Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
October 5, 2025Open Access

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

View Full Paper
Ask AI
Bookmark
Share

Authors

ALAndrés Laveda-MartínezNGNatalia P. García-de-la-PuenteFGFernando García-Torres

Discussion

Loading...

Member takes

Overview

Automated system detects defects in OCT scans using deep learning, indicating improvements in quality control.

Key Points

  • The developed system achieved a Dice Score of 0.979, demonstrating high accuracy in defect detection.
  • Utilizing a U-Net architecture, the automated system enhances detection of defects in ceramic parts for non-destructive testing.
  • Post-processing techniques were applied for both quantitative and qualitative evaluation of the defect segmentations.
  • The system's inference time of 18.98 seconds per volume indicates its potential for efficient quality assurance in manufacturing.

Cite This Study

Laveda-Martínez et al. (2025) studied this question.

synapsesocial.com/papers/68e25378d6d66a53c24741cdhttps://doi.org/10.48550/arxiv.2510.00745
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 13-Dimension Epithelial Segmentation in Optical Coherence Tomography of the Oral Cavity Using Deep Learning2024 · 4 citations
  2. 2Three-Dimension Epithelial Segmentation in Optical Coherence Tomography of the Oral Cavity Using Deep Learning2024 · 10 citations
  3. 3CeraMIRScan: Mid-infrared OCT Scan Dataset for Ceramic Quality Assessment2026
  4. 4Deep learning for three-dimensional segmentation of electron microscopy images of complex ceramic materials2024 · 41 citations
  5. 5Deep Learning for Classification of Internal Defects in Fused Filament Fabrication Using Optical Coherence Tomography2026 · 1 citations