AI-Driven Three-Dimensional Reconstruction and Quantitative Analysis for Burn Injury Assessment

TL;DR

The paper addresses the need for objective, longitudinal burn assessment beyond subjective 2D photography by introducing an AI-powered platform that fuses multi-view photogrammetry, 3D reconstruction, and deep learning segmentation within a guideline-driven clinical workflow. The approach delivers metrically scaled 3D burn surfaces, perimeters, depth proxies, and volumetric change, with automatic longitudinal alignment to track healing over time. Key contributions include an end-to-end pipeline (data capture, metric extraction, and report generation), a metric-scaling strategy using known references, and an explainable AI framework that maps 2D segmentation onto a 3D surface for view-independent measurements. The work demonstrates feasibility with simulation-based evaluation, showing stable reconstructions and clinically plausible healing trajectories, and highlights potential to improve objectivity, reproducibility, and medico-legal documentation in both acute and outpatient burn care.

Abstract

Accurate, reproducible burn assessment is critical for treatment planning, healing monitoring, and medico-legal documentation, yet conventional visual inspection and 2D photography are subjective and limited for longitudinal comparison. This paper presents an AI-enabled burn assessment and management platform that integrates multi-view photogrammetry, 3D surface reconstruction, and deep learning-based segmentation within a structured clinical workflow. Using standard multi-angle images from consumer-grade cameras, the system reconstructs patient-specific 3D burn surfaces and maps burn regions onto anatomy to compute objective metrics in real-world units, including surface area, TBSA, depth-related geometric proxies, and volumetric change. Successive reconstructions are spatially aligned to quantify healing progression over time, enabling objective tracking of wound contraction and depth reduction. The platform also supports structured patient intake, guided image capture, 3D analysis and visualization, treatment recommendations, and automated report generation. Simulation-based evaluation demonstrates stable reconstructions, consistent metric computation, and clinically plausible longitudinal trends, supporting a scalable, non-invasive approach to objective, geometry-aware burn assessment and decision support in acute and outpatient care.

Figures (12)

• Figure 1: Figure 1: Overview of the 3D Burn Reconstruction System.
• Figure 2: Figure 2a: Initial mode selection screen allowing clinicians to choose between emergency assessment and comprehensive medical consultation pathways.
• Figure 3: Figure 2b: Structured patient intake process showing consulting physician details and patient demographics.
• Figure 4: Figure 2c: Structured patient intake process showing history of present illness and medical background.
• Figure 5: Figure 2d: Structured patient intake process showing physical examination.