CoChat
Sign Up
Cited by 93

The DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.

Deep learning for automated size and shape analysis of nanoparticles in scanning electron microscopy

Bals, Jonas, Epple, Matthias·2023·RSC Advances
DOI 10.1039/d2ra07812kPMC PMC9850277
Open this paper in CoChat — free account

Abstract

Particles depicted in scanning electron micrographs are automatically identified and classified according to size and shape with a deep-learning algorithm. The procedure works for both SE images and STEM images.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1039/d2ra07812k

Cites

4 of 4 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1 Representative SEM image from the training dataset for segmentation containing ZnO nanorods (2048 × 1886 pixels; SE mode). Orange boxes show typical cut-out patches used for training.
Fig. 1 Representative SEM image from the training dataset for segmentation containing ZnO nanorods (2048 × 1886 pixels; SE mode). Orange boxes show typical cut-out patches used for training.CC BY-NC · PubMed Central
Fig. 2 SE image depicting SiO2 microspheres (A1) with corresponding segmentation map (B1), and distance-based weight loss map calculated by eqn (1) (C1). STEM image of Au nanoparticles (A2) with segmentation map (B2) and intensity-based weight loss map (C2). Each background pixel (black) of the segmentation map was assigned with an individual weight loss depending on the distance to the edges of the two nearest particles. These weights varied between 1 and 11 for SE images and 1 and 13 for STEM images. The general weight of foreground pixels (white) was 1.
Fig. 2 SE image depicting SiO2 microspheres (A1) with corresponding segmentation map (B1), and distance-based weight loss map calculated by eqn (1) (C1). STEM image of Au nanoparticles (A2) with segmentation map (B2) and intensity-based weight loss map (C2). Each background pixel (black) of the segmentation map was assigned with an individual weight loss depending on the distance to the edges of the two nearest particles. These weights varied between 1 and 11 for SE images and 1 and 13 for STEM images. The general weight of foreground pixels (white) was 1.CC BY-NC · PubMed Central
Fig. 3 The input SEM image (SE mode) is segmented by a UNet++ model. The dimensions of all foreground objects (white coherent areas) were defined by their enclosing bounding box (red boxes) in the segmentation map. The cut-out areas in the SEM image were slightly larger than the bounding boxes to provide additional background information around each object. The image patches were resized until each side of the patch was 224 pixels long because the classification network used only square images. The additional pixels were filled with zero-pixel values (zero-padding; black). The classification model took these square images and assigned each particle to a class (upper row: a circle). If the image contained a particle which was partially covered, this particle was assigned to the class “covered” and excluded from further shape classification (bottom row).
Fig. 3 The input SEM image (SE mode) is segmented by a UNet++ model. The dimensions of all foreground objects (white coherent areas) were defined by their enclosing bounding box (red boxes) in the segmentation map. The cut-out areas in the SEM image were slightly larger than the bounding boxes to provide additional background information around each object. The image patches were resized until each side of the patch was 224 pixels long because the classification network used only square images. The additional pixels were filled with zero-pixel values (zero-padding; black). The classification model took these square images and assigned each particle to a class (upper row: a circle). If the image contained a particle which was partially covered, this particle was assigned to the class “covered” and excluded from further shape classification (bottom row).CC BY-NC · PubMed Central
Fig. 4 Confusion matrix for the shape classification of nanoparticles. Left: results for STEM images; right: results for SE images.
Fig. 4 Confusion matrix for the shape classification of nanoparticles. Left: results for STEM images; right: results for SE images.CC BY-NC · PubMed Central
Fig. 5 Representative classification of particles of different materials recorded in SE and STEM modes. The images are illustrative cut-outs from larger images subjected to segmentation and classification. They show nanoparticles of (A): SiO2 (SE), (B): Au (STEM), (C): Ag (SE), and (D): ZnO (SE). The full analysis involved the segmentation, followed by classification. The coloured areas are foreground areas (i.e. particles) identified by the segmentation and then assigned to a shape class.
Fig. 5 Representative classification of particles of different materials recorded in SE and STEM modes. The images are illustrative cut-outs from larger images subjected to segmentation and classification. They show nanoparticles of (A): SiO2 (SE), (B): Au (STEM), (C): Ag (SE), and (D): ZnO (SE). The full analysis involved the segmentation, followed by classification. The coloured areas are foreground areas (i.e. particles) identified by the segmentation and then assigned to a shape class.CC BY-NC · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 4 references

Research works printed but not linked: 32

  1. Fissan, 2014, Anal. Methods, 6, 7324, 10.1039/C4AY01203H · DOI
  2. Modena, 2019, Adv. Mater., 31, 1901556, 10.1002/adma.201901556 · DOI
  3. Bals, 2022, Materialwiss. Werkstofftech., 53, 270, 10.1002/mawe.202100285 · DOI
  4. Modarres, 2017, Sci. Rep., 7, 13282, 10.1038/s41598-017-13565-z · DOI
  5. Holm, 2020, Metall. Mater. Trans. A, 51, 5985, 10.1007/s11661-020-06008-4 · DOI
  6. Schmidt, 2019, npj Comput. Mater., 5, 83, 10.1038/s41524-019-0221-0 · DOI
  7. Timoshenko, 2018, Nano Lett., 19, 520, 10.1021/acs.nanolett.8b04461 · DOI
  8. Oktay, 2019, Micron, 120, 113, 10.1016/j.micron.2019.02.009 · DOI
  9. Ede, 2020, Sci. Rep., 10, 8332, 10.1038/s41598-020-65261-0 · DOI
  10. Ilett, 2020, J. Microsc., 279, 177, 10.1111/jmi.12853 · DOI
  11. Kim, 2020, Nanoscale, 12, 19461, 10.1039/D0NR04140H · DOI
  12. Lee, 2020, ACS Nano, 14, 17125, 10.1021/acsnano.0c06809 · DOI
  13. A.Krizhevsky , I.Sutskever and G. E.Hinton , Presented in part at the Proceedings of the 25th International Conference on Neural Information Processing Systems – Volume 1 , Lake Tahoe , Nevada , 2012
  14. K.He , X.Zhang , S.Ren and J.Sun , Presented in part at the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 27–30 June 2016 , 2016
  15. Jacobs, 2022, Comput. Mater. Sci., 211, 111527, 10.1016/j.commatsci.2022.111527 · DOI
  16. Treder, 2022, Microscopy, 71, i100, 10.1093/jmicro/dfab043 · DOI
  17. I.Goodfellow , Y.Bengio and A.Courville , Deep Learning , MIT Press , 2016
  18. Z.Zhou , M. M.Rahman Siddiquee , N.Tajbakhsh and J.Liang , in Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support , Springer , 2018 , pp. 3–11 , 10.1007/978-3-030-00889-5_1 · DOI
  19. Ruehle, 2021, Sci. Rep., 11, 4942, 10.1038/s41598-021-84287-6 · DOI
  20. Zhou, 2020, IEEE Trans. Med. Imag., 39, 1856, 10.1109/TMI.2019.2959609 · DOI
  21. G.Huang , Z.Liu , L.van der Maaten and K. Q.Weinberger , Presented in part at the 2017 IEEE Conference on Computer Vision and Pattern Recognition ( CVPR ), 2017 , pp. 21–26
  22. Unnikrishnan, 2007, IEEE Trans. Pattern Anal. Mach. Intell., 29, 929, 10.1109/TPAMI.2007.1046 · DOI
  23. Saaim, 2022, Ultramicroscopy, 233, 113437, 10.1016/j.ultramic.2021.113437 · DOI
  24. D. P.Kingma and J.Ba , arXiv , 2015 , preprint, arXiv:1412.6980, 10.48550/arXiv.1412.6980 · DOI · Paper page
  25. M.Abadi , P.Barham , J.Chen , Z.Chen , A.Davis , J.Dean , M.Devin , S.Ghemawat , G.Irving , M.Isard , M.Kudlur , J.Levenberg , R.Monga , S.Moore , D. G.Murray , B.Steiner , P.Tucker , V.Vasudevan , P.Warden , M.Wicke , Y.Yu and X.Zheng , Presented in Part at the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16) , Savannah, GA, USA , 2016
  26. Aldrich, 1997, Stat. Sci., 12, 162, 10.1214/ss/1030037906 · DOI
  27. K.He , X.Zhang , S.Ren and J.Sun , arXiv , 2015 , preprint, arXiv:1502.01852, 10.48550/arXiv.1502.01852 · DOI
  28. M. D.Zeiler and R.Fergus , Presented in Part at the Computer Vision – ECCV 2014 , Cham , 2014
  29. Munoz-Marmol, 2015, Nanomedicine, 11, 457, 10.1016/j.nano.2014.07.006 · DOI
  30. Hughes, 2015, PeerJ, 2, e671v671
  31. Baiyasi, 2020, J. Phys. Chem. A, 124, 5262, 10.1021/acs.jpca.0c03190 · DOI
  32. De Siqueira, 2014, Microsc. Res. Tech., 77, 71, 10.1002/jemt.22314 · DOI

Cited by

Sorted by citations

Metadata

Authors
Bals, J., & Epple, M.
Venue
RSC Advances
Publisher
Royal Society of Chemistry (RSC)
Published
2023
Volume
13
Issue
5
Pages
2795-2802
ISSN
2046-2069
DOI
10.1039/d2ra07812k
PMC
PMC9850277
Cited by
93
References
4
Language
en
Licence
creativecommons.org/licenses/by-nc/3.0/ (vor, 18 d)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review