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

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 $\mathbf{\text{10}}\mathbf{\text{annotated}}\mathbf{\text{scanning}}\mathbf{\text{electron}}\mathbf{\text{microscopy}}\mathbf{\text{images}}$. Despite limited data, our model achieves a $\mathbf{\text{Dice-Sørensen}}\mathbf{\text{coefficient}}\mathbf{\text{of}}\mathbf{\text{0.98}}$, 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.