SALVE: A 3D Reconstruction Benchmark of Wounds from Consumer-Grade Videos

2024-07-29

IEEE Workshop/Winter Conference on Applications of Computer Vision

AI Summary

Clinical assessment of chronic wounds requires accurate, quantitative 3D surface models, yet conventional Structure-from-Motion/Multi-View Stereo (SfM/MVS) methods yield geometrically discontinuous reconstructions that fail to meet clinical accuracy requirements. Method: We introduce SALVE—the first benchmark for consumer-grade video-based 3D wound reconstruction—comprising a real-world chronic wound video dataset and a systematic evaluation framework comparing photogrammetric and neural rendering approaches. Contribution/Results: Quantitative analysis reveals SfM/MVS reconstructions exceed clinically acceptable geometric error thresholds. In contrast, neural radiance fields (NeRF) and their variants produce smooth, depth-consistent, and quantitatively measurable wound surfaces. Neural rendering significantly outperforms photogrammetry in surface continuity, normal consistency, and lesion-region measurability. These findings establish neural rendering as a robust, low-cost, remote-capable, and automatable solution for clinical-grade wound monitoring.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Managing chronic wounds is a global challenge that can be alleviated by the adoption of automatic systems for clinical wound assessment from consumer-grade videos. While 2D image analysis approaches are insufficient for handling the 3D features of wounds, existing approaches utilizing 3D reconstruction methods have not been thor-oughly evaluated. To address this gap, this paper presents a comprehensive study on 3D wound reconstruction from consumer-grade videos. Specifically, we introduce the SALVE dataset, comprising video recordings of realistic wound phantoms captured with different cameras. Using this dataset, we assess the accuracy and precision of state-of-the-art methods for 3D reconstruction, ranging from traditional photogrammetry pipelines to advanced neural rendering approaches. In our experiments, we observe that photogrammetry approaches do not provide smooth surfaces suitable for precise clinical measurements of wounds. Neural rendering approaches show promise in addressing this issue, advancing the use of this technology in wound care practices. We encourage the readers to visit the project page: https://rcmichierchia.github.io/SALVE/.

Problem

• Evaluating 3D reconstruction methods for wound assessment
• Addressing limitations of 2D analysis in wound measurement
• Improving clinical wound care with neural rendering technology

Innovation

• 3D wound reconstruction from consumer videos
• SALVE dataset with realistic wound phantoms
• Neural rendering improves clinical measurement accuracy