Cited by 36 publications

(16 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, in this paper we proposed the use of machine learning to discriminate burns and injured skin. The motivation behind this proposal are-(1) human expertise is not readily available in most remote locations; (2) assessment by human experts is time consuming and subjective [11]; (3) up to-date approved device (i.e., LDI) for burns assessment by burn community is highly expensive [12] and (4) to the best of our knowledge, no technique was proposed to address discriminating burns and injured skin, as such we proposed the use of machine learning to discriminate whether a given image is burn or injured. The use of machine learning can serve as alternative to human expertise thereby aiding in timely decision making.…”

Section: Introductionmentioning

confidence: 99%

Comparison of Deep Transfer Learning Techniques in Human Skin Burns Discrimination

Abubakar

Ajuji

Yahya

2020

ASI

View full text Add to dashboard Cite

While visual assessment is the standard technique for burn evaluation, computer-aided diagnosis is increasingly sought due to high number of incidences globally. Patients are increasingly facing challenges which are not limited to shortage of experienced clinicians, lack of accessibility to healthcare facilities and high diagnostic cost. Certain number of studies were proposed in discriminating burn and healthy skin using machine learning leaving a huge and important gap unaddressed; whether burns and related skin injuries can be effectively discriminated using machine learning techniques. Therefore, we specifically use transfer learning by leveraging pre-trained deep learning models due to deficient dataset in this paper, to discriminate two classes of skin injuries—burnt skin and injured skin. Experiments were extensively conducted using three state-of-the-art pre-trained deep learning models that includes ResNet50, ResNet101 and ResNet152 for image patterns extraction via two transfer learning strategies—fine-tuning approach where dense and classification layers were modified and trained with features extracted by base layers and in the second approach support vector machine (SVM) was used to replace top-layers of the pre-trained models, trained using off-the-shelf features from the base layers. Our proposed approach records near perfect classification accuracy in categorizing burnt skin ad injured skin of approximately 99.9%.

show abstract

Section: Introductionmentioning

confidence: 99%

Comparison of Deep Transfer Learning Techniques in Human Skin Burns Discrimination

Abubakar

Ajuji

Yahya

2020

ASI

View full text Add to dashboard Cite

show abstract

“…In 2018, a study published by King Edward Medical University and Mayo Hospital in Pakistan comparing the accuracy of LDI and clinical assessment in determining wound depth showed 90.21% diagnostic accuracy, 92.75% sensitivity, 82% specificity, 94% positive predictive value, and 79% negative predictive value. The results for clinical assessment were 81.52%, 81%, 82%, 93%, and 59%, respectively [ 8 ]. Burn surgery and wound management involve a multidisciplinary treatment team.…”

Section: Discussionmentioning

confidence: 99%

“…Even though studies indicate that visual evaluation of digital images is accurate enough for clinical decision-making, there are not sufficient studies looking into the accuracy of assessing digital images of indeterminate-depth burn wounds [ 8 ]. The reliability of making a preliminary indeterminate-depth burn wound assessment based on digital images should be further explored due to its two-dimensional limitations.…”

Section: Introductionmentioning

confidence: 99%

The Added Benefit of Combining Laser Doppler Imaging With Clinical Evaluation in Determining the Need for Excision of Indeterminate-Depth Burn Wounds

Asif

Chin²,

Lagziel

et al. 2020

Cureus

View full text Add to dashboard Cite

Background Managing indeterminate-depth burn wounds remains challenging. Laser Doppler Imaging (LDI) has been validated for burn wound depth and can influence the clinical assessment. Our study investigated the value of LDI as an adjunct in determining the need for excision. Methods Seventy American Burn Association (ABA)-verified burn centers were surveyed. A controlled pre-test assessment without LDI and post-test assessment with LDI of 100 indeterminate-depth burn wounds was conducted to evaluate the influence on the clinical judgment among different health professionals. Relative risk, analysis of variance (ANOVA), paired t-test, and intention-to-treat were used for analysis. A p-value \begin{document}\leq\end{document} 0.05 was considered significant. Results Among 32 burn centers, three confirmed using LDI. Six thousand grader-image interactions were analyzed. There was a significant difference in the predictive accuracy for pre-LDI and post-LDI assessments when all graders were considered (51.9% ± 7.0 vs. 72.9% ± 7.9; p < 0.0001). Post-LDI assessment added 20.9% more accuracy than the pre-LDI assessment. The post-LDI assessment was 1.4 times more likely to correctly predict the need for excision and skin-grafting than the pre-LDI assessment. All groups had an improved performance post-LDI: Group 1 (physicians), 51.9 ± 7.5 versus 76.4±5; Group 2 (nurses), 52.1 ± 6.1 versus 72.7±7.7; and Group 3 (others), 51.7 ± 9.2 versus 68.6 ± 10.1. No statistical difference was observed between groups (p = 0.92). Conclusion LDI makes the clinical examination of indeterminate-depth burn wounds more accurate. For every five LDI evaluations performed, one assessor changed their treatment plan as a result of this imaging technique. LDI is cost-effective and increases the accuracy of determining the severity of indeterminate-depth burn wounds.

show abstract

“…A recent RCT showed LDI led to faster decision making about excision and grafting, and had a cost-saving benefit, 99 and a recent study showed that LDI had superior specificity, sensitivity, positive predictive value, and negative predictive value than the clinical examination for estimating burn depth. 100 There is some evidence to support the use of laser speckle imaging (LSI) in very small burns 101 and although it has high specificity to detect deep dermal burns, it has limitations in sensitivity and accuracy. Spatial frequency domain imaging (SFDI) is noninferior to the physical examination in animal studies.…”

Section: Adjuncts To the Clinical Assessment Of Patients With Burnsmentioning

confidence: 99%

A Critical Update of the Assessment and Acute Management of Patients with Severe Burns

Lang

Zhao²,

Kim

et al. 2019

Advances in Wound Care

View full text Add to dashboard Cite

Burns are debilitating, life threatening, and difficult to assess and manage. Recent advances in assessment and management have occurred since a comprehensive review of the care of patients with severe burns was last published, which may influence research and clinical practice. Recent Advances: Recent advances have occurred in the understanding of burn pathophysiology, which has led to the identification of potential biomarkers of burn severity, such as protein C. There is new evidence about the potential superiority of natural colloids over crystalloids during fluid resuscitation, and new evidence about components of initial and perioperative management, including an improved understanding of pain following burns. Critical Issues: The limitations of the clinical examination highlight the need for imaging and biomarkers to assist in estimations of burn severity. Fluid resuscitation reduces mortality, although there is conjecture over the ideal method. The subsequent perioperative period is associated with significant morbidity and the evidence for preventing and treating pain, infection, and fluid overload while maximizing wound healing potential is described. Future Directions: Promising developments are ongoing in imaging technology, histopathology, biomarkers, and wound healing adjuncts such as hyperbaric oxygen therapy, topical negative pressure therapy, stem cell treatments, and skin substitutes. The greatest benefit from further research on management of patients with burns would most likely be derived from the elucidation of optimal fluid resuscitation protocols, pain management protocols, and surgical techniques from randomized controlled trials.

show abstract

Comparison of Laser Doppler Imaging (LDI) and clinical assessment in differentiating between superficial and deep partial thickness burn wounds

Cited by 36 publications

References 30 publications

Comparison of Deep Transfer Learning Techniques in Human Skin Burns Discrimination

Comparison of Deep Transfer Learning Techniques in Human Skin Burns Discrimination

The Added Benefit of Combining Laser Doppler Imaging With Clinical Evaluation in Determining the Need for Excision of Indeterminate-Depth Burn Wounds

A Critical Update of the Assessment and Acute Management of Patients with Severe Burns

Contact Info

Product

Resources

About