Fusing ToF-SIMS Images for Spatial-Spectral Resolution Enhancement using a Convolutional Neural Network

Hyperspectral data sets generated by time-of-flight secondary ion mass spectrometry (ToF-SIMS) contain valuable spatial-spectral information characterizing the distribution of atomic and molecular species across a sample surface. Modern ToF-SIMS instruments have high spatial resolution (in the order of tens of nanometers) relative to most other mass spectrometry imaging (MSI) techniques. However, there is generally a trade-off between spatial and mass resolution when using different instrument modes. In this study, a convolutional neural network (CNN) fusion method is used to fuse correlated high spatial and high mass resolution ToF-SIMS hyperspectral data sets. This process generates resolution-enhanced data, which exhibit both high spatial and mass resolution. The CNN fusion method is applied to ToF-SIMS images of a simple, well-characterized gold mesh sample and a significantly more complex biological (tumor) tissue section. The method is compared to another linear fusion method used in the broader MSI community and a substantial improvement is found. This comparison focuses on both visual quality observations as well as statistical similarity measures. This work demonstrates the utility of the CNN fusion method for ToF-SIMS data, enabling investigation of the atomic and molecular characteristics of surfaces at high spatial and mass spectral resolution.

Automated summary

This study applies a convolutional neural network (CNN) fusion method to fuse ToF-SIMS hyperspectral data sets, achieving resolution-enhanced data with high spatial and mass resolution. The method is applied to ToF-SIMS images of a gold mesh sample and a tumor tissue section, and the improvement is compared to another linear fusion method used in the broader MSI community.