Deep Learning–Assisted Burn Wound Diagnosis: Diagnostic Model Development Study

Abstract

Background Accurate assessment of the percentage 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 discrepancies 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 2-step procedure was used to convert burn wound diagnosis into %TBSA. In the first step, images of burn wounds were collected from medical records and labeled by burn surgeons, and the data set was then input into 2 deep learning architectures, U-Net and Mask R-CNN, each configured with 2 different backbones, to segment the burn wounds. In the second step, we collected and labeled images of hands to create another data set, which was also input into U-Net and Mask R-CNN to segment the hands. The %TBSA of burn wounds was then calculated by comparing the pixels of mask areas on images of the burn wound and hand of the same patient according to the rule of hand, which states 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 data set. The data set was randomly split into training, validation, and testing sets in a ratio of 8:1:1. Four hundred images of volar hands were collected and labeled to form the hand data set, which was also split into 3 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 DC values of 0.9920 and 0.9910, respectively. Lastly, we conducted a test diagnosis in a burn patient. Mask R-CNN with ResNet101 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, thereby helping to provide precise care to burn victims.

Machine learning approach for predicting inhalation injury in patients with burns

“…AI has developed rapidly in recent years, and numerous related studies have been conducted in the field of burn injury and treatment [11] , [12] , [13] , [14] . To the best of our knowledge, this is the first study to apply a machine-learning approach to predict inhalation injury in patients with burns.…”

Review of machine learning for optical imaging of burn wound severity assessment

“…Although some preliminary burn classification work using digital color images and deep learning technology had been reported prior to 2019, 27 the period from 2019 to 2023 saw a substantial increase in the use of deep learning approaches for burn wound classification. [28][29][30][31][32][33][34][35][36][37][38][39][40][41][42][43][44][45] Several studies in this time period used deep learning algorithms to segment images into burned and un-burned regions. 31,34,35,[38][39][40] A 2019 study 31 used 1,000 images to train a mask region with a convolutional neural network (Mask R-CNN) algorithm, comparing several different underlying network types and obtaining a maximum accuracy of 85% for identifying burn regions in images of different severities of burns.…”

“…[28][29][30][31][32][33][34][35][36][37][38][39][40][41][42][43][44][45] Several studies in this time period used deep learning algorithms to segment images into burned and un-burned regions. 31,34,35,[38][39][40] A 2019 study 31 used 1,000 images to train a mask region with a convolutional neural network (Mask R-CNN) algorithm, comparing several different underlying network types and obtaining a maximum accuracy of 85% for identifying burn regions in images of different severities of burns. Another 2019 study 38 used deep learning with semantic segmentation to distinguish between burn, skin, and background portions of images.…”

“…Although some preliminary burn classification work using digital color images and deep learning technology had been reported prior to 2019, 27 the period from 2019 to 2023 saw a substantial increase in the use of deep learning approaches for burn wound classification. 28 – 45 …”

“…Several studies in this time period used deep learning algorithms to segment images into burned and un-burned regions. 31 , 34 , 35 , 38 – 40 A 2019 study 31 used 1,000 images to train a mask region with a convolutional neural network (Mask R-CNN) algorithm, comparing several different underlying network types and obtaining a maximum accuracy of 85% for identifying burn regions in images of different severities of burns. Another 2019 study 38 used deep learning with semantic segmentation to distinguish between burn, skin, and background portions of images.…”