Finding cells, finding molecules, finding patterns

International Journal of Signal and Imaging Systems Engineering 01/2008; DOI: 10.1504/IJSISE.2008.017768
Source: OAI

ABSTRACT Many modern molecular labeling techniques result in bright point signals. Signals from molecules that are detected directly inside a cell can be captured by fluorescence microscopy. Signals representing different types of molecules may be randomly distributed in the cells or show systematic patterns indicating that the corresponding molecules have specific, non-random localizations and functions in the cell. Assessing this information requires high speed robust image segmentation followed by signal detection, and finally pattern analysis. We present and discuss this type of methods and show an example of how the distribution of different variants of mitochondrial DNA can be analyzed.
Accepted for publication in International Journal of Signal and Imaging Systems Engineering (IJSISE), 2006 (

  • [Show abstract] [Hide abstract]
    ABSTRACT: Fine-Needle Aspiration Biopsy (FNAB) is a non-surgical method of determining benign or malignant state of the thyroid nodule. To achieve high accuracy in the determination of benign or malignant state, the screening process should be carried out with an acceptable sensitivity. It is also necessary to develop efficient automated methods to perform the segmentation of cancer cells from the FNAB microscopic images before classification. In this paper, we have used an image segmentation method to perform cell image segmentation in Fine Needle Aspiration Biopsy Cytological Images of thyroid nodules under noise conditions and varying staining conditions. The segmentation method combines the image processing techniques thresholding, distance transform, watershed transform and Gaussian low pass filter. The watershed transform separates the overlapped cell images and Gaussian low pass filter prevents over segmentation by removing the noise objects in the image. The segmentation method is successfully tested for Papillary carcinoma and Medullary carcinoma Cytological Images of thyroid nodules, showing promising results, encouraging future research work.
  • [Show abstract] [Hide abstract]
    ABSTRACT: The problem of automatic extraction of cell nuclei in cytological images for automated diagnostics of hematological diseases is considered. A combined two-level segmentation method based on an active contour model is presented. The method employs different strategies to form the active contour model at coarse and fine approximation steps. The capture range of the active contour is extended by employing a wave propagation model. Unsupervised initialization of the active contour involves binarization of the a component of the input image in the CIE Lab color space. The efficiency of the developed method is demonstrated by a computational experiment.
    Pattern Recognition and Image Analysis 01/2008; 18(1):177-192. DOI:10.1134/S1054661808010215
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Image segmentation is an important research area in image analysis and its applications to medical and bio- logical imaging. In particular, eec- tive segmentation methods play an essential role in the analysis, clas- sification, and quantification of bio- images for prognosis and preventive treatment. Dierent segmentation methods based on dierent crite- ria of optimality often give dier- ent results. This paper introduces a new strategy for modeling image spatial information in the setting of the fuzzy c-means algorithm for seg- menting bio-images that are inher- ently fuzzy. The experimental re- sults have shown the superior perfor- mance of the new method over some popular models for the segmentation of cell puncta.

Full-text (2 Sources)

Available from
Jun 4, 2014