Segmentation Of Cell Nuclei Research Articles

Nuclei Segmentation Using Marker-Controlled Watershed, Tracking Using Mean-Shift, and Kalman Filter in Time-Lapse Microscopy

It is important to observe and study cancer cells' cycle progression in order to better understand drug effects on cancer cells. Time-lapse microscopy imaging serves as an important method to measure the cycle progression of individual cells in a large population. Since manual analysis is unreasonably time consuming for the large volumes of time-lapse image data, automated image analysis is proposed. Existing approaches dealing with time-lapse image data are rather limited and often give inaccurate analysis results, especially in segmenting and tracking individual cells in a cell population. In this paper, we present a new approach to segment and track cell nuclei in time-lapse fluorescence image sequence. First, we propose a novel marker-controlled watershed based on mathematical morphology, which can effectively segment clustered cells with less oversegmentation. To further segment undersegmented cells or to merge oversegmented cells, context information among neighboring frames is employed, which is proved to be an effective strategy. Then, we design a tracking method based on modified mean shift algorithm, in which several kernels with adaptive scale, shape, and direction are designed. Finally, we combine mean-shift and Kalman filter to achieve a more robust cell nuclei tracking method than existing ones. Experimental results show that our method can obtain 98.8% segmentation accuracy, 97.4% cell division tracking accuracy, and 97.6% cell tracking accuracy

Automated Segmentation, Classification, and Tracking of Cancer Cell Nuclei in Time-Lapse Microscopy

Quantitative measurement of cell cycle progression in individual cells over time is important in understanding drug treatment effects on cancer cells. Recent advances in time-lapse fluorescence microscopy imaging have provided an important tool to study the cell cycle process under different conditions of perturbation. However, existing computational imaging methods are rather limited in analyzing and tracking such time-lapse datasets, and manual analysis is unreasonably time-consuming and subject to observer variances. This paper presents an automated system that integrates a series of advanced analysis methods to fill this gap. The cellular image analysis methods can be used to segment, classify, and track individual cells in a living cell population over a few days. Experimental results show that the proposed method is efficient and effective in cell tracking and phase identification.

Cell Nucleus Segmentation Based on Fuzzy Growing Snake

Cell Nucleus Segmentation Based on Fuzzy Growing Snake

Automated evaluation of her-2/neu status in breast tissue from fluorescent in situ hybridization images

The evaluation of fluorescent in situ hybridization (FISH) images is one of the most widely used methods to determine Her-2/neu status of breast samples, a valuable prognostic indicator. Conventional evaluation is a difficult task since it involves manual counting of dots in multiple images. In this paper, we present a multistage algorithm for the automated classification of FISH images from breast carcinomas. The algorithm focuses not only on the detection of FISH dots per image, but also on combining results from multiple images taken from a slice for overall case classification. The algorithm includes mainly two stages for nuclei and dot detection respectively. The dot segmentation consists of a top-hat filtering stage followed by template matching to separate real signals from noise. Nuclei segmentation includes a nonlinearity correction step, global thresholding to identify candidate regions, and a geometric rule to distinguish between holes within a nucleus and holes between nuclei. Finally, the marked watershed transform is used to segment cell nuclei with markers detected as regional maxima of the distance transform. Combining the two stages allows the measurement of FISH signals ratio per cell nucleus and the collective classification of cases as positive or negative. The system was evaluated with receiver operating characteristic analysis and the results were encouraging for the further development of this method.

Nuclear morphometry of neoplastic cells as a method for diagnosis of histiocytoma, mastocytoma and transmissible venereal tumor in dogs

Image analysis has been used in medicine and veterinary science as an increasingly important auxiliary tool for histopathology evaluation, because of its potential for decreasing the intrinsic subjectivity of the human visual analysis. However, the geometrical features currently used are often inefficient, not always leading to correct diagnosis. The present work has as its main objective to suggest several approaches to geometric and texture characterization of the cell nuclei, characterized by low computational cost, rapid analysis and sound biological interpretation and good agreement with the visual analysis by expert pathologists. We consider digital images of histological slides obtained from histiocytoma, mastocytoma and transmissible venereal tumors in dogs. Segmented cell nuclei of these tumors were evaluated morphometrically considering the features normally used in medicine together with novel features suggested in the present work, applied in order to characterize the distribution and morphology of the nucleoli and heterochromatin inside the nuclei. Statistical characterization of the obtained results was performed through variance and discriminant analysis, leading to the identification of the most important features. The approach proposed in this article has been verified to be an effective auxiliary tool for differential diagnosis of histiocytoma, mastocytoma and TVT in dogs. Its low computational cost allows fast morphometric evaluation, paving the way for real-time tumor diagnosis.

Combining intensity, edge and shape information for 2D and 3D segmentation of cell nuclei in tissue sections.

We present a region-based segmentation method in which seeds representing both object and background pixels are created by combining morphological filtering of both the original image and the gradient magnitude of the image. The seeds are then used as starting points for watershed segmentation of the gradient magnitude image. The fully automatic seeding is done in a generous fashion, so that at least one seed will be set in each foreground object. If more than one seed is placed in a single object, the watershed segmentation will lead to an initial over-segmentation, i.e. a boundary is created where there is no strong edge. Thus, the result of the initial segmentation is further refined by merging based on the gradient magnitude along the boundary separating neighbouring objects. This step also makes it easy to remove objects with poor contrast. As a final step, clusters of nuclei are separated, based on the shape of the cluster. The number of input parameters to the full segmentation procedure is only five. These parameters can be set manually using a test image and thereafter be used on a large number of images created under similar imaging conditions. This automated system was verified by comparison with manual counts from the same image fields. About 90% correct segmentation was achieved for two- as well as three-dimensional images.

Robust automatic coregistration, segmentation, and classification of cell nuclei in multimodal cytopathological microscopic images

The paper describes the key component of the Multimodal Cell Analysis approach, a novel cytologic evaluation method for early cancer detection. The approach is based on repeated staining of a cell smear. The correlation of features and data extracted from the different stains, and related to relocated individual cells, may yield a dramatic increase of diagnostic reliability. In order to utilise the technique, fully automatic, adaptive image preprocessing techniques need to be applied, which are described in this article: coregistration of multimodal images, segmentation, and classification of cell nuclei. The presented feasibility study shows both efficiency and robustness of all steps being high regarding medical image material, and it strongly supports clinical application.

A hybrid 3D watershed algorithm incorporating gradient cues and object models for automatic segmentation of nuclei in confocal image stacks.

Automated segmentation of fluorescently-labeled cell nuclei in 3D confocal microscope images is essential to many studies involving morphological and functional analysis. A common source of segmentation error is tight clustering of nuclei. There is a compelling need to minimize these errors for constructing highly automated scoring systems. A combination of two approaches is presented. First, an improved distance transform combining intensity gradients and geometric distance is used for the watershed step. Second, an explicit mathematical model for the anatomic characteristics of cell nuclei such as size and shape measures is incorporated. This model is constructed automatically from the data. Deliberate initial over-segmentation of the image data is performed, followed by statistical model-based merging. A confidence score is computed for each detected nucleus, measuring how well the nucleus fits the model. This is used in combination with the intensity gradient to control the merge decisions. Experimental validation on a set of rodent brain cell images showed 97% concordance with the human observer and significant improvement over prior methods. Combining a gradient-weighted distance transform with a richer morphometric model significantly improves the accuracy of automated segmentation and FISH analysis.

Segmentation of confocal microscope images of cell nuclei in thick tissue sections.

Segmentation of intact cell nuclei from three-dimensional (3D) images of thick tissue sections is an important basic capability necessary for many biological research studies. However, segmentation is often difficult because of the tight clustering of nuclei in many specimen types. We present a 3D segmentation approach that combines the recognition capabilities of the human visual system with the efficiency of automatic image analysis algorithms. The approach first uses automatic algorithms to separate the 3D image into regions of fluorescence-stained nuclei and unstained background. This includes a novel step, based on the Hough transform and an automatic focusing algorithm to estimate the size of nuclei. Then, using an interactive display, each nuclear region is shown to the analyst, who classifies it as either an individual nucleus, a cluster of multiple nuclei, partial nucleus or debris. Next, automatic image analysis based on morphological reconstruction and the watershed algorithm divides clusters into smaller objects, which are reclassified by the analyst. Once no more clusters remain, the analyst indicates which partial nuclei should be joined to form complete nuclei. The approach was assessed by calculating the fraction of correctly segmented nuclei for a variety of tissue types: Caenorhabditis elegans embryos (839 correct out of a total of 848), normal human skin (343/362), benign human breast tissue (492/525), a human breast cancer cell line grown as a xenograft in mice (425/479) and invasive human breast carcinoma (260/335). Furthermore, due to the analyst's involvement in the segmentation process, it is always known which nuclei in a population are correctly segmented and which not, assuming that the analyst's visual judgement is correct.

Unsupervised cell nucleus segmentation with active contours

The task of segmenting cell nuclei from cytoplasm in conventional Papanicolaou (Pap) stained cervical cell images is a classical image analysis problem which may prove to be crucial to the development of successful systems which automate the analysis of Pap smears for detection of cancer of the cervix. Although simple thresholding techniques will extract the nucleus in some cases, accurate unsupervised segmentation of very large image databases is elusive. Conventional active contour models as introduced by Kass, Witkin and Terzopoulos (1988) offer a number of advantages in this application, but suffer from the well-known drawbacks of initialisation and minimisation. Here we show that a Viterbi search-based dual active contour algorithm is able to overcome many of these problems and achieve over 99% accurate segmentation on a database of 20 130 Pap stained cell images.

Efficient, interactive, and three-dimensional segmentation of cell nuclei in thick tissue sections.

Segmentation of intact cell nuclei in three-dimensional (3D) images of thick tissue sections is an important basic capability necessary for many biological research studies. Because automatic algorithms do not correctly segment all nuclei in tissue sections, interactive algorithms may be preferable for some applications. Existing interactive segmentation algorithms require the analyst to draw a border around the nucleus under consideration in all successive two-dimensional (2D) planes of the 3D image. The present paper describes an algorithm with two main advantages over the existing method. First, the analyst draws borders only in 2D planes that cut approximately through the center of the nucleus under consideration so that the nuclear borders generally are most distinct. Second, the analyst draws only five borders around each nucleus, and then the algorithm interpolates the entire surface. The algorithm results in segmented objects that correspond to individual, visually identifiable nuclei. The segmented surfaces, however, may not exactly represent the true nuclear surface. An optional, automatic surface optimization algorithm can be applied to reduce this error.

Iterative Multilevel Thresholding and Splitting for Three-Dimensional Segmentation of Live Cell Nuclei Using Laser Scanning Confocal Microscopy

Accurate thresholding and segmentation of three-dimensional structures within thick biological specimens is particularly difficult to achieve. However, there exists a vast array of possible methods and approaches with which to tackle this problem. In this paper, we describe the problems associated with cellular segmentation and computerised analysis of confocal derived data from living blood vessels. In addition, current segmentation methods are examined and discussed in relation to their use with biological samples. Finally, a novel iterative multilevel thresholding and splitting method for semiautomated 3D segmentation of objects of different brightness and intensity homogeneity is presented. The method is particularly suited to segmentation of vascular cell volumes. The method has been tested on three typical confocal data sets, each of which have features common to 3D volumes of living biological tissue. The segmenter has been estimated to produce results which are accurate to within 90% of the “ground truth” measurements.

Automatic Hough Transform-Based 3D Segmentation of Cell Nuclei in Thick Tissue Sections

Combining pathology, which reports the structural features of individual cells and their spatial organi-zation in a tissue specimen, with molecular biology techniques (immunocytochemistry and fluores-cence in situ hybridization, FISH) for detecting the distribution of specific molecular species in individual cells is a powerful approach for gaining insight into the underlying disease mechanisms of carcinogenesis. This approach requires analysis of thick (>20 ¼m) tissue sections in which cells are preserved intact within the context of their environment. 3D (confocal) microscope image acquisition followed by 3D image analysis (IA) for extracting quantitative information are then used for quantita-tive analysis of tissue features such as nuclear and/or cell volume, shape, total fluorescence or FISH signal number. An essential component of the IA is detection of the individual cells, or their nuclei since many molecular species of interest are localized within the nucleus (e.g. genetic aberrations). We present here a completely automatic, 3D algorithm for this task, which based on the Hough transform (HT).

Three‐dimensional DNA image cytometry by confocal scanning laser microscopy in thick tissue blocks of prostatic lesions

DNA ploidy provides important information for the evaluation of the prognosis of prostate cancer. For the purpose of DNA cytometry and nuclear measurements, we developed an image processing system for the acquisition and processing of three-dimensional (3D) images based on confocal scanning laser microscopy (CSLM). The advantage of the CSLM is the preservation of the tissue architecture and the possibility of multilabeling. It is possible to determine both individual nuclear features and cellular features and the degree of the spatial heterogeneity of several markers. Special attention was paid to the development of the automatic method for the 3D segmentation of cell nuclei. Thick tissue slides (100 μm), stained for DNA with chromomycin A3, from 4 patients (with benign hyperplasia, prostatic intraepithelial neoplasia (PIN), and well-and poorly-differentiated adenocarcinoma of the prostate), were studied in order to test the practicability of the developed methodology. DNA histograms showed a single peak in the diploid range for the hyperplasia and PIN cases. For the case of well-differentiated carcinoma, 2 peaks were observed, 1 in the diploid range and 1 in the tetraploid range. The case of poorly-differentiated carcinoma was characterized by an aneuploid distribution. For the cases of PIN and carcinomas, we observed a considerable variation of the volume of nuclei. Cytometry 27:99–105, 1997. © 1997 Wiley-Liss, Inc.

Three-dimensional DNA image cytometry by confocal scanning laser microscopy in thick tissue blocks of prostatic lesions

DNA ploidy provides important information for the evaluation of the prognosis of prostate cancer. For the purpose of DNA cytometry and nuclear measurements, we developed an image processing system for the acquisition and processing of three-dimensional (3D) images based on confocal scanning laser microscopy (CSLM). The advantage of the CSLM is the preservation of the tissue architecture and the possibility of multilabeling. It is possible to determine both individual nuclear features and cellular features and the degree of the spatial heterogeneity of several markers. Special attention was paid to the development of the automatic method for the 3D segmentation of cell nuclei. Thick tissue slides (100 microm), stained for DNA with chromomycin A3, from 4 patients (with benign hyperplasia, prostatic intraepithelial neoplasia (PIN), and well-and poorly-differentiated adenocarcinoma of the prostate), were studied in order to test the practicability of the developed methodology. DNA histograms showed a single peak in the diploid range for the hyperplasia and PIN cases. For the case of well-differentiated carcinoma, 2 peaks were observed, 1 in the diploid range and I in the tetraploid range. The case of poorly-differentiated carcinoma was characterized by an aneuploid distribution. For the cases of PIN and carcinomas, we observed a considerable variation of the volume of nuclei.

Pupil diameter in migraine and tension headache.

Pupil diameter was measured in darkness and in dull and bright illumination in 39 migrainous patients and in 15 tension headache sufferers during headache. In 21 migrainous patients, measurements were repeated during the headache-free interval. Mean pupil diameter was smaller in patients with common migraine at the time of examination than in 20 nonheadache control subjects, and smaller on the symptomatic side in migrainous patients with unilateral headache. During the headache-free interval mean pupil diameter did not differ from values in non-headache controls. These findings suggest that migraine is associated with a sympathetic pupillary deficit which is greater on the habitually-affected side.

The Wedge Filter Technique for Convex Boundary Estimation

This paper describes a method for segmentation of convex shaped image regions. The wedge filter technique first employs the converging squares algorithm [1] to locate a region of interest. Then a region oriented boundary estimation technique, called the wedge filter, is applied. This wedge filter entails angular filtering and subsampling, and boundary interpolation. The technique is more capable of segmenting noncircular shapes than some earlier methods based on the Hough transform. In addition, unlike many edge-based segmentation schemes, this method is relatively tolerant to edge gaps and to blurred or thick edges. This technique is tested on a number of synthesized images over a range of convex shapes, for different algorithm parameters, and under various conditions of region size and image noise. In addition, the technique has been applied to segmentation of liver cell nuclei in light microscope images of human liver tissue.

Segmentation of cell nuclei in tissue section analysis.

Image segmentation is a critical step in digital picture analysis, especially for that of tissue sections. As the morphology of the cell nuclei provides important biological information, their segmentation is of particular interest. The known segmentation methods are not adequate for segmenting cell nuclei of tissue sections; the reason for this lies in the optical properties of their images. We have developed new gradient methods of segmentation of previously presegmented images by taking these properties into account and by using the approximately circular shape of the cell nuclei as a priori information. In our first technique, the segment method, the images of the nuclei are divided into eight segments, special gradient filters being defined for each segment. This has enabled us to improve the gradient image. After searching for local maxima, the contours of nuclei can be found. In the second method, the method of transformation into the polar coordinate system (PCS), the a priori information serves to define a circular direction field for gradient computation and contour finding. In contrast with the first method, which offers a rapid, general idea about the nuclear shape, the PCS method permits precise segmentation and morphological analysis of the cell nuclei.

Fine structure of extremely slender nuclear bridges in segmented cell nuclei

Fine structure of extremely slender nuclear bridges in segmented cell nuclei