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


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


Available from: Xian du, Feb 25, 2014
    • "More general approaches to manage images from different sources rely on unsupervised data mining. Successful examples are reported for cell segmentation [14] [17] [4]. More complex structures like those shown in this paper, however, present challenges that rule out most unsupervised approaches. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Supervised learning approaches to image segmentation receive considerable interest due to their power and flexibility. However, the training phase is not painless, often being long and tedious. Accurate image labelling can take several hours of expert operators' valuable time. User interfaces are often specifically designed to assist the user for the task at hand. This is clearly unfeasible for most application domains. We propose a simple segmentation framework based on classification and supervised incremental learning. A statistical model of pixel classes is learnt by incrementally adding new sample image patches to automatically-learned probability functions. Learning is iterated and refined in a number of steps rather than being executed in a one-shot training phase. We show that one-shot training and incremental labelling tend to produce similar statistical models, as the number of iterations grows. Comparable classification results are thus obtained with considerably less human effort.
    No preview · Article · Mar 2015 · Computer Vision and Image Understanding
  • Source
    • "Several studies have been proposed for segmenting fluorescent images [4] [7] [9] [10]. In [1], Du et al. developed and evaluated the performance of unsupervised data mining techniques in cell image segmentation. They compared kmeans clustering, Expectation Maximization (EM), Otsu´s threshold method, and Global Minimization by Active Contour (GMAC). "
    [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.
    Full-text · Conference Paper · Aug 2014
  • Source
    • "To make the validation more accurate and precise, the image segmentation should indicate cells’ membrane, cells’ cytoplasm and/or nuclei and/or other organelles (e.g. the lysosome) efficiently and robustly [7-9]. The error in objects detection ought to be as small as possible and should be given explicitly since it determines errors in features important in the process of diagnosis. "
    [Show abstract] [Hide abstract]
    ABSTRACT: The comparative study of the results of various segmentation methods for the digital images of the follicular lymphoma cancer tissue section is described in this paper. The sensitivity and specificity and some other parameters of the following adaptive threshold methods of segmentation: the Niblack method, the Sauvola method, the White method, the Bernsen method, the Yasuda method and the Palumbo method, are calculated. Methods are applied to three types of images constructed by extraction of the brown colour information from the artificial images synthesized based on counterpart experimentally captured images. This paper presents usefulness of the microscopic image synthesis method in evaluation as well as comparison of the image processing results. The results of thoughtful analysis of broad range of adaptive threshold methods applied to: (1) the blue channel of RGB, (2) the brown colour extracted by deconvolution and (3) the ’brown component’ extracted from RGB allows to select some pairs: method and type of image for which this method is most efficient considering various criteria e.g. accuracy and precision in area detection or accuracy in number of objects detection and so on. The comparison shows that the White, the Bernsen and the Sauvola methods results are better than the results of the rest of the methods for all types of monochromatic images. All three methods segments the immunopositive nuclei with the mean accuracy of 0.9952, 0.9942 and 0.9944 respectively, when treated totally. However the best results are achieved for monochromatic image in which intensity shows brown colour map constructed by colour deconvolution algorithm. The specificity in the cases of the Bernsen and the White methods is 1 and sensitivities are: 0.74 for White and 0.91 for Bernsen methods while the Sauvola method achieves sensitivity value of 0.74 and the specificity value of 0.99. According to Bland-Altman plot the Sauvola method selected objects are segmented without undercutting the area for true positive objects but with extra false positive objects. The Sauvola and the Bernsen methods gives complementary results what will be exploited when the new method of virtual tissue slides segmentation be develop. Virtual Slides The virtual slides for this article can be found here: slide 1: and slide 2:
    Full-text · Article · Mar 2013 · Diagnostic Pathology
Show more