Can Artificial Intelligence Guided Image Assessment be as Accurate as Laser Doppler Perfusion Scanning in Predicting Depth of Burn Injury?
Year: 2023
Type: article
Abstract: PURPOSE: Appropriate identification of burn depth and size is paramount. Despite the development of assessment aids [e.g., laser doppler imaging (LDI)], clinical assessments remain the gold standard, which assesses partial thickness burn depth with ~67% accuracy. We sought to develop an image-based artificial intelligence (AI) system that predicts burn severity and margins for use in acute burn triage. METHOD: A convoluted neural network (CNN) was trained on 1855 mobile-device-captured burn images of different burn depths. The CNN was used to develop a novel Boundary-Attention Mapping (BAM) algorithm, using elements of saliency mapping, which was utilized to recognize the boundaries of burns. For validation, 144 patient charts that included clinical assessments, burn location, total body surface area, LDI-assessments, were retrieved for a retrospective study at the University of Alberta. The clinical images underwent CNN-BAM assessments and were directly compared with the LDI assessment. RESULTS: The CNN-BAM system can highlight burns from surrounding tissue with high confidence. The CNN can classify four levels of burn severity with an accuracy of 80%. Results comparing the CNN-BAM outputs to clinical and LDI assessments have shown a high degree of correlation (approximately 85%) between the CNN burn severity predictions to those extrapolated from LDI healing potential. When compared to pre-LDI clinical assessment, the accuracy of the CNN-BAM outcomes has been equivalent or superior in most cases. A high degree of correlation has been demonstrated between the LDI scans and BAM maps created by the system when identifying the overall burn injury margins. CONCLUSION: This novel AI algorithm gives approximately equal accuracy in detecting burn depth as an LDI with a more economical and accessible application when embedded in a mobile device.
Authors: Justin Lee, Alexander Morzycki, Hannah Chan, Rakesh Joshi, Collin Hong, Joshua Wong
Institution: University of Alberta
Language: English
Subfield: Surgery
Field: Medicine
Domain: Health Sciences
Open Access status: gold
Estimated APC paid: $2,195
OpenAlex ID: W4387941216