Article

Segmentation of Fluorescence Microscopy Cell Images Using Unsupervised Mining

Data Mining Research Laboratory, Department of Computer Science, College of Engineering and Science, Louisiana Tech University, Ruston, LA, USA.
The Open Medical Informatics Journal 08/2010; 4(1):41-9. DOI: 10.2174/1874431101004020041
Source: PubMed

ABSTRACT The accurate measurement of cell and nuclei contours are critical for the sensitive and specific detection of changes in normal cells in several medical informatics disciplines. Within microscopy, this task is facilitated using fluorescence cell stains, and segmentation is often the first step in such approaches. Due to the complex nature of cell issues and problems inherent to microscopy, unsupervised mining approaches of clustering can be incorporated in the segmentation of cells. In this study, we have developed and evaluated the performance of multiple unsupervised data mining techniques in cell image segmentation. We adapt four distinctive, yet complementary, methods for unsupervised learning, including those based on k-means clustering, EM, Otsu's threshold, and GMAC. Validation measures are defined, and the performance of the techniques is evaluated both quantitatively and qualitatively using synthetic and recently published real data. Experimental results demonstrate that k-means, Otsu's threshold, and GMAC perform similarly, and have more precise segmentation results than EM. We report that EM has higher recall values and lower precision results from under-segmentation due to its Gaussian model assumption. We also demonstrate that these methods need spatial information to segment complex real cell images with a high degree of efficacy, as expected in many medical informatics applications.

Download full-text

Full-text

Available from: Xian du, Feb 25, 2014
3 Followers
 · 
121 Views
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper describes the first steps for the automation of the serum titration process. In fact, this process requires an Indirect Immunofluorescence (IIF) diagnosis automation. We deal with the initial phase that represents the fluorescence images segmentation. Our approach consists of three principle stages: (1) a color based segmentation which aims at extracting the fluorescent foreground based on k-means clustering, (2) the segmentation of the fluorescent clustered image, and (3) a region-based feature segmentation, intended to remove the fluorescent noisy regions and to locate fluorescent parasites. We evaluated the proposed method on 40 IIF images. Experimental results show that such a method provides reliable and robust automatic segmentation of fluorescent Promastigote parasite.
    Engineering in Medicine and Biology Society (EMBC), 2014 36th Annual International Conference of the IEEE, Chicago, IL, USA; 08/2014
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Interpreting images from fluorescence microscopy is often a time-consuming task with poor reproducibility. Various image processing routines that can help investigators evaluate the images are therefore useful. The critical aspect for a reliable automatic image analysis system is a robust segmentation algorithm that can perform accurate segmentation for different cell types. In this study, several image segmentation methods were therefore compared and evaluated in order to identify the most appropriate segmentation schemes that are usable with little new parameterization and robustly with different types of fluorescence-stained cells for various biological and biomedical tasks. The study investigated, compared, and enhanced four different methods for segmentation of cultured epithelial cells. The maximum-intensity linking (MIL) method, an improved MIL, a watershed method, and an improved watershed method based on morphological reconstruction were used. Three manually annotated datasets consisting of 261, 817, and 1,333 HeLa or L929 cells were used to compare the different algorithms. The comparisons and evaluations showed that the segmentation performance of methods based on the watershed transform was significantly superior to the performance of the MIL method. The results also indicate that using morphological opening by reconstruction can improve the segmentation of cells stained with a marker that exhibits the dotted surface of cells.
    Cytometry Part A 11/2011; 79(11):933-45. DOI:10.1002/cyto.a.21122 · 3.07 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Cardiac hypertrophy is controlled by a complex signal transduction and gene regulatory network, containing multiple layers of crosstalk and feedback. While numerous individual components of this network have been identified, understanding how these elements are coordinated to regulate heart growth remains a challenge. Past approaches to measure cardiac myocyte hypertrophy have been manual and often qualitative, hindering the ability to systematically characterize the network's higher-order control structure and identify therapeutic targets. Here, we develop and validate an automated image analysis approach for objectively quantifying multiple hypertrophic phenotypes from immunofluorescence images. This approach incorporates cardiac myocyte-specific optimizations and provides quantitative measures of myocyte size, elongation, circularity, sarcomeric organization, and cell-cell contact. As a proof-of-concept, we examined the hypertrophic response to α-adrenergic, β-adrenergic, tumor necrosis factor (TNFα), insulin-like growth factor-1 (IGF-1), and fetal bovine serum pathways. While all five hypertrophic pathways increased myocyte size, other hypertrophic metrics were differentially regulated, forming a distinct phenotype signature for each pathway. Sarcomeric organization was uniquely enhanced by α-adrenergic signaling. TNFα and α-adrenergic pathways markedly decreased cell circularity due to increased myocyte protrusion. Surprisingly, adrenergic and IGF-1 pathways differentially regulated myocyte-myocyte contact, potentially forming a feed-forward loop that regulates hypertrophy. Automated image analysis unlocks a range of new quantitative phenotypic data, aiding dissection of the complex hypertrophic signaling network and enabling myocyte-based high-content drug screening.
    Journal of Molecular and Cellular Cardiology 12/2011; 52(5):923-30. DOI:10.1016/j.yjmcc.2011.11.009 · 5.22 Impact Factor