Evaluating the Suitability of Different Intraoral Scan Resolutions for Deep Learning-Based Tooth Segmentation

2025-02-26

AI Summary

This study investigates the impact of intraoral scan mesh resolution on deep learning-based tooth segmentation performance, aiming to balance computational efficiency for edge-device deployment with clinical accuracy requirements. Method: We systematically evaluate segmentation accuracy across resolutions ranging from 2K to 16K vertices, introduce cross-resolution generalization training and high-resolution inference within a PointMLP framework, and propose an optimization paradigm for selecting the optimal resolution under resource constraints. Contribution/Results: We quantitatively characterize the accuracy degradation induced by multi-level downsampling—first reported in dental AI—and identify 8K resolution as optimal: it retains 98.3% of the segmentation accuracy achieved at 16K while reducing GPU memory consumption by 75%. This outperforms conventional 10K/16K settings and establishes a reproducible, resolution-aware optimization guideline for lightweight dental AI deployment.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Hardware-aware ML
• Search and Optimization: Distributed Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Intraoral scans are widely used in digital dentistry for tasks such as dental restoration, treatment planning, and orthodontic procedures. These scans contain detailed topological information, but manual annotation of these scans remains a time-consuming task. Deep learning-based methods have been developed to automate tasks such as tooth segmentation. A typical intraoral scan contains over 200,000 mesh cells, making direct processing computationally expensive. Models are often trained on downsampled versions, typically with 10,000 or 16,000 cells. Previous studies suggest that downsampling may degrade segmentation accuracy, but the extent of this degradation remains unclear. Understanding the extent of degradation is crucial for deploying ML models on edge devices. This study evaluates the extent of performance degradation with decreasing resolution. We train a deep learning model (PointMLP) on intraoral scans decimated to 16K, 10K, 8K, 6K, 4K, and 2K mesh cells. Models trained at lower resolutions are tested on high-resolution scans to assess performance. Our goal is to identify a resolution that balances computational efficiency and segmentation accuracy.

Problem

• Assess resolution impact on tooth segmentation
• Determine optimal scan resolution for deep learning
• Balance computational cost and segmentation accuracy

Innovation

• Deep learning for tooth segmentation
• Evaluating scan resolution impact
• Balancing efficiency and accuracy