Artificial Intelligence for MSI Data Analysis

A combination of ion images and AI tools allows us to understand the data better.

Mass spectrometry imaging (MSI) generates hundreds of molecular images in a single experiment. However, interpretation of the vast data is challenging. Machine learning and deep learning methods have been developed to automatically identify distinct cell types or co-localized molecules from tissue samples using only MSI data. These tools allow us to quantify molecules and analyze biochemical pathways.

Publications

Hu, H., Yin, R., Brown, H. M., & Laskin, J. (2021). Spatial Segmentation of Mass Spectrometry Imaging Data by Combining Multivariate Clustering and Univariate Thresholding. Analytical Chemistry, 93 (7), 3477-3485. https://doi.org/10.1021/acs.analchem.0c04798

Hu, H., Bindu, J. P., and Laskin, J.. Self-supervised clustering of mass spectrometry imaging data using contrastive learning. Chemical Science 13, 90–98 (2022). https//doi.org/10.1039/D1SC04077D