XRF-ROI-Finder: Machine learning to guide region-of-interest scanning for X-ray fluorescence microscopy
The microscopy research at the Bionanoprobe (currently at beamline 9-ID and later 2-ID after APS-U) of Argonne National Laboratory focuses on applying synchrotron X-ray fluorescence (XRF) techniques to obtain trace elemental mappings of cryogenic biological samples to gain insights about their role in critical biological activities. The elemental mappings and the morphological aspects of the biological samples, in this instance, the bacterium Escherichia coli (E. coli), also serve as label-free biological fingerprints to identify differently treated samples via fuzzy clustering. The key limitations of achieving good identification performance is the extraction of cells from raw XRF measurement via binary conversion, definition of features based on domain knowledge, dwell time and proportion of differently treated cells in the measurement.
Funding
We acknowledge support from National Institutes of Health grants GM038784 and P41GM181350 (to T.V.O.). Funding for this project was provided through Laboratory Directed Research and Development (LDRD) research grants by Argonne National Laboratory, owned by the U.S Department of Energy and operated by UChicago Argonne LLC (contract No. DE-AC02-06CH11357). A.T, R.K and Z.L acknowledge the support of Laboratory Directed Research and Development grant PRJ 1008870. Y.L. and S.C. acknowledge the support of ANL Laboratory Directed Research and Development grant PRJ1008073. S.C. acknowledges the support of DOE grant PRJ1009594. The funding for BNP was obtained through an NIH ARRA S10 grant SP0007167.
History
Email Address of Submitting Author
chowdm@rpi.eduORCID of Submitting Author
0000-0002-9759-5295Submitting Author's Institution
Argonne National LaboratorySubmitting Author's Country
- Bangladesh
