Correlative Multimodal Chemical Imaging via Machine Learning

This technology introduces an advanced machine learning approach for enhancing chemical imaging by correlating data from two mass spectrometry imaging (MSI) techniques. One technique offers low spatial resolution with intact molecular spectra, and the other provides high-resolution imaging with fragmented molecular data. The innovation lies in combining these two data types to predict molecular MSI spectra with unprecedented submicron spatial resolution, significantly improving the accuracy and detail of chemical imaging.

Description

The core of this invention is a machine learning model trained to correlate and transform spectral image data from two distinct MSI techniques, effectively compensating for their respective limitations. The process involves dimensionality reduction, transformation into abundance maps, and spatial correlation of these maps to generate high-resolution MSI spectra. This system allows for the detailed visualization of chemical compositions at a submicron scale by leveraging the complementary strengths of both imaging methods. Such a technique is pivotal for analyzing complex samples where high spatial resolution and intact molecular information are critical for understanding the sample's chemical makeup.

Benefits

• Provides high-resolution chemical imaging capable of distinguishing between closely spaced molecular compounds
• Enhances the understanding of chemical compositions in complex samples without compromising molecular integrity

Applications and Industries

• Pharmaceutical research for drug distribution studies within biological tissues
• Material science for analyzing nanomaterials and polymer blends
• Environmental science for detailed mapping of pollutant distributions

Related ORNL Technologies

• Machine Learning on Multimodal Chemical and Whole Slide Imaging Data for Predicting Cancer Labels Directly from Tissue Images
• Pan-Sharpening for Microscopy
• Science-Driven Automated Experiments
• Hypothesis Learning in Automated Experiments
• Human-in-the-Loop Machine Learning for Automated Experiments

Contact

To learn more about this technology, email partnerships@ornl.gov or call 865-574-1051.