Instance Segmentation of Dislocations in TEM Images

TL;DR

This paper evaluates and compares advanced instance segmentation methods for detecting dislocations in TEM images, introducing a novel length-aware metric that improves the assessment of segmentation quality in materials science applications.

Contribution

It presents a comprehensive comparison of Mask R-CNN and YOLOv8 for dislocation segmentation and introduces a physics-based, length-aware metric for better performance evaluation.

Findings

High accuracy segmentation suitable for domain-specific analysis

The length-aware metric outperforms traditional pixel-wise metrics

Quantitative analysis of dislocation geometry enabled by segmentation

Abstract

Quantitative Transmission Electron Microscopy (TEM) during in-situ straining experiment is able to reveal the motion of dislocations -- linear defects in the crystal lattice of metals. In the domain of materials science, the knowledge about the location and movement of dislocations is important for creating novel materials with superior properties. A long-standing problem, however, is to identify the position and extract the shape of dislocations, which would ultimately help to create a digital twin of such materials. In this work, we quantitatively compare state-of-the-art instance segmentation methods, including Mask R-CNN and YOLOv8. The dislocation masks as the results of the instance segmentation are converted to mathematical lines, enabling quantitative analysis of dislocation length and geometry -- important information for the domain scientist, which we then propose to include as a novel length-aware quality metric for estimating the network performance. Our segmentation pipeline shows a high accuracy suitable for all domain-specific, further post-processing. Additionally, our physics-based metric turns out to perform much more consistently than typically used pixel-wise metrics.