Manifold projection image segmentation for nano-XANES imaging
As spectral imaging techniques are becoming more prominent in science, advanced image segmentation algorithms are required to identify appropriate domains in these images. We present a version of image segmentation called manifold projection image segmentation (MPIS) that is generally applicable to...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIP Publishing LLC
2023-12-01
|
| Series: | APL Machine Learning |
| Online Access: | http://dx.doi.org/10.1063/5.0167584 |
| _version_ | 1827391482841006080 |
|---|---|
| author | Samantha Tetef Ajith Pattammattel Yong S. Chu Maria K. Y. Chan Gerald T. Seidler |
| author_facet | Samantha Tetef Ajith Pattammattel Yong S. Chu Maria K. Y. Chan Gerald T. Seidler |
| author_sort | Samantha Tetef |
| collection | DOAJ |
| description | As spectral imaging techniques are becoming more prominent in science, advanced image segmentation algorithms are required to identify appropriate domains in these images. We present a version of image segmentation called manifold projection image segmentation (MPIS) that is generally applicable to a broad range of systems without the need for training because MPIS uses unsupervised machine learning with a few physically motivated hyperparameters. We apply MPIS to nanoscale x-ray absorption near edge structure (XANES) imaging, where XANES spectra are collected with nanometer spatial resolution. We show the superiority of manifold projection over linear transformations, such as the commonly used principal component analysis (PCA). Moreover, MPIS maintains accuracy while reducing computation time and sensitivity to noise compared to the standard nano-XANES imaging analysis procedure. Finally, we demonstrate how multimodal information, such as x-ray fluorescence data and spatial location of pixels, can be incorporated into the MPIS framework. We propose that MPIS is adaptable for any spectral imaging technique, including scanning transmission x-ray microscopy, where the length scale of domains is larger than the resolution of the experiment. |
| first_indexed | 2024-03-08T17:11:37Z |
| format | Article |
| id | doaj.art-34baa60092e045d3bf37303fdabf6dd6 |
| institution | Directory Open Access Journal |
| issn | 2770-9019 |
| language | English |
| last_indexed | 2024-03-08T17:11:37Z |
| publishDate | 2023-12-01 |
| publisher | AIP Publishing LLC |
| record_format | Article |
| series | APL Machine Learning |
| spelling | doaj.art-34baa60092e045d3bf37303fdabf6dd62024-01-03T19:54:29ZengAIP Publishing LLCAPL Machine Learning2770-90192023-12-0114046119046119-710.1063/5.0167584Manifold projection image segmentation for nano-XANES imagingSamantha Tetef0Ajith Pattammattel1Yong S. Chu2Maria K. Y. Chan3Gerald T. Seidler4University of Washington, Seattle, Washington 98195, USANational Synchrotron Light Source II, Brookhaven National Laboratory, Upton, New York 11973, USANational Synchrotron Light Source II, Brookhaven National Laboratory, Upton, New York 11973, USACenter for Nanoscale Materials, Argonne National Laboratory, Lemont, Illinois 60439, USAUniversity of Washington, Seattle, Washington 98195, USAAs spectral imaging techniques are becoming more prominent in science, advanced image segmentation algorithms are required to identify appropriate domains in these images. We present a version of image segmentation called manifold projection image segmentation (MPIS) that is generally applicable to a broad range of systems without the need for training because MPIS uses unsupervised machine learning with a few physically motivated hyperparameters. We apply MPIS to nanoscale x-ray absorption near edge structure (XANES) imaging, where XANES spectra are collected with nanometer spatial resolution. We show the superiority of manifold projection over linear transformations, such as the commonly used principal component analysis (PCA). Moreover, MPIS maintains accuracy while reducing computation time and sensitivity to noise compared to the standard nano-XANES imaging analysis procedure. Finally, we demonstrate how multimodal information, such as x-ray fluorescence data and spatial location of pixels, can be incorporated into the MPIS framework. We propose that MPIS is adaptable for any spectral imaging technique, including scanning transmission x-ray microscopy, where the length scale of domains is larger than the resolution of the experiment.http://dx.doi.org/10.1063/5.0167584 |
| spellingShingle | Samantha Tetef Ajith Pattammattel Yong S. Chu Maria K. Y. Chan Gerald T. Seidler Manifold projection image segmentation for nano-XANES imaging APL Machine Learning |
| title | Manifold projection image segmentation for nano-XANES imaging |
| title_full | Manifold projection image segmentation for nano-XANES imaging |
| title_fullStr | Manifold projection image segmentation for nano-XANES imaging |
| title_full_unstemmed | Manifold projection image segmentation for nano-XANES imaging |
| title_short | Manifold projection image segmentation for nano-XANES imaging |
| title_sort | manifold projection image segmentation for nano xanes imaging |
| url | http://dx.doi.org/10.1063/5.0167584 |
| work_keys_str_mv | AT samanthatetef manifoldprojectionimagesegmentationfornanoxanesimaging AT ajithpattammattel manifoldprojectionimagesegmentationfornanoxanesimaging AT yongschu manifoldprojectionimagesegmentationfornanoxanesimaging AT mariakychan manifoldprojectionimagesegmentationfornanoxanesimaging AT geraldtseidler manifoldprojectionimagesegmentationfornanoxanesimaging |