Pith. sign in

REVIEW 2 major objections 5 minor 152 references

AI in nanoparticle electron microscopy is shifting from labeling what is visible to recovering structure, dynamics, and materials insight.

Reviewed by Pith at T0; open to challenge. T0 means a machine referee read the full paper against a public rubric. the ladder, T0–T4 →

Challenge this review Re-run · record.json Download PDF Read on arXiv ↗

T0 review · grok-4.5

2026-07-14 12:05 UTC pith:N35EQ5CQ

load-bearing objection Solid challenge-organized review of AI for nanoparticle EM; useful taxonomy and fidelity caveats, ordinary review-selection risk on the tables. the 2 major comments →

arxiv 2607.10388 v1 pith:N35EQ5CQ submitted 2026-07-11 cond-mat.mtrl-sci cs.AI

The evolution of AI from image interpretation toward scientific inference in nanoparticle electron microscopy

Evropi Toulkeridou , Jiafei Li , Leonardo Lari , Panagiotis Grammatikopoulos This is my paper
classification cond-mat.mtrl-sci cs.AI
keywords electron microscopynanoparticlesdeep learningcomputer visionin situ TEMstructural inferencephysics-informed learningautonomous microscopy
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

The pith

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This review argues that artificial intelligence for nanoparticle electron microscopy has moved past routine image labeling. Early work automated detection, counting, and segmentation of particles in TEM images. Newer methods try to restore atomic-scale detail from noisy low-dose data, infer three-dimensional shape and crystallography from two-dimensional projections, and quantify growth, coalescence, and surface motion in in situ videos. The authors organize the field by scientific challenge rather than algorithm fashion, and they show how convolutional networks, transformers, self-supervised models, foundation models, and physics-informed training are being combined with simulations and microscope metadata. The practical stake is clear: once AI can extract physically meaningful descriptors at scale, electron microscopy becomes a quantitative engine for relating synthesis, structure, dynamics, and function, and for closing the loop toward autonomous materials discovery.

Core claim

AI methodologies in nanoparticle electron microscopy have evolved from image-level interpretation—detection and segmentation—into tools for scientific inference: recovering lattice-level structure under noise, estimating latent three-dimensional morphology from projections, and quantifying dynamic nanoscale processes, by coupling computer vision with microscopy physics, simulation-based training, metadata, and increasingly autonomous experimental control.

What carries the argument

A hierarchical task ladder from detection and segmentation, through atomic-resolution restoration, to 2D-to-3D structural inference and spatiotemporal analysis of in situ data, with physics-informed and simulation-driven learning as the bridge from visible pixels to latent physical variables.

Load-bearing premise

That the reported performance ranges and maturity levels across detection, denoising, structural inference, and dynamics fairly represent the broader literature, even though many high scores rest on simulated ground truth or carefully curated datasets that may not match routine experimental conditions.

What would settle it

A community benchmark that holds the same models to experimental nanoparticle TEM, HRTEM, and in situ video sets with independent physical validation (for example measured growth rates, facet statistics, or strain maps) and shows that the claimed progression from image labeling to reliable scientific inference does not hold outside simulation or narrow curated tests.

Watch this falsifier — get emailed when new claim-graph text bears on it.

If this is right

  • Detection and segmentation become routine infrastructure, while the competitive frontier shifts to restoration fidelity, uncertainty-aware 3D inference, and kinetic quantification from video.
  • Physics-informed and hybrid simulation–experiment training becomes standard for atomic-resolution and inverse problems because pure data-driven models lack experimental ground truth.
  • Benchmarking moves from PSNR, Dice, and mAP toward structural fidelity metrics (such as Fourier ring correlation) and measurable physical outputs (diffusion coefficients, coalescence rates, facet distributions).
  • Foundation models, multimodal image–metadata systems, and closed-loop AI control turn microscopes into active discovery platforms rather than post-processing cameras.
  • Materials discovery pipelines can treat AI-extracted nanoparticle descriptors as direct inputs to structure–property models and inverse design.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • If structural inference and dynamics remain under-benchmarked relative to detection, the field risks overstating readiness for autonomous materials discovery while the load-bearing inverse problems stay unstandardized.
  • The same hierarchical ladder implies that progress on rare-event kinetics and defect energetics will depend more on uncertainty quantification and domain adaptation than on larger generic vision backbones alone.
  • Commercial AI microscopy platforms will face pressure to publish transparent experimental benchmarks, not only internal Dice or mAP numbers, if the review’s maturity map is taken seriously.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit.

Referee Report

2 major / 5 minor

Summary. This review argues that AI for nanoparticle electron microscopy has progressed from image-level interpretation (detection/segmentation of TEM ensembles) toward scientific inference: atomic-resolution restoration with structural fidelity, 2D-to-3D structural inference, spatiotemporal analysis of in situ dynamics, and closed-loop autonomous experimentation. The narrative is organized by scientific challenge rather than by algorithm family (Fig. 2; §§4–7), covering TEM/HRTEM/STEM and in situ TEM, and spanning CNNs through transformers, self-supervised learning, foundation models, multimodal AI, and physics-informed/simulation-driven methods. Representative performance and evaluation tables (Tables 1–4) and architecture appendices (Tables A1–A4) support maturity rankings and a forward-looking agenda (Table 5; §8).

Significance. If the synthesis is accepted, the paper provides a useful, problem-centered map of a rapidly expanding and fragmented literature for materials scientists and microscopists. Strengths include the hierarchical framing (Fig. 2), repeated emphasis on simulation-to-experiment domain gap, structural fidelity over PSNR/SSIM (FRC, crystallographic consistency), and the need for uncertainty quantification and community benchmarks (§§5.4, 6.3, 7.4, 8). The appendices (A1–A4) and commercial-tool mention give practical orientation. As a review, its value is organizational and critical rather than a new theorem or experiment; residual risk is ordinary selection/maturity bias in aggregated metrics, which the manuscript already flags.

major comments (2)
  1. Table 1 and §4.5 present typical mAP/Dice/IoU ranges (e.g., Dice 0.85–0.95, mAP >0.90) as evidence of maturity. The text correctly notes dependence on morphology, contrast, and annotation, but the table still reads as cross-study comparable. Please state explicitly that ranges are illustrative upper bounds from curated datasets (often with simulated or expert labels), not meta-analytic estimates, and add a short note on how many studies and what domain shifts underlie each row so maturity rankings cannot be over-read.
  2. Tables 2–4 and §§5.4, 6.3, 7.4 correctly stress missing experimental ground truth and domain shift, yet Table 5 and §8 still rank detection/segmentation as “highly mature” and list foundation models/closed-loop systems as primary next drivers. Tighten the link: either qualify maturity labels with “on curated/static TEM” vs “atomic/dynamic/inverse tasks,” or add one paragraph that separates (i) routine morphology pipelines from (ii) inference tasks where simulation fidelity and uncertainty remain load-bearing, so the evolutionary claim is not overstated by the most mature subfield alone.
minor comments (5)
  1. Figure 1 caption and text cite Scopus analysis “performed in April 2026” and a 2025 peak of 735 papers; ensure the query string, date, and counts are reproducible and consistent with the arXiv posting timeline.
  2. Several figure panels (Figs. 3–7, A1) are author-generated schematics “inspired by” literature; captions should state more clearly that they are illustrative, not reprocessed experimental data, to avoid misreading as primary results.
  3. Reference list has occasional incomplete or inconsistent entries (e.g., missing DOIs or venue details for some 2025–2026 items; Table A4 “Giner et al.” with “—” DOI). Normalize citations and fix typographical issues (e.g., “Heslignton,” duplicated sensing refs [7, 12, 12]).
  4. Appendix Tables A1–A3 are valuable but dense; a brief caveat that “First Use in Microscopy” is a class of applications rather than a single definitive paper (already noted in text) should appear in the table caption for skimmers.
  5. Commercial platform SenseAI is listed in Table A4/Table 5; a one-sentence disclosure of any author relationship (or none) would improve transparency for readers.

Circularity Check

0 steps flagged

No circular derivation: this is a hierarchical literature review whose evolutionary narrative is synthesis of external work, not a self-referential prediction or fitted result.

full rationale

The manuscript is a review organized around a hierarchy of AI tasks in nanoparticle electron microscopy (detection/segmentation → atomic restoration → 2D-to-3D inference → spatiotemporal dynamics → scientific inference; Abstract; §§1–3, 8; Fig. 2). It does not claim a first-principles derivation, uniqueness theorem, or parameter-free prediction that could reduce to its own inputs. Representative performance ranges (Tables 1–4) and architecture timelines (Tables A1–A4) are presented as literature summaries with explicit caveats on simulated ground truth, domain shift, missing community benchmarks, and hallucination risk (§§4.5, 5.4, 6.3, 7.4). Author-related citations (e.g., nanoparticle synthesis/microscopy background) are ordinary context and do not force the review’s conclusions by construction. No self-definitional equation, fitted-input-called-prediction, load-bearing self-citation uniqueness claim, or renamed known result appears. Circularity score is therefore 0.

Axiom & Free-Parameter Ledger

0 free parameters · 4 axioms · 0 invented entities

As a review, the paper’s load-bearing premises are domain assumptions about microscopy physics, data scarcity, and the validity of literature-reported metrics, not free parameters or invented physical entities. No numerical model is fitted to produce a central prediction.

axioms (4)
  • domain assumption TEM/STEM images are 2D projections of 3D nanostructures whose contrast is governed by electron scattering, dose, aberrations, thickness, and orientation.
    Invoked throughout §§2, 5–6 as the reason restoration and 3D inference are inverse problems rather than pure computer-vision tasks.
  • domain assumption Experimentally verified noise-free atomic-resolution ground truth is generally unavailable, so simulation-driven or self-supervised training is necessary.
    Central to §§5.2 and 6.1; underpins reliance on multi-slice simulations and physics-informed learning.
  • ad hoc to paper Reported detection/segmentation metrics (mAP, Dice, IoU) and restoration metrics (PSNR, SSIM, FRC) are sufficiently comparable across studies to support maturity rankings.
    Tables 1–4 aggregate heterogeneous literature results; the paper itself notes dependence on morphology, contrast, and annotation quality.
  • ad hoc to paper Foundation models, multimodal learning, and closed-loop autonomous microscopy will become primary drivers of next-generation nanoparticle characterization.
    Forward-looking claim in Abstract, §8, and Table 5; supported by early citations but not established as settled fact.

pith-pipeline@v1.1.0-grok45 · 37574 in / 2896 out tokens · 34091 ms · 2026-07-14T12:05:39.725834+00:00 · methodology

0 comments
read the original abstract

Artificial intelligence (AI) is transforming electron microscopy by enabling quantitative analysis of increasingly large and complex datasets for nanoparticle characterization. Recent advances in machine learning (ML) and deep learning (DL) have expanded microscopy from a descriptive imaging technique into a data-driven platform for structural interpretation, dynamic analysis, and scientific inference. This review examines AI methodologies for nanoparticle electron microscopy, focusing on transmission electron microscopy (TEM), high-resolution transmission electron microscopy (HRTEM), scanning transmission electron microscopy (STEM), and in situ TEM. The discussion is organized around the principal challenges in nanoparticle characterization, including particle detection, segmentation, morphology quantification, atomic-resolution restoration, defect identification, two-dimensional-to-three-dimensional structural inference, and analysis of dynamic processes in situ. We review computational approaches from conventional ML and convolutional neural networks to transformer architectures, self-supervised learning, foundation models, multimodal AI, and physics-informed learning. We further discuss integrating microscopy data with simulations, metadata, and autonomous experimentation to relate nanoparticle structure, dynamics, synthesis conditions, and functional properties. The advantages, limitations, benchmarking, and data requirements of current methodologies are critically assessed. Finally, emerging opportunities for foundation models, AI-guided microscopy, closed-loop experimentation, and autonomous materials discovery are discussed. By integrating advances across computer vision, materials informatics, and electron microscopy, this review highlights the role of AI in next-generation nanoparticle characterization and accelerated materials discovery.

Figures

Figures reproduced from arXiv: 2607.10388 by Evropi Toulkeridou, Jiafei Li, Leonardo Lari, Panagiotis Grammatikopoulos.

Figure 1
Figure 1. Figure 1: Annual number of publications related to artificial intelligence and nanoparticle electron microscopy indexed in Scopus between 2012 and 2026, based on the query [(TEM OR HRTEM OR STEM) AND nanoparticle AND (deep learning OR machine learning)] restricted to the Materials Science subject area. A total of 2415 documents were identified. The plot reveals limited activity during the early 2010s, followed by ra… view at source ↗
Figure 3
Figure 3. Figure 3: Representative electron microscopy modalities commonly used in nanoparticle characterization. (a) Conventional TEM illustrating nanoparticle ensemble morphology and size distribution. (b) HRTEM illustrating atomic-resolution lattice imaging within an individual nanoparticle. (c) Illustrative in situ TEM time sequence showing structural evolution during dynamic nanoparticle processes. All panels are author-… view at source ↗
Figure 4
Figure 4. Figure 4: Workflow for AI-assisted nanoparticle analysis in TEM. Raw TEM images are processed through DL–based detection and instance segmentation to identify individual nanoparticles, delineate particle boundaries, and extract quantitative descriptors such as size distributions, morphology, and population statistics. The figure illustrates the transition from microscopy image acquisition to automated high-throughpu… view at source ↗
Figure 7
Figure 7. Figure 7: Schematic illustration of AI-assisted spatiotemporal analysis of nanoparticle dynamics in in situ TEM. (a) Initial nanoparticle configuration before structural evolution. (b) Dynamic restructuring and neck formation during particle interaction. (c) Final coalesced nanoparticle morphology. (d) Deep learning-assisted temporal quantification through automated tracking and extraction of projected area, equival… view at source ↗

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

152 extracted references · 75 canonical work pages · 2 internal anchors

  1. [1]

    Nanoparticle Design by Gas-Phase Synthesis

    Grammatikopoulos, P.; Steinhauer, S.; Vernieres, J.; Singh, V.; Sowwan, M. Nanoparticle Design by Gas-Phase Synthesis. Adv. Phys. X 2016, 1, 81–100. https://doi.org/10.1080/23746149.2016.1142829

    doi:10.1080/23746149.2016.1142829 2016

  2. [2]

    Metal Catalysts for Heterogeneous Catalysis: From Single Atoms to Nanoclusters and Nanoparticles

    Liu, L.; Corma, A. Metal Catalysts for Heterogeneous Catalysis: From Single Atoms to Nanoclusters and Nanoparticles. Chem. Rev. 2018, 118, 4981–5079. https://doi.org/10.1021/acs.chemrev.7b00776

    work page doi:10.1021/acs.chemrev.7b00776 2018

  3. [3]

    U.; Khan, M

    Farooq, N.; Rehman, Z. U.; Khan, M. I.; et al. Nanomaterial-Based Energy Conversion and Energy Storage Devices: A Comprehensive Review. New J. Chem. 2024, 48, 8933. https://doi.org/10.1039/D3NJ04846B

    work page doi:10.1039/d3nj04846b 2024

  4. [4]

    N.; Hall, W

    Anker, J. N.; Hall, W. P.; Lyandres, O.; Shah, N. C.; Zhao, J.; Van Duyne, R. P. Biosensing with Plasmonic Nanosensors. Nat. Mater. 2008, 7, 442–453. https://doi.org/10.1038/nmat2162

    doi:10.1038/nmat2162 2008

  5. [5]

    Magnetic Nanoparticles: Synthesis, Anisotropy, and Applications

    Ma, Z.; et al. Magnetic Nanoparticles: Synthesis, Anisotropy, and Applications. Chem. Rev. 2022, 122, 127–231. https://doi.org/10.1021/acs.chemrev.1c00860

    work page doi:10.1021/acs.chemrev.1c00860 2022

  6. [6]

    McNamara, K.; Tofail, S. A. M. Nanoparticles in Biomedical Applications. Adv. Phys. X 2017, 2, 54–

    2017

  7. [7]

    https://doi.org/10.1080/23746149.2016.1254570

    doi:10.1080/23746149.2016.1254570 2016

  8. [8]

    M.; Hafner, J

    Mayer, K. M.; Hafner, J. H. Localized Surface Plasmon Resonance Sensors. Chem. Rev. 2011, 111, 3828–3857. https://doi.org/10.1021/cr100313v

    doi:10.1021/cr100313v 2011

  9. [9]

    B.; Gupta, A.; Pandey, A

    Bhattacharya, S.; Gupta, A. B.; Gupta, A.; Pandey, A. A Review on Nanomaterials for Environmental Remediation. Energy Environ. Sci. 2012, 5, 8075–8109. https://doi.org/10.1039/C2EE21818F

    work page doi:10.1039/c2ee21818f 2012

  10. [10]

    L.; Seifer, S.; Ilavsky, J.; Pellin, M.; Sowwan, M.; Grammatikopoulos, P.; Vajda, S

    Halder, A.; Kioseoglou, J.; Yang, B.; Kolipaka, K. L.; Seifer, S.; Ilavsky, J.; Pellin, M.; Sowwan, M.; Grammatikopoulos, P.; Vajda, S. Nanoassemblies of Ultrasmall Clusters with Remarkable Activity in 43 Carbon Dioxide Conversion to C1 Fuels. Nanoscale 2019, 11, 4683–4687. https://doi.org/10.1039/C8NR06664G

    work page doi:10.1039/c8nr06664g 2019

  11. [11]

    Hydrogen Flux through Size-Selected Pd Nanoparticles into Underlying Mg Nanofilms

    Kumar, S.; Pavloudis, T.; Singh, V.; Nguyen, S.; Steinhauer, S.; Pursell, C.; Clemens, B.; Kioseoglou, J.; Grammatikopoulos, P.; Sowwan, M. Hydrogen Flux through Size-Selected Pd Nanoparticles into Underlying Mg Nanofilms. Adv. Energy Mater. 2018, 8, 1701326. https://doi.org/10.1002/aenm.201701326

    work page doi:10.1002/aenm.201701326 2018

  12. [12]

    S.; Mathioudaki, S.; Kioseoglou, J.; Grammatikopoulos, P

    Bohra, M.; Giaremis, S.; Abisegapriyan, K. S.; Mathioudaki, S.; Kioseoglou, J.; Grammatikopoulos, P. Ferromagnetic-Antiferromagnetic Coupling in Gas-Phase Synthesized M(Fe, Co, Ni)-Cr Nanoparticles for Next-Generation Magnetic Applications. Adv. Sci. 2024, 11, 2403708. https://doi.org/10.1002/advs.202403708

    work page doi:10.1002/advs.202403708 2024

  13. [13]

    Adjusting Surface Coverage of Pt Nanocatalyst Decoration for Selectivity Control in CMOS-Integrated SnO₂ Thin Film Sensors

    Sosada-Ludwikowska, F.; Reiner, L.; Egger, L.; Lackner, E.; Krainer, J.; Wimmer-Teubenbacher, R.; Singh, V.; Steinhauer, S.; Grammatikopoulos, P.; Köck, A. Adjusting Surface Coverage of Pt Nanocatalyst Decoration for Selectivity Control in CMOS-Integrated SnO₂ Thin Film Sensors. Nanoscale Adv. 2024, 6, 1127–1134. https://doi.org/10.1039/D3NA00552F

    work page doi:10.1039/d3na00552f 2024

  14. [14]

    E.; Nordlund, K.; Djurabekova, F.; Grammatikopoulos, P.; Sowwan, M

    Vernieres, J.; Steinhauer, S.; Zhao, J.; Chapelle, A.; Menini, P.; Dufour, N.; Diaz, R. E.; Nordlund, K.; Djurabekova, F.; Grammatikopoulos, P.; Sowwan, M. Gas Phase Synthesis of Multifunctional Fe- Based Nanocubes. Adv. Funct. Mater. 2017, 27, 1605328. https://doi.org/10.1002/adfm.201605328

    doi:10.1002/adfm.201605328 2017

  15. [15]

    B.; Carter, C

    Williams, D. B.; Carter, C. B. Transmission Electron Microscopy: A Textbook for Materials Science; Springer: New York, 2009

    2009

  16. [16]

    J.; Nellist, P

    Pennycook, S. J.; Nellist, P. D., Eds. Scanning Transmission Electron Microscopy: Imaging and Analysis; Springer: New York, 2011

    2011

  17. [17]

    A Versatile Machine Learning Workflow for High-Throughput Analysis of Supported Metal Catalyst Particles

    Genç, A.; Marlowe, J.; Jalil, A.; Belzberg, D.; Kovarik, L.; Christopher, P. A Versatile Machine Learning Workflow for High-Throughput Analysis of Supported Metal Catalyst Particles. Ultramicroscopy 2025, 271, 114116. https://doi.org/10.1016/j.ultramic.2025.114116

    work page doi:10.1016/j.ultramic.2025.114116 2025

  18. [18]

    Statistical Characterization of the Morphologies of Nanoparticles through Machine Learning Based Electron Microscopy Image Analysis

    Lee, B.; et al. Statistical Characterization of the Morphologies of Nanoparticles through Machine Learning Based Electron Microscopy Image Analysis. ACS Nano 2020, 14, 17125–17133. https://doi.org/10.1021/acsnano.0c06809

    work page doi:10.1021/acsnano.0c06809 2020

  19. [19]

    Ziatdinov, M.; Dyck, O.; Jesse, S.; Kalinin, S. V. Deep Learning of Atomically Resolved Scanning Transmission Electron Microscopy Data. ACS Nano 2017, 11:12, 12742-12752. https://doi.org/10.1021/acsnano.7b07504

    work page doi:10.1021/acsnano.7b07504 2017

  20. [20]

    B.; Hansen, T

    Madsen, J.; Liu, P.; Kling, J.; Wagner, J. B.; Hansen, T. W.; Winther, O.; Schiøtz, J. A. Deep Learning Approach to Identify Local Structures in Atomic-Resolution Transmission Electron Microscopy Images. Adv. Theory Simul. 2018, 1, 1800037. https://doi.org/10.1002/adts.201800037

    work page doi:10.1002/adts.201800037 2018

  21. [21]

    Four-Dimensional Scanning Transmission Electron Microscopy (4D-STEM): From Scanning Nanodiffraction to Ptychography and Beyond

    Ophus, C. Four-Dimensional Scanning Transmission Electron Microscopy (4D-STEM): From Scanning Nanodiffraction to Ptychography and Beyond. Microsc. Microanal. 2019, 25, 563–582. https://doi.org/10.1017/S1431927619000497

    doi:10.1017/s1431927619000497 2019

  22. [22]

    Characterization of Nanomaterials Using In Situ Liquid-Cell Transmission Electron Microscopy

    Chen, Y.; et al. Characterization of Nanomaterials Using In Situ Liquid-Cell Transmission Electron Microscopy. ACS Appl. Nano Mater. 2023, 6, 24, 22545–22567. https://doi.org/10.1021/acsanm.3c03003 44

    work page doi:10.1021/acsanm.3c03003 2023

  23. [23]

    Recent Advances in In Situ Transmission Electron Microscopy for Heterogeneous Catalysis

    Qu, J.; et al. Recent Advances in In Situ Transmission Electron Microscopy for Heterogeneous Catalysis. Chem. Soc. Rev. 2023, 26, 7, 107072. https://doi.org/10.1016/j.isci.2023.107072

    work page doi:10.1016/j.isci.2023.107072 2023

  24. [24]

    H.; Johnstone, D

    Martineau, B. H.; Johnstone, D. N.; van Helvoort, A. T. J.; et al. Unsupervised Machine Learning Applied to Scanning Precession Electron Diffraction Data. Adv. Struct. Chem. Imaging 2019, 5, 3. https://doi.org/10.1186/s40679-019-0063-3

    doi:10.1186/s40679-019-0063-3 2019

  25. [25]

    Scanning Precession Electron Diffraction—Beyond Orientation and Phase Mapping

    Bergh, T. Scanning Precession Electron Diffraction—Beyond Orientation and Phase Mapping. Microsc. Microanal. 2025, 31 (Suppl. 1), ozaf048.288. https://doi.org/10.1093/mam/ozaf048.288

    work page doi:10.1093/mam/ozaf048.288 2025

  26. [26]

    L.; Lari, L.; Ward, M

    Gai, P. L.; Lari, L.; Ward, M. R.; Boyes, E. D. Visualisation of Single Atom Dynamics and their Role in Nanocatalysts under Controlled Reaction Environments. Chem. Phys. Lett. 2014, 592, 355–359. https://doi.org/10.1016/j.cplett.2013.12.038

    work page doi:10.1016/j.cplett.2013.12.038 2014

  27. [27]

    In Situ Chemoresistive Sensing in the Environmental TEM: Probing Functional Devices and their Nanoscale Morphology

    Steinhauer, S.; Vernieres, J.; Krainer, J.; Köck, A.; Grammatikopoulos, P.; Sowwan, M. In Situ Chemoresistive Sensing in the Environmental TEM: Probing Functional Devices and their Nanoscale Morphology. Nanoscale 2017, 9, 7380–7384. https://doi.org/10.1039/C6NR09322A

    work page doi:10.1039/c6nr09322a 2017

  28. [28]

    Thermal Oxidation of Size-Selected Pd Nanoparticles Supported on CuO Nanowires: The Role of the CuO–Pd Interface

    Steinhauer, S.; Zhao, J.; Singh, V.; Pavloudis, T.; Kioseoglou, J.; Nordlund, K.; Djurabekova, F.; Grammatikopoulos, P.; Sowwan, M. Thermal Oxidation of Size-Selected Pd Nanoparticles Supported on CuO Nanowires: The Role of the CuO–Pd Interface. Chem. Mater. 2017, 29, 6153–6160. https://doi.org/10.1021/acs.chemmater.7b02242

    work page doi:10.1021/acs.chemmater.7b02242 2017

  29. [29]

    Machine Learning in Electron Microscopy for Advanced Nanocharacterization: Current Developments, Available Tools and Future Outlook

    Botifoll, M.; et al. Machine Learning in Electron Microscopy for Advanced Nanocharacterization: Current Developments, Available Tools and Future Outlook. Nanoscale Horiz. 2022, 7, 1427–1477. https://doi.org/10.1039/D2NH00377E

    work page doi:10.1039/d2nh00377e 2022

  30. [30]

    Dynamic Wet-ETEM Observation of Pt/C Electrode Catalysts in a Moisturized Cathode Atmosphere

    Yoshida, K.; et al. Dynamic Wet-ETEM Observation of Pt/C Electrode Catalysts in a Moisturized Cathode Atmosphere. Nanotechnology 2014, 25, 425702. https://doi.org/10.1088/0957- 4484/25/42/425702

    doi:10.1088/0957- 2014

  31. [31]

    Y.; Ferrando, R.; Slater, T

    Dearg, M.; Roncaglia, C.; Nelli, D.; El Koraychy, E. Y.; Ferrando, R.; Slater, T. J. A.; Palmer, R. E. Frame-by-Frame Observations of Structure Fluctuations in Single Mass-Selected Au Clusters using Aberration-Corrected Electron Microscopy. Nanoscale Horiz. 2024, 9, 143–147. https://doi.org/10.1039/D3NH00291H

    work page doi:10.1039/d3nh00291h 2024

  32. [32]

    Ede, J. M. Review: Deep Learning in Electron Microscopy. Mach. Learn.: Sci. Technol. 2020, arXiv:2009.08328. https://doi.org/10.48550/arXiv.2009.08328

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2009.08328 2020

  33. [33]

    P.; Niu, Y.; Palmer, R

    Dearg, M.; Hoddinott, H. P.; Niu, Y.; Palmer, R. E.; Slater, T. J. A. Classification of Metal Nanoclusters using Convolutional Neural Networks. Microsc. Microanal. 2022, 28, 3000–3001. https://doi.org/10.1017/S1431927622011230

    work page doi:10.1017/s1431927622011230 2022

  34. [34]

    V.; et al

    Kalinin, S. V.; et al. Machine Learning in Scanning Transmission Electron Microscopy. Nat. Rev. Methods Primers 2022, 2, 11. https://doi.org/10.1038/s43586-022-00095-w

    doi:10.1038/s43586-022-00095-w 2022

  35. [35]

    V.; et al

    Kalinin, S. V.; et al. Deep Learning for Electron and Scanning Probe Microscopy. MRS Bull. 2022. https://doi.org/10.1557/s43577-022-00413-3 45

    work page doi:10.1557/s43577-022-00413-3 2022

  36. [36]

    Contrastive Image-Metadata Pre-Training for Materials Transmission Electron Microscopy

    Channing, G.; Keller, D.; Rossell, M. D.; Torr, P.; Helveg, S.; Eliasson, H. Contrastive Image– Metadata Pre-Training for Materials Transmission Electron Microscopy. arXiv 2026, arXiv:2604.24909. https://doi.org/10.48550/arXiv.2604.24909

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2604.24909 2026

  37. [37]

    A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools

    Van et al. A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools. arXiv 2025, arXiv:2506.20743v1. https://doi.org/10.48550/arXiv.2506.20743

    Pith/arXiv arXiv doi:10.48550/arxiv.2506.20743 2025

  38. [38]

    Morphology Prediction of Small Nanoparticles in Any Orientation from Single Electron Micrographs

    Eliasson et al. Morphology Prediction of Small Nanoparticles in Any Orientation from Single Electron Micrographs. npj Comput. Mater. 2026. https://doi.org/10.1038/s41524-026-02114-w

    work page doi:10.1038/s41524-026-02114-w 2026

  39. [39]

    P.; Famiani, S.; Sergides, A.; Lari, L.; Lloyd, D

    LaGrow, A. P.; Famiani, S.; Sergides, A.; Lari, L.; Lloyd, D. C.; Takahashi, M.; Maenosono, S.; Boyes, E. D.; Gai, P. L.; Thanh, N. T. K. Environmental STEM Study of the Oxidation Mechanism for Iron and Iron Carbide Nanoparticles. Materials 2022, 15, 1557. https://doi.org/10.3390/ma15041557

    work page doi:10.3390/ma15041557 2022

  40. [40]

    DetectNano: Deep Learning-Based Detection and Characterization of Nanoparticles in Electron Microscopy Images

    Ferji, K. DetectNano: Deep Learning-Based Detection and Characterization of Nanoparticles in Electron Microscopy Images. Nanoscale 2025, 17, 18777-18786. https://doi.org/10.1039/D5NR02446C

    work page doi:10.1039/d5nr02446c 2025

  41. [41]

    Lari, L.; Steinhauer, S.; Lazarov, V. K. In Situ TEM Oxidation Study of Fe Thin-Film Transformation to Single-Crystal Magnetite Nanoparticles. J. Mater. Sci. 2020, 55, 12897–12905. https://doi.org/10.1007/s10853-020-04917-8

    work page doi:10.1007/s10853-020-04917-8 2020

  42. [42]

    E.; Slater, T

    Dearg, M.; Lethbridge, S.; McCormack, J.; Palmer, R. E.; Slater, T. J. A. Characterisation of the Morphology of Surface-Assembled Au Nanoclusters on Amorphous Carbon. Nanoscale 2024, 16, 10827– 10832. https://doi.org/10.1039/D4NR00978A

    work page doi:10.1039/d4nr00978a 2024

  43. [43]

    P.; Welling, M

    Kingma, D. P.; Welling, M. Auto-Encoding Variational Bayes. arXiv 2013, arXiv:1312.6114. https://doi.org/10.48550/arXiv.1312.6114

    Pith/arXiv arXiv doi:10.48550/arxiv.1312.6114 2013

  44. [44]

    Y.; Young, N

    Li, Z. Y.; Young, N. P.; Di Vece, M.; Palomba, S.; Palmer, R. E.; Bleloch, A. L.; Curley, B. C.; Johnston, R. L.; Jiang, J.; Yuan, J. Three-Dimensional Atomic-Scale Structure of Size-Selected Gold Nanoclusters. Nature 2008, 451, 46–48. https://doi.org/10.1038/nature06470

    work page doi:10.1038/nature06470 2008

  45. [45]

    A.; Dunin-Borkowski, R

    Midgley, P. A.; Dunin-Borkowski, R. E. Electron Tomography and Holography in Materials Science. Nat. Mater. 2009, 8, 271–280. https://doi.org/10.1038/nmat2406

    work page doi:10.1038/nmat2406 2009

  46. [48]

    V.; et al

    Kalinin, S. V.; et al. Machine Learning for Automated Experimentation in Scanning Transmission Electron Microscopy. npj Comput. Mater. 2023, 9, 227. https://doi.org/10.1038/s41524-023-01142-0

    doi:10.1038/s41524-023-01142-0 2023

  47. [49]

    T.; Davies, D

    Butler, K. T.; Davies, D. W.; Cartwright, H.; Isayev, O.; Walsh, A. Machine Learning for Molecular and Materials Science. Nature 2018, 559, 547–555. https://doi.org/10.1038/s41586-018-0337-2

    doi:10.1038/s41586-018-0337-2 2018

  48. [50]

    Bishop, C. M. Pattern Recognition and Machine Learning; Springer: New York, 2006. 46

    2006

  49. [51]

    Support-Vector Networks

    Cortes, C.; Vapnik, V. Support-Vector Networks. Mach. Learn. 1995, 20, 273–297. https://doi.org/10.1007/BF00994018

    doi:10.1007/bf00994018 1995

  50. [52]

    Random Forests

    Breiman, L. Random Forests. Mach. Learn. 2001, 45, 5–32. https://doi.org/10.1023/A:1010933404324

    doi:10.1023/a:1010933404324 2001

  51. [53]

    Gradient-Based Learning Applied to Document Recognition

    LeCun, Y.; Bottou, L.; Bengio, Y.; Haffner, P. Gradient-Based Learning Applied to Document Recognition. Proc. IEEE 1998, 86, 2278–2324. https://doi.org/10.1109/5.726791

    doi:10.1109/5.726791 1998

  52. [54]

    Krizhevsky, A.; Sutskever, I.; Hinton, G. E. ImageNet Classification with Deep Convolutional Neural Networks. Adv. Neural Inf. Process. Syst. 2012, 25. https://doi.org/10.1145/3065386

    doi:10.1145/3065386 2012

  53. [56]

    U-Net: Convolutional Networks for Biomedical Image Segmentation

    Ronneberger, O.; Fischer, P.; Brox, T. U-Net: Convolutional Networks for Biomedical Image Segmentation. In Medical Image Computing and Computer-Assisted Intervention (MICCAI); 2015. https://doi.org/10.1007/978-3-319-24574-4_28

    doi:10.1007/978-3-319-24574-4_28 2015

  54. [57]

    Quantitative Analysis of Liquid-Phase Transmission Electron Microscopy Experiments Using Deep Learning

    Sun, Y.; et al. Quantitative Analysis of Liquid-Phase Transmission Electron Microscopy Experiments Using Deep Learning. Nanoscale 2024, 6, 2945-2954. https://doi.org/10.1039/D3NR04480G

    work page doi:10.1039/d3nr04480g 2024

  55. [58]

    Advancing Electron Microscopy Using Deep Learning: Recent Progress and Future Directions

    Chen, Y.; et al. Advancing Electron Microscopy Using Deep Learning: Recent Progress and Future Directions. Mach. Learn.: Sci. Technol. 2024, 7, 2, 022001. https://doi.org/10.1088/2515-7639/ad229b

    work page doi:10.1088/2515-7639/ad229b 2024

  56. [59]

    Recent Developments and Perspectives of Ti-Based Transition Metal Carbides/Nitrides for Photocatalytic Applications: A Critical Review

    Fan, Z.; et al. Recent Developments and Perspectives of Ti-Based Transition Metal Carbides/Nitrides for Photocatalytic Applications: A Critical Review. Mater. Today 2024, 76, 110-135. https://doi.org/10.1016/j.mattod.2024.05.003

    work page doi:10.1016/j.mattod.2024.05.003 2024

  57. [60]

    An Interpretable and Transferrable Vision Transformer Model for Rapid Materials Spectra Classification

    Chen, X.; et al. An Interpretable and Transferrable Vision Transformer Model for Rapid Materials Spectra Classification. Digital Discovery 2024, 3, 369–380. https://doi.org/10.1039/D3DD00198A

    work page doi:10.1039/d3dd00198a 2024

  58. [61]

    A Machine Learning Model for Textured X-Ray Scattering and Diffraction Image Denoising

    Zhou, Y.; et al. A Machine Learning Model for Textured X-Ray Scattering and Diffraction Image Denoising. npj Comput. Mater. 2023, 9, 58. https://doi.org/10.1038/s41524-023-01011-y

    work page doi:10.1038/s41524-023-01011-y 2023

  59. [62]

    Efficient and Robust Automated Segmentation of Nanoparticles and Aggregates from Transmission Electron Microscopy Images with Highly Complex Backgrounds

    Zhou, X.; et al. Efficient and Robust Automated Segmentation of Nanoparticles and Aggregates from Transmission Electron Microscopy Images with Highly Complex Backgrounds. Nanomaterials 2024, 14,

    2024

  60. [63]

    https://doi.org/10.3390/nano14141169

    doi:10.3390/nano14141169

  61. [64]

    Deep Learning Detection of Nanoparticles and Multiple Object Tracking of their Dynamic Evolution during In Situ ETEM Studies

    Faraz, M.; et al. Deep Learning Detection of Nanoparticles and Multiple Object Tracking of their Dynamic Evolution during In Situ ETEM Studies. Sci. Rep. 2022, 12, 2484. https://doi.org/10.1038/s41598-022-06308-2

    work page doi:10.1038/s41598-022-06308-2 2022

  62. [65]

    Enhancing Semantic Segmentation in High-Resolution TEM Images: A Comparative Study of Batch Normalization and Instance Normalization

    Kazimi, E.; et al. Enhancing Semantic Segmentation in High-Resolution TEM Images: A Comparative Study of Batch Normalization and Instance Normalization. Microsc. Microanal. 2025, 31, ozae093. https://doi.org/10.1093/mam/ozae093

    work page doi:10.1093/mam/ozae093 2025

  63. [66]

    Automated Nanoparticle Segmentation and Characterization Pipeline for Electron Microscopy

    Day, A.; et al. Automated Nanoparticle Segmentation and Characterization Pipeline for Electron Microscopy. Sci. Rep. 2025, 15, 17180. https://doi.org/10.1038/s41598-025-01337-z 47

    work page doi:10.1038/s41598-025-01337-z 2025

  64. [67]

    Self-Supervised Learning for Analysis of Liquid-Phase Transmission Electron Microscopy Data

    Kim, J.; et al. Self-Supervised Learning for Analysis of Liquid-Phase Transmission Electron Microscopy Data. Sci. Adv. 2025, 11, 14. https://doi.org/10.1126/sciadv.ads5552

    doi:10.1126/sciadv.ads5552 2025

  65. [68]

    AI-Assisted Design of Advanced Polymeric Materials: Challenges and Solutions

    Gao, Y.; et al. AI-Assisted Design of Advanced Polymeric Materials: Challenges and Solutions. Adv. Mater. 2025, 38, e202516857. https://doi.org/10.1002/adma.202516857

    work page doi:10.1002/adma.202516857 2025

  66. [69]

    I.; Haigh, S

    Kirkland, A. I.; Haigh, S. J. Exit Wavefunction Reconstruction in Transmission Electron Microscopy. In: Advanced Computing in Electron Microscopy, 2nd ed.; Springer: New York, 2009

    2009

  67. [70]

    J.; Yang, Q

    Pan, S. J.; Yang, Q. A Survey on Transfer Learning. IEEE Trans. Knowl. Data Eng. 2010, 22, 1345–

    2010

  68. [71]

    https://doi.org/10.1109/TKDE.2009.191

    doi:10.1109/tkde.2009.191 2009

  69. [72]

    P.; et al

    Treder, K. P.; et al. Applications of Deep Learning in Electron Microscopy. Mach. Learn.: Sci. Technol. 2022, 71(Supplement_1):i100-i115. PMID: 35275181. https://doi.org/10.1093/jmicro/dfab043

    work page doi:10.1093/jmicro/dfab043 2022

  70. [73]

    You Only Look Once: Unified, Real-Time Object Detection

    Redmon, J.; Divvala, S.; Girshick, R.; Farhadi, A. You Only Look Once: Unified, Real-Time Object Detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2016. https://doi.org/10.1109/CVPR.2016.91

    doi:10.1109/cvpr.2016.91 2016

  71. [74]

    Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

    Ren, S.; He, K.; Girshick, R.; Sun, J. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Trans. Pattern Anal. Mach. Intell. 2017, 39, 1137–1149. https://doi.org/10.1109/TPAMI.2016.2577031

    doi:10.1109/tpami.2016.2577031 2017

  72. [75]

    C.; et al

    Schloz, M.; Müller, J.; Pekin, T. C.; et al. Deep Reinforcement Learning for Data-Driven Adaptive Scanning in Ptychography. Sci. Rep. 2023, 13, 8732. https://doi.org/10.1038/s41598-023-35740-1

    doi:10.1038/s41598-023-35740-1 2023

  73. [76]

    Mask R-CNN

    He, K.; Gkioxari, G.; Dollár, P.; Girshick, R. Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV); 2017. https://doi.org/10.1109/ICCV.2017.322

    doi:10.1109/iccv.2017.322 2017

  74. [77]

    E.; Baum, D.; Doya, K.; Economo, E

    Toulkeridou, E.; Gutierrez, C. E.; Baum, D.; Doya, K.; Economo, E. P. Automated Segmentation of Insect Anatomy from Micro-CT Images using Deep Learning. Nat. Sci. 2023, 3, e20230010. https://doi.org/10.1002/ntls.20230010

    work page doi:10.1002/ntls.20230010 2023

  75. [78]

    Segment Anything

    Kirillov, A.; et al. Segment Anything. arXiv 2023, arXiv:2304.02643. https://doi.org/10.48550/arXiv.2304.02643

    Pith/arXiv arXiv doi:10.48550/arxiv.2304.02643 2023

  76. [79]

    Segment Anything in Medical Images

    Ma, J.; et al. Segment Anything in Medical Images. Nat. Commun. 2024, 15, 654. https://doi.org/10.1038/s41467-024-44824-z

    doi:10.1038/s41467-024-44824-z 2024

  77. [80]

    NP-SAM: Implementing the Segment Anything Model for Easy Nanoparticle Segmentation in Electron Microscopy Images

    Larsen, R.; et al. NP-SAM: Implementing the Segment Anything Model for Easy Nanoparticle Segmentation in Electron Microscopy Images. ChemRxiv 2023. https://doi.org/10.26434/chemrxiv-2023- k73qz

    doi:10.26434/chemrxiv-2023- 2023

  78. [81]

    Automated Particle Size Analysis of Supported Nanoparticle TEM Images Using a Pre-Trained SAM Model

    Zhong, X.; Liang, G.; Meng, L.; Xi, W.; Gu, L.; Tian, N.; Zhai, Y.; He, Y.; Huang, Y.; Jin, F.; et al. Automated Particle Size Analysis of Supported Nanoparticle TEM Images Using a Pre-Trained SAM Model. Nanomaterials 2025, 15, 1886. https://doi.org/10.3390/nano15241886

    work page doi:10.3390/nano15241886 2025

  79. [82]

    nnU-Net: A Self-Configuring Method for Deep Learning-Based Biomedical Image Segmentation

    Isensee, F.; et al. nnU-Net: A Self-Configuring Method for Deep Learning-Based Biomedical Image Segmentation. Nat. Methods 2021, 18, 203–211. https://doi.org/10.1038/s41592-020-01008-z 48

    doi:10.1038/s41592-020-01008-z 2021

  80. [83]

    Machine Learning in Electron Microscopy Data Analysis

    Yao, L.; Chen, Q. Machine Learning in Electron Microscopy Data Analysis. In: Electron Microscopy Methods and Protocols; Elsevier, 2022. https://doi.org/10.1016/B978-0-323-85796-3.00010-X

    work page doi:10.1016/b978-0-323-85796-3.00010-x 2022

Showing first 80 references.