(262e) Deep Learning-Based Segmentation of Complex Microparticles in Scanning Electron Microscopy Images

Nanoscale chirality is an actively growing research field spurred by the giant chiroptical activity, enantioselective biological activity, and asymmetric catalytic activity of chiral nanostructures.¹ Compared to chiral molecules, the handedness of chiral nano- and microstructures can be directly established via electron microscopy, which can be utilized for the automatic analysis of chiral nanostructures and prediction of their properties. However, chirality in complex materials may have multiple geometric forms. Its identification from electron microscopy images rather than optical measurements is fundamentally challenging because (1) image features differentiating left- and right-handed particles can be ambiguous, and (2) three-dimensional structure essential for chirality is 'flattened' into two-dimensional projections typical for electron microscopy images. Here, we show that deep learning algorithms can identify twisted bowtie-shaped microparticles² with nearly 100% accuracy and classify them as left- and right-handed with as high as 99% accuracy. Importantly, such accuracy was achieved with as few as 30 original electron microscopy images of bowties. Furthermore, after training on bowtie particles with complex nanostructured features, the model can recognize other chiral shapes with different geometries without re-training for their specific chiral geometry with 93% accuracy, indicating the learning abilities of the employed neural networks. These findings indicate that our deep learning algorithm trained on a practically feasible training set of experimental data enables automated analysis of microscopy data for the accelerated discovery of chiral particles and their complex systems for multiple applications.

Figure. Examples of segmentation of bowties using scanning electron microscopy images. Green color – right-handed particles, violet color – left-handed particles.

References

1) Cho, N.H., Guerrero-Martínez, A., Ma, J., Bals, S., Kotov, N.A., Liz-Marzán, L.M. and Nam, K.T., 2023. Bioinspired chiral inorganic nanomaterials. Nature Reviews Bioengineering, pp.1-19.

2) Kumar, P., Vo, T., Cha, M., Visheratina, A., Kim, J.Y., Xu, W., Schwartz, J., Simon, A., Katz, D., Nicu, V.P. and Marino, E., 2023. Photonically active bowtie nanoassemblies with chirality continuum. Nature, 615(7952), pp.418-424.