Defect Segmentation in OCT scans of ceramic parts for non-destructive inspection using deep learning

2025-10-01

AI Summary

Accurate segmentation of minute defects—such as pores, delaminations, and inclusions—in optical coherence tomography (OCT) images of ceramic components remains challenging due to their small size and low contrast. To address this, we propose an enhanced U-Net architecture integrating multi-scale feature extraction and channel-spatial attention mechanisms, coupled with a post-processing pipeline based on connected-component analysis and morphological optimization. The model is trained on a manually curated, high-fidelity OCT dataset of ceramic specimens. Experimental results demonstrate state-of-the-art performance: a Dice score of 0.979 for defect segmentation, with an inference time of only 18.98 seconds per 3D volume. Compared to existing approaches, our method achieves significant improvements in both segmentation accuracy—particularly in boundary localization and small-object recall—and computational efficiency. This work delivers a robust, end-to-end, deployable solution for automated, non-destructive evaluation of ceramic materials.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Non-destructive testing (NDT) is essential in ceramic manufacturing to ensure the quality of components without compromising their integrity. In this context, Optical Coherence Tomography (OCT) enables high-resolution internal imaging, revealing defects such as pores, delaminations, or inclusions. This paper presents an automatic defect detection system based on Deep Learning (DL), trained on OCT images with manually segmented annotations. A neural network based on the U-Net architecture is developed, evaluating multiple experimental configurations to enhance its performance. Post-processing techniques enable both quantitative and qualitative evaluation of the predictions. The system shows an accurate behavior of 0.979 Dice Score, outperforming comparable studies. The inference time of 18.98 seconds per volume supports its viability for detecting inclusions, enabling more efficient, reliable, and automated quality control.

Problem

• Automating defect detection in ceramic parts using deep learning
• Segmenting internal defects from OCT scans non-destructively
• Improving quality control accuracy and efficiency in manufacturing

Innovation

• U-Net architecture for defect segmentation
• Deep learning on OCT scan images
• Post-processing for quantitative qualitative evaluation