
The study involves both simulated burns and real patient cases, demonstrating how curvature affects wound area calculations. For flatter regions like the back, the 3D-to-2D ratio remains close to 1.0, indicating minimal discrepancy. However, highly contoured areas exhibit significantly larger 3D-to-2D ratios, with the dorsal foot (1.908) and head/neck (1.641) showing the greatest discrepancies. This highlights the importance of adopting 3D-based assessments to ensure accurate clinical evaluations. The study also reveals that burns covering multiple body regions exhibit more variability in measurement, further emphasizing the limitations of conventional 2D segmentation.
By leveraging LiDAR sensors, deep learning segmentation, and AI-enhanced processing, this research sets the stage for more precise, automated burn assessments. The B.E.N. application enables medical professionals to generate 3D wound maps, measure surface area more accurately, and reduce human error in critical burn evaluations. These advancements pave the way for AI-driven diagnostic tools that integrate real-world depth data with clinical imaging, improving both treatment planning and patient outcomes.
For more details on the study, read the full article HERE
Thank you for reading!














