Estimating Bacterial and Cellular Load in FCFM Imaging
| Autor: | Ahsan R. Akram, Sohan Seth, Kanwaldeep Dhaliwal, Christopher Williams |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2018 |
| Předmět: |
FCFM imaging
Confocal Biology lcsh:Computer applications to medicine. Medical informatics 01 natural sciences supervised learning lcsh:QA75.5-76.95 Human lung lung 010309 optics 03 medical and health sciences 0302 clinical medicine radial basis function network 0103 physical sciences medicine Fluorescence microscope Radiology Nuclear Medicine and imaging lcsh:Photography Electrical and Electronic Engineering bacteria Pixel business.industry logistic regression Supervised learning Pattern recognition cell lcsh:TR1-1050 Computer Graphics and Computer-Aided Design Autofluorescence medicine.anatomical_structure 030228 respiratory system lcsh:R858-859.7 Computer Vision and Pattern Recognition Artificial intelligence lcsh:Electronic computers. Computer science business |
| Zdroj: | Journal of Imaging, Vol 4, Iss 1, p 11 (2018) Seth, S, Akram, A R, Dhaliwal, K & Williams, C K I 2018, ' Estimating Bacterial and Cellular Load in FCFM Imaging ', Journal of Imaging, vol. 4, no. 1 . https://doi.org/10.3390/jimaging4010011 Journal of Imaging; Volume 4; Issue 1; Pages: 11 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|