A binary segmentation approach for boxing ribosome particles in cryo EM micrographs.

Three-dimensional reconstruction of ribosome particles from electron micrographs requires selection of many single-particle images. Roughly 100,000 particles are required to achieve approximately 10 A resolution. Manual selection of particles, by visual observation of the micrographs on a computer screen, is recognized as a bottleneck in automated single-particle reconstruction. This paper describes an efficient approach for automated boxing of ribosome particles in micrographs. Use of a fast, anisotropic non-linear reaction-diffusion method to pre-process micrographs and rank-leveling to enhance the contrast between particles and the background, followed by binary and morphological segmentation constitute the core of this technique. Modifying the shape of the particles to facilitate segmentation of individual particles within clusters and boxing the isolated particles is successfully attempted. Tests on a limited number of micrographs have shown that over 80% success is achieved in automatic particle picking.

Segmentation of volumetric tissue images using constrained active contour models.

In this article we describe an application of active contour model for the segmentation of 3D histo-pathological images. The 3D images of a thick tissue specimen are obtained as a stack of optical sections using confocal laser beam scanning microscope (CLSM). We have applied noise reduction and feature enhancement methods so that a smooth and slowly varying potential surface is obtained for proper convergence. To increase the capture range of the potential surface, we use a combination of distance potential and the diffused gradient potential as external forces. It has been shown that the region-based information obtained from low-level segmentation can be applied to reduce the adverse influence of the neighbouring nucleus having a strong boundary feature. We have also shown that, by increasing the axial resolution of the image stack, we can automatically propagate the optimum active contour of one image slice to its neighbouring image slices as an appropriate initial model. Results on images of prostate tissue section are presented.

An integrated system for feature evaluation of 3D images of a tissue specimen.

In this article we have proposed an integrated system for measurement of important features from 3D tissue images. We propose a segmentation technique, where we combine several methods to achieve a good degree of automation. Important histological and cytological three-dimensional features and strategies to measure them are described.

Automatic analysis of agarose gel images.

MOTIVATION: Automatic tools to speed up routine biological processes are very much sought after in bio-medical research. Much repetitive work in molecular biology, such as allele calling in genetic analysis, can be made semi-automatic or task specific automatic by using existing techniques from computer science and signal processing. Computerized analysis is reproducible and avoids various forms of human error. Semi-automatic techniques with an interactive check on the results speed up the analysis and reduce the error. RESULTS: We have successfully implemented an image processing software package to automatically analyze agarose gel images of polymorphic DNA markers. We have obtained up to 90% accuracy for the classification of alleles in good quality images and up to 70% accuracy in average quality images. These results are obtained within a few seconds. Even after subsequent interactive checking to increase the accuracy of allele classification to 100%, the overall speed with which the data can be processed is greatly increased, compared to manual allele classification. AVAILABILITY: The IDL source code of the software is available on request from jonathan.flint@well.ox.ac.uk

Integrated approach for segmentation of 3-D confocal images of a tissue specimen.

In this article we have proposed an integrated approach for segmentation of cells in volumetric image data obtained using the Confocal Microscope. The volumetric images are the stack of two-dimensional (2-D) images. Segmentation of cells in such an image stack is a difficult problem due to the complex structure of the objects and the spatial relationship of the object signatures in different image slices of the image stack. Here we have proposed a segmentation technique, which is a combination of several known and novel segmentation methods. Low-level techniques such as edge operators, middle-level techniques such as 3-D watershed, rule-based merging, and a high level technique, active surface model optimization, are integrated in one approach to get better segmentation with less human interaction. Some image enhancement and noise reduction techniques are also used to reduce the error in intermediate stages and speed up the segmentation process. Results are shown on 3-D images of prostate cancer tissue specimen.

Some efficient methods to correct confocal images for easy interpretation.

In this paper we have explained some efficient methods to correct artefacts in confocal laser beam scanning microscope (CLSM) images. The main aim is to enhance object features such that they become clearly visible for interactive evaluation and to reduce the overall noise so that the automatic segmentation and feature measurement can be done easily. A simple automatic-thresholding technique, and a straightforward method to restore the light intensity along the depth of the image stack are proposed. Another problem associated with the CLSM is the non-isotropic resolution. We have presented an interpolation technique based on XOR contouring and morphing to virtually insert the image slices in the image stack for improving the axial resolution. This interpolation technique has the merits of both contour- and intensity-based interpolations. Results of application of these methods on CLSM data are shown.

Region based techniques for segmentation of volumetric histo-pathological images.

In this article we have presented the application of three region based segmentation techniques namely, seeded volume growing, constrained erosion-dilation techniques and 3-D watershed algorithm. The algorithms are suitably extended to apply on 3-D histo-pathological images. Suitable modifications and extension for each algorithm is done to obtain better segmentation. A quantitative as well as qualitative comparison of the three methods is presented. Modifications to these algorithms for obtaining better results are discussed. The modifications include, (1) design of adaptive similarity measures to control the seeded volume growing and (2) rule-based merging of the over-segmented cells in the case of the 3-D watershed algorithm. Some results and quantitative study is also presented.

Segmentation and counting of FISH signals in confocal microscopy images.

In this paper we have presented a semi-automatic method for segmenting and counting the Fluorescence In Situ Hybridization (FISH) signals per cell nucleus in a 3D tissue image. The number of FISH signals indicate the gain (trisomy) or loss (monosomy) of certain base-sequences in deoxyribonucleic acid (DNA). The quantitative evaluation of the loss or gain in DNA is necessary in qualitative diagnostic molecular pathology. Multispectral volumetric images are obtained using the Confocal Microscope. Each consists of a red channel depicting the 3D morphology of the tissue and green channel containing the FISH signals. The red channel tissue image is segmented first to determine the membership of the FISH signal to a particular nuclei. Various segmentation methods starting from simple local thresholding to volume growing and active volumes are used for segmentation. A brief comparative study of the visual signal count by pathologist and our automatic count is also presented.

Deformable models for segmentation of CLSM tissue images and its application in FISH signal analysis.

In this paper we present an application of deformable models for the segmentation of volumetric tissue images. The three-dimensional images are obtained using confocal microscope. The segmented images have been used for the quantitative analysis of the Fluorescence In Situ Hybridization (FISH) signals. An ellipsoidal surface initialized around the cell of interest acts as a deformable model. The deformable model surface voxels are subjected to various internal and external forces derived from underlying image features as well as externally imposed constraints. The deformable model converges to the optimum cell shape when the vector sum of all the forces acting on the model is zero. The result of segmentation is used to confirm the cell membership of the FISH signals and to reject all the signals that lie outside the cell nuclei. Three-dimensional region isolation and labeling technique is used to label and count the FISH signals per cell nucleus. A simple study on the effect of different segmentation methods over a quantitative analysis of FISH signals is also presented.

Efficient cell segmentation tool for confocal microscopy tissue images and quantitative evaluation of FISH signals.

In this paper we have presented a semi-automatic method for segmenting 3-D cell nuclei from tissue images obtained using Confocal Laser Scanning Microscope. This microscope can focus at different layers of the specimen and hence a stack of images giving a 3D representation can be obtained. The existing methods for segmenting the cells in 3-D confocal images are highly interactive and, hence, time consuming. We have developed an approach, where, given one segmented image-slice (optical section) of the set of confocal images, the remaining image-slices in the image stack can be automatically segmented in a layered approach. One of the image-slices in an image stack is considered as a representative image-slice. In this image-slice, overlapping boundary pixels are identified interactively while the remaining part of the cell boundary is marked using Laplacian of a Gaussian operator. This interactively traced portion of the boundary is considered as initial boundary for finding the overlapping boundary pixels in the neighboring image-slices. Simple basic search strategy is used for boundary search in the neighboring image-slices. The method minimizes the human interaction and is also found to be efficient and reasonably accurate. Some experimental results are presented to illustrate the usefulness of the technique. We have also given the application of our segmentation method to quantitative evaluation of fluorescence in situ hybridization (FISH) signals. A brief comparative study of visual FISH signal evaluation and the FISH signal counting by automatic image analysis is also given.

Groping for quantitative digital 3-D image analysis: an approach to quantitative fluorescence in situ hybridization in thick tissue sections of prostate carcinoma.

In molecular pathology numerical chromosome aberrations have been found to be decisive for the prognosis of malignancy in tumours. The existence of such aberrations can be detected by interphase fluorescence in situ hybridization (FISH). The gain or loss of certain base sequences in the desoxyribonucleic acid (DNA) can be estimated by counting the number of FISH signals per cell nucleus. The quantitative evaluation of such events is a necessary condition for a prospective use in diagnostic pathology. To avoid occlusions of signals, the cell nucleus has to be analyzed in three dimensions. Confocal laser scanning microscopy is the means to obtain series of optical thin sections from fluorescence stained or marked material to fulfill the conditions mentioned above. A graphical user interface (GUI) to a software package for display, inspection, count and (semi-)automatic analysis of 3-D images for pathologists is outlined including the underlying methods of 3-D image interaction and segmentation developed. The preparative methods are briefly described. Main emphasis is given to the methodical questions of computer-aided analysis of large 3-D image data sets for pathologists. Several automated analysis steps can be performed for segmentation and succeeding quantification. However tumour material is in contrast to isolated or cultured cells even for visual inspection, a difficult material. For the present a fully automated digital image analysis of 3-D data is not in sight. A semi-automatic segmentation method is thus presented here.