Transmission electron microscopy (TEM) image datasets of peptide / protein nanowire morphologies

TEM image dataset containing four nanowire morphologies of bio-derived protein nanowires and synthetic peptide nanowires.

The peptide / protein nanowires used in this study were synthesized and imaged by Brian Montz in Prof. Todd Emrick's research group at the Department of Polymer Science and Engineering Department, University of Massachusetts Amherst. 

We acknowledge financial support from the U.S. National Science Foundation, Grant NSF DMREF #1921839 and DMREF #1921871.

Nanowires were classified into either of the four morphologies: bundle, singular, dispersed or network. Each morphology contains 100 images (jpg files).

For the dispersed and network morphologies, because these two morphologies are harder to visually distinguish, we have created manual segmentation labels of the nanowires (included in these two morphology folders as png files). Percolation analysis was done on these manually segmented nanowires to provide quantitative metric on whether the nanowires form a network in the image. 

seg_mask_5_resolutions.zip contains ground truth 2D binary encoding of segmented nanowires at 5 resolutions.

encoders_trained_with_optimized_hyperparameter.zip contains 4 sets of encoders trained with either SimCLR or Barlow-Twins self-supervised methods on either generic TEM images, or generic everyday photographic images (each with 5 replicates with different random seed) with optimized hyperparameters.

The official github page of the implementation of the machine learning models is self-supervised_learning_microscopy_images.

If you use the dataset or the codes in the repository linked above, please cite the following manuscript:

@misc{lu2022selfsupervised,
      title={Self-supervised machine learning model for analysis of nanowire morphologies from transmission electron microscopy images}, 
      author={Shizhao Lu and Brian Montz and Todd Emrick and Arthi Jayaraman},
      year={2022},
      eprint={2203.13875},
      archivePrefix={arXiv},
      primaryClass={cond-mat.mtrl-sci}
}