TY - JOUR
T1 - A framework for general-purpose microscopic image analysis via self-supervised learning
AU - Zheng, Zhiwei
AU - Yue, Xuezheng
AU - Wang, Jincheng
AU - Hou, Juan
PY - 2024/7
Y1 - 2024/7
N2 - Combining materials science, artificial intelligence (AI) offers great potential for the extensive quantitative analysis and processing of material characterization associated with high-throughput experiments. However, due to the complex and diverse morphology of structural components, the development of AI models requires substantial annotation and models are usually task-specific with limited generalizability to different clinical applications. Here, we present a universal self-supervised learning framework for microscopic images. Our framework learns generalizable representations from unlabelled images and provides a pixel-wise segmentation for quantitative microstructure analysis in a variety of materials science applications. Specifically, the framework learns feature from a single image by means of self-supervised learning, and adapts it to a series of related tasks. We show that our method consistently outperforms several comparisons supervised or weakly supervised learning models in the context of various applications. Our approach provides a generalizable solution to improve model performance and alleviate the annotation workload of experts to enable practical AI applications from microscopic imaging.
AB - Combining materials science, artificial intelligence (AI) offers great potential for the extensive quantitative analysis and processing of material characterization associated with high-throughput experiments. However, due to the complex and diverse morphology of structural components, the development of AI models requires substantial annotation and models are usually task-specific with limited generalizability to different clinical applications. Here, we present a universal self-supervised learning framework for microscopic images. Our framework learns generalizable representations from unlabelled images and provides a pixel-wise segmentation for quantitative microstructure analysis in a variety of materials science applications. Specifically, the framework learns feature from a single image by means of self-supervised learning, and adapts it to a series of related tasks. We show that our method consistently outperforms several comparisons supervised or weakly supervised learning models in the context of various applications. Our approach provides a generalizable solution to improve model performance and alleviate the annotation workload of experts to enable practical AI applications from microscopic imaging.
KW - Electron microscope
KW - Image segmentation
KW - Optical microscope
KW - Quantitative microscopic analysis
KW - Unsupervised learning
UR - http://www.scopus.com/inward/record.url?scp=85194589189&partnerID=8YFLogxK
U2 - 10.1016/j.matchar.2024.114003
DO - 10.1016/j.matchar.2024.114003
M3 - Article
AN - SCOPUS:85194589189
SN - 1044-5803
VL - 213
JO - Materials Characterization
JF - Materials Characterization
M1 - 114003
ER -