UA-Net: Uncertainty-Aware Network for TRISO Image Semantic Segmentation

TL;DR

UA-Net is a deep learning framework designed for semantic segmentation of TRISO fuel micrographs, incorporating uncertainty estimation to improve defect detection and reduce manual analysis.

Contribution

The paper introduces UA-Net, a novel uncertainty-aware deep learning model with a multi-stage training strategy for accurate TRISO micrograph segmentation.

Findings

Achieved 95.5% mIoU and 97.3% mP on test images.

Meta-model attained 91.8% specificity and 93.5% sensitivity.

Demonstrated high accuracy in qualitative analysis of new TRISO images.

Abstract

Tristructural isotropic (TRISO)-coated particle fuels undergo dimensional changes and chemical reactions during high-temperature neutron irradiation. Post-irradiation materialography helps understand processes that impact fuel performance, such as coating integrity and fission product retention. Conventionally, experts manually evaluate features in thousands of cross sections of sub-mm-sized samples, which is tedious and subjective. In this work, we propose UA-Net, a deep learning framework that segments five characteristic regions of TRISO fuel micrographs and generates an uncertainty map for predictions. The model uses a multi-stage pretraining strategy, starting with general image representations learned from ImageNet, followed by fine-tuning on TRISO micrographs from various irradiation experiments and AGR-5/6/7 particle cross sections. A meta-model for uncertainty prediction is integrated to identify small defects in TRISO images. UA-Net was evaluated on a test set of 102 images, achieving mean Intersection over Union (mIoU) and mean Precision (mP) of 95.5% and 97.3%, respectively. The meta-model achieved a specificity of 91.8% and sensitivity of 93.5%, demonstrating strong performance in detecting misclassifications. The model was also applied to new TRISO images for qualitative evaluation, showing high accuracy in extracting layer regions.