Estimating Bacterial and Cellular Load in FCFM Imaging
We address the task of estimating bacterial and cellular load in the human distal lung with fibered confocal fluorescence microscopy (FCFM). In pulmonary FCFM some cells can display autofluorescence, and they appear as disc like objects in the FCFM images, whereas bacteria, although not autofluoresc...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-01-01
|
| Series: | Journal of Imaging |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2313-433X/4/1/11 |
| _version_ | 1819179929526337536 |
|---|---|
| author | Sohan Seth Ahsan R. Akram Kevin Dhaliwal Christopher K. I. Williams |
| author_facet | Sohan Seth Ahsan R. Akram Kevin Dhaliwal Christopher K. I. Williams |
| author_sort | Sohan Seth |
| collection | DOAJ |
| description | We address the task of estimating bacterial and cellular load in the human distal lung with fibered confocal fluorescence microscopy (FCFM). In pulmonary FCFM some cells can display autofluorescence, and they appear as disc like objects in the FCFM images, whereas bacteria, although not autofluorescent, appear as bright blinking dots when exposed to a targeted smartprobe. Estimating bacterial and cellular load becomes a challenging task due to the presence of background from autofluorescent human lung tissues, i.e., elastin, and imaging artifacts from motion etc. We create a database of annotated images for both these tasks where bacteria and cells were annotated, and use these databases for supervised learning. We extract image patches around each pixel as features, and train a classifier to predict if a bacterium or cell is present at that pixel. We apply our approach on two datasets for detecting bacteria and cells respectively. For the bacteria dataset, we show that the estimated bacterial load increases after introducing the targeted smartprobe in the presence of bacteria. For the cell dataset, we show that the estimated cellular load agrees with a clinician’s assessment. |
| first_indexed | 2024-12-22T22:06:15Z |
| format | Article |
| id | doaj.art-45490b32b3bb46ac971c0d80ac25b1eb |
| institution | Directory Open Access Journal |
| issn | 2313-433X |
| language | English |
| last_indexed | 2024-12-22T22:06:15Z |
| publishDate | 2018-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Imaging |
| spelling | doaj.art-45490b32b3bb46ac971c0d80ac25b1eb2022-12-21T18:10:58ZengMDPI AGJournal of Imaging2313-433X2018-01-01411110.3390/jimaging4010011jimaging4010011Estimating Bacterial and Cellular Load in FCFM ImagingSohan Seth0Ahsan R. Akram1Kevin Dhaliwal2Christopher K. I. Williams3School of Informatics, University of Edinburgh, Edinburgh EH8 9AB, UKPulmonary Molecular Imaging Group, MRC Center for Inflammation Research, Queens Medical Research Institute, University of Edinburgh, Edinburgh EH14 4TJ, UKPulmonary Molecular Imaging Group, MRC Center for Inflammation Research, Queens Medical Research Institute, University of Edinburgh, Edinburgh EH14 4TJ, UKSchool of Informatics, University of Edinburgh, Edinburgh EH8 9AB, UKWe address the task of estimating bacterial and cellular load in the human distal lung with fibered confocal fluorescence microscopy (FCFM). In pulmonary FCFM some cells can display autofluorescence, and they appear as disc like objects in the FCFM images, whereas bacteria, although not autofluorescent, appear as bright blinking dots when exposed to a targeted smartprobe. Estimating bacterial and cellular load becomes a challenging task due to the presence of background from autofluorescent human lung tissues, i.e., elastin, and imaging artifacts from motion etc. We create a database of annotated images for both these tasks where bacteria and cells were annotated, and use these databases for supervised learning. We extract image patches around each pixel as features, and train a classifier to predict if a bacterium or cell is present at that pixel. We apply our approach on two datasets for detecting bacteria and cells respectively. For the bacteria dataset, we show that the estimated bacterial load increases after introducing the targeted smartprobe in the presence of bacteria. For the cell dataset, we show that the estimated cellular load agrees with a clinician’s assessment.http://www.mdpi.com/2313-433X/4/1/11FCFM imaginglungbacteriacellsupervised learninglogistic regressionradial basis function network |
| spellingShingle | Sohan Seth Ahsan R. Akram Kevin Dhaliwal Christopher K. I. Williams Estimating Bacterial and Cellular Load in FCFM Imaging Journal of Imaging FCFM imaging lung bacteria cell supervised learning logistic regression radial basis function network |
| title | Estimating Bacterial and Cellular Load in FCFM Imaging |
| title_full | Estimating Bacterial and Cellular Load in FCFM Imaging |
| title_fullStr | Estimating Bacterial and Cellular Load in FCFM Imaging |
| title_full_unstemmed | Estimating Bacterial and Cellular Load in FCFM Imaging |
| title_short | Estimating Bacterial and Cellular Load in FCFM Imaging |
| title_sort | estimating bacterial and cellular load in fcfm imaging |
| topic | FCFM imaging lung bacteria cell supervised learning logistic regression radial basis function network |
| url | http://www.mdpi.com/2313-433X/4/1/11 |
| work_keys_str_mv | AT sohanseth estimatingbacterialandcellularloadinfcfmimaging AT ahsanrakram estimatingbacterialandcellularloadinfcfmimaging AT kevindhaliwal estimatingbacterialandcellularloadinfcfmimaging AT christopherkiwilliams estimatingbacterialandcellularloadinfcfmimaging |