Data-efficient U-Net for Segmentation of Carbide Microstructures in SEM Images of Steel Alloys

TL;DR

This paper introduces a lightweight, data-efficient U-Net model that accurately segments carbide microstructures in SEM images of steel alloys using only 10 annotated images, significantly outperforming traditional methods.

Contribution

The study presents a novel, highly data-efficient deep learning segmentation pipeline that requires minimal annotated data and generalizes well across steel types.

Findings

Achieved Dice-Sørensen coefficient of 0.98 with only 10 images

Outperformed classical image analysis methods (0.85)

Reduced annotation effort by an order of magnitude

Abstract

Understanding reactor-pressure-vessel steel microstructure is crucial for predicting mechanical properties, as carbide precipitates both strengthen the alloy and can initiate cracks. In scanning electron microscopy images, gray-value overlap between carbides and matrix makes simple thresholding ineffective. We present a data-efficient segmentation pipeline using a lightweight U-Net (30.7~M parameters) trained on just \textbf{10 annotated scanning electron microscopy images}. Despite limited data, our model achieves a \textbf{Dice-S{\o}rensen coefficient of 0.98}, significantly outperforming the state-of-the-art in the field of metallurgy (classical image analysis: 0.85), while reducing annotation effort by one order of magnitude compared to the state-of-the-art data efficient segmentation model. This approach enables rapid, automated carbide quantification for alloy design and generalizes to other steel types, demonstrating the potential of data-efficient deep learning in reactor-pressure-vessel steel analysis.