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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Gerçek, Alinda Ezgi, Korten, Till, Chekhonin, Paul, Hassan, Maleeha, Steinbach, Peter
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908653625278464
author Gerçek, Alinda Ezgi
Korten, Till
Chekhonin, Paul
Hassan, Maleeha
Steinbach, Peter
author_facet Gerçek, Alinda Ezgi
Korten, Till
Chekhonin, Paul
Hassan, Maleeha
Steinbach, Peter
contents 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-Sørensen 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_11485
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Data-efficient U-Net for Segmentation of Carbide Microstructures in SEM Images of Steel Alloys
Gerçek, Alinda Ezgi
Korten, Till
Chekhonin, Paul
Hassan, Maleeha
Steinbach, Peter
Machine Learning
Materials Science
I.4.6
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-Sørensen 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.
title Data-efficient U-Net for Segmentation of Carbide Microstructures in SEM Images of Steel Alloys
topic Machine Learning
Materials Science
I.4.6
url https://arxiv.org/abs/2511.11485