Deep Learning-Enabled Transformation of Scanning Superlens Microscopy Images into Scanning Electron Microscopy-like Large Depth-of-Field Images

Abstract Scanning electron microscopy (SEM) enables nanoscale imaging but requires vacuum environments and coating samples with conductive films. We present a deep learning approach to transform optical super-resolution (OSR) microscopy images into SEM-like images without these limitations. Our custom scanning superlens microscopy system acquires OSR images down to ~80 nm without coatings or vacuum. A generative adversarial network (GAN) model is trained on paired OSR and SEM images to learn the mapping between domains. The model is then used to transform previously unseen OSR test images. Quantitative analysis shows the reconstructed images achieve a mean peak signal-to-noise ratio 0.74 dB higher than the input OSR images. Qualitative assessment further demonstrates the model's ability to generate results with high structural detail. This technique overcomes key SEM constraints while preserving nanoscale resolution, promising wide applicability for challenges such as chip-level defect detection and biological sample analysis where coating or vacuum requirements pose obstacles.