Quantification and classification of carbon nanotubes in electron micrographs using vision foundation models

Accurate characterization of carbon nanotube morphologies in electron microscopy images is vital for exposure assessment and toxicological studies, yet current workflows rely on slow, subjective manual segmentation. This work presents a unified framework that leverages vision foundation models to automate the quantification and classification of carbon nanotubes (CNTs) in electron microscopy images. First, an interactive quantification tool built on the Segment Anything Model segments particles with near-perfect accuracy using minimal user input. Second, a classification pipeline uses the resulting masks to spatially constrain a DINOv2 vision transformer, extracting features exclusively from particle regions while suppressing background noise. Evaluated on a dataset of approximately 1800 TEM images, the architecture achieves 89.5% cross-validated accuracy and 92.7% on a held-out test set in distinguishing four CNT morphologies, outperforming the previous baseline while using a fraction of the training data. Instance-level processing enables the framework to resolve mixed samples, correctly classifying distinct particle types co-existing within a single field of view. These results demonstrate that integrating zero-shot segmentation with self-supervised feature learning enables high-throughput, reproducible nanomaterial analysis, transforming a labor-intensive bottleneck into a scalable, data-driven process.

Authors

Publication Details

Journal
Scientific Reports
Published
2026-11-21
DOI
https://doi.org/10.1038/s41598-026-79572-1
Primary Topic
Advanced Electron Microscopy Techniques and Applications
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Quantification and classification of carbon nanotubes in electron micrographs using vision foundation models

Matthew M. Dahm, S. Pradeep, Jeff D. Eldredge, Chen Wang et al.
2 links
Scientific Reports
Advanced Electron Microscopy Techniques and Applications
article

Quantification and classification of carbon nanotubes in electron micrographs using vision foundation models

Matthew M. Dahm, S. Pradeep, Jeff D. Eldredge, Chen Wang, Candace S. J. Tsai
article en

Abstract

Accurate characterization of carbon nanotube morphologies in electron microscopy images is vital for exposure assessment and toxicological studies, yet current workflows rely on slow, subjective manual segmentation. This work presents a unified framework that leverages vision foundation models to automate the quantification and classification of carbon nanotubes (CNTs) in electron microscopy images. First, an interactive quantification tool built on the Segment Anything Model segments particles with near-perfect accuracy using minimal user input. Second, a classification pipeline uses the resulting masks to spatially constrain a DINOv2 vision transformer, extracting features exclusively from particle regions while suppressing background noise. Evaluated on a dataset of approximately 1800 TEM images, the architecture achieves 89.5% cross-validated accuracy and 92.7% on a held-out test set in distinguishing four CNT morphologies, outperforming the previous baseline while using a fraction of the training data. Instance-level processing enables the framework to resolve mixed samples, correctly classifying distinct particle types co-existing within a single field of view. These results demonstrate that integrating zero-shot segmentation with self-supervised feature learning enables high-throughput, reproducible nanomaterial analysis, transforming a labor-intensive bottleneck into a scalable, data-driven process.

Scientific Reports
Centers for Disease Control and Prevention, National Institute for Occupational Safety and Health
Advanced Electron Microscopy Techniques and Applications
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon