Unsupervised cell identification on multidimensional X-ray fluorescence datasets
A novel approach to locate, identify and refine positions and whole areas of cell structures based on elemental contents measured by X-ray fluorescence microscopy is introduced. It is shown that, by initializing with only a handful of prototypical cell regions, this approach can obtain consistent id...
| Veröffentlicht in: | Journal of synchrotron radiation. - 1994. - 21(2014), Pt 3 vom: 01. Mai, Seite 568-79 |
|---|---|
| 1. Verfasser: | |
| Weitere Verfasser: | , , , , |
| Format: | Online-Aufsatz |
| Sprache: | English |
| Veröffentlicht: |
2014
|
| Zugriff auf das übergeordnete Werk: | Journal of synchrotron radiation |
| Schlagworte: | Journal Article Research Support, U.S. Gov't, Non-P.H.S. X-ray fluorescence microscopy (XFM) cell identification modeling overlapping cells trace element distributions unsupervised object recognition |
| Zusammenfassung: | A novel approach to locate, identify and refine positions and whole areas of cell structures based on elemental contents measured by X-ray fluorescence microscopy is introduced. It is shown that, by initializing with only a handful of prototypical cell regions, this approach can obtain consistent identification of whole cells, even when cells are overlapping, without training by explicit annotation. It is robust both to different measurements on the same sample and to different initializations. This effort provides a versatile framework to identify targeted cellular structures from datasets too complex for manual analysis, like most X-ray fluorescence microscopy data. Possible future extensions are also discussed |
|---|---|
| Beschreibung: | Date Completed 30.03.2015 Date Revised 05.12.2017 published: Print-Electronic Citation Status PubMed-not-MEDLINE |
| ISSN: | 1600-5775 |
| DOI: | 10.1107/S1600577514001416 |