Automated detection of working area of peripheral blood smears using mathematical morphology.

The paper presents a technique to automatically detect the working area of peripheral blood smears stained with May-Grünwuald Giemsa. The optimal area is defined as the well spread part of the smear. This zone starts when the erythrocytes stop overlapping (on the body film side) and finishes when the erythrocytes start losing their clear central zone (on the feather edge side). The approach yields a quick detection of this area in images scanned under low magnifying power (immersion objective x 25 or x 16). The algorithm consists of two stages. First, an image analysis procedure using mathematical morphology is applied for extracting the erythrocytes, the centers of erythrocytes and the erythrocytes with center. Second, the number of connected components from the three kinds of particles is counted and the coefficient of spreading rho(s) and the coefficient of overlapping rho(o) are calculated. The data from fourteen smears illustrate how the technique is used and its performance. Colour figures can be viewed on http://www.esacp.org/acp/2003/25-1/angulo.htm.     

Automated image segmentation by fractal grey tone functions

A new image segmentation method is presented. It is based on mathematical derivations stemming from both mathematical morphology and fractal geometry. Structures of different nature are most often characterized by a fractal grey tone function, in a certain range of resolutions, with a particular value of the fractal dimension. Our method allows the isolation of such structures. It only requires a series of dilated and eroded grey tone images.     

Automated identification of diploid reference cells in cervical smears using image analysis

BACKGROUND: Acquisition of DNA ploidy histograms by image analysis may yield important information regarding the behavior of premalignant cervical lesions. Accurate selection of nuclei for DNA measurement is an important prerequisite for obtaining reliable data. Traditionally, manual selection of nuclei of diagnostic and reference cells is performed by an experienced cytotechnologist. In the present study, a method for the fully automated identification of nuclei of diploid epithelial reference cells in Feulgen- restained Papanicolaou (PAP) smears is described. METHODS: The automated procedure consists of a decision tree implemented on the measurement device, containing nodes with feature threshold values and multivariate discriminant functions. Nodes were constructed to recognize debris and inflammatory cells, as well as diploid and nondiploid epithelial cells of the uterine cervix. Evaluation of the classifier was performed by comparing resulting diploid integrated optical densities with those from manually selected reference cells. RESULTS AND CONCLUSION: On average, automatically acquired values deviated 2.4% from manually acquired values, indicating that the method described in this paper may be useful in cytometric practice.     

Automated fluorescence image cytometry. DNA quantification and detection of chlamydial infections

Digitized fluorescence microscopy in conjunction with automated image segmentation is a promising approach for screening clinical specimens quickly and reliably. This paper describes the hardware and software of a prototype image-based cytometer that can identify fluorescent objects, discriminate true objects from artifacts and divide overlapping pairs of objects. The use of this image cytometer is discussed for: (1) the measurement of the DNA ploidy distribution of isolated mature rat liver nuclei labeled with 4',6-diamidine-2-phenylindole; (2) the comparison of the DNA ploidy distributions of the same samples measured by image cytometry (ICM) and flow cytometry (FCM); and (3) the quantification of chlamydial infection by double labeling cells with antichlamydiae antibody and Hoechst 33258 for nuclear DNA analysis. Ploidy distributions measured by the automated image cytometer compared favorably to those obtained by FCM. All pairs of overlapping nuclei were automatically detected by an additional computer algorithm, and those pairs that were clearly more than one nucleus by visual inspection were correctly divided. The irregular morphology of the chlamydiae-infected cells meant that 26% of them were not correctly identified in the fluorescein-stained images (as judged by manual inspection), but all cells were nevertheless detected correctly from the images of the Hoechst-stained samples. Automated fluorescence ICM yielded results similar to those obtained with FCM and had the additional benefit of maintaining cell and tissue architecture while preserving the opportunity for subsequent manual inspection of the specimen.     

Detecting infection-related changes in peripheral blood smears with image analysis techniques

High-resolution image analysis has the potential to flag subtle changes in white blood cell morphology that may indicate the presence of certain diseases. A study was made of the feasibility of identifying patients with hematologic bacterial infections (sepsis) using measurements on Wright-Giemsa-stained peripheral blood smears. Neutrophils and lymphocytes from a group of patients with sepsis and from a control group were digitized, and parameters quantifying geometry, color, texture and shape were extracted. While color parameters differed the most between the infected and control samples, substantial differences in geometric, texture and shape parameters also were observed. Analysis of the data showed that individual neutrophils and lymphocytes from patients with sepsis were distinguishable from those of the control group with better than 84% accuracy. When average parameters were calculated from all cells of one type for each specimen, 100% accurate classification was obtained. These studies demonstrate that the image-analysis techniques used are sensitive enough to detect disease-related changes in cell morphology that are generally too subtle for reliable detection by the human eye. Future experiments will determine the specificity of this test for bacterial infections and will explore the possibility of using image analysis techniques on peripheral blood to detect and monitor a wide variety of diseases.     

Mobile image sensors for object detection using color segmentation

The intelligent mobile robot with sensors and image processing embedded system combines the suction and aerodynamic attraction to achieve good balance between strong adhesion force and high mobility. Experimental results showed that the robot can move upward on the wall at the speed of 2.9 m/min and carry 5 kg payload in addition to 2.5 kg self-weight, which record the highest payload capacity among climbing robots of similar size. It also implements object detection ability using effective color transform and segmentation technique for the exact target detection on the wall using a embedded camera system, communication module and several active sensors.     

Automated detection and segmentation of synaptic contacts in nearly isotropic serial electron microscopy images

We describe a protocol for fully automated detection and segmentation of asymmetric, presumed excitatory, synapses in serial electron microscopy images of the adult mammalian cerebral cortex, taken with the focused ion beam, scanning electron microscope (FIB/SEM). The procedure is based on interactive machine learning and only requires a few labeled synapses for training. The statistical learning is performed on geometrical features of 3D neighborhoods of each voxel and can fully exploit the high z-resolution of the data. On a quantitative validation dataset of 111 synapses in 409 images of 1948×1342 pixels with manual annotations by three independent experts the error rate of the algorithm was found to be comparable to that of the experts (0.92 recall at 0.89 precision). Our software offers a convenient interface for labeling the training data and the possibility to visualize and proofread the results in 3D. The source code, the test dataset and the ground truth annotation are freely available on the website http://www.ilastik.org/synapse-detection.     

Calculus of variations and image segmentation.

A survey of free discontinuity problems related to image segmentation is given. The main properties and open problems about Mumford and Shah and Blake and Zisserman functionals are shown together with an extensive bibliography about recent mathematical developments.     

Automated detection and recognition of live cells in tissue culture using image cytometry

An automated image cytometry device, the Cell Analyzer, was used to locate live V79 cells plated at low densities in a tissue culture flask. Cells and other objects were detected by moving the flask in steps across a linear solid-state image sensor. The step size was selected to be small enough to allow detection of all the cells in the area being scanned but sufficiently large so that most cells would be detected on only one image line. To distinguish cells from other detected objects, a recognition algorithm utilizing 18 characteristic cell signal features was developed. The algorithm first tests whether a set of feature values falls within specified upper and lower bounds, and then applies a linear discriminant function to the remaining data to further discriminate cells from debris. False-positive errors of 5% or less were achieved with this method, whereas 15-35% of cells were misclassified as debris.     

Automated image analysis in autoradiography

Light microscope autoradiographs can be analysed with the aid of the Quantimet, a commercially available image scanning instrument. Standardization of the performance of the instrument was obtained by performing on-line data reduction and display with a small digital computer. The number of silver grains over individual cells can be rapidly and routinely determined, and excellent agreement can be achieved between visually determined and machine generated grain counts.     

Automated detection of Salmonella spp. in foods.

An automated method to detect salmonellae in foods was developed and tested in food samples intentionally contaminated with the test organisms. Liquid eggs, shell eggs, dry eggs, skim milk and chicken were spiked with Salmonella enteritidis, S. typhimurium or S. newport to yield 2 to 25 CFU per 25 g or ml of sample. Following pre-enrichment in universal pre-enrichment broth at 42 degrees C for 6 h (eggs and milk) or 16 h (chicken), Salmonella cells were captured by immunomagnetic beads coated with Salmonella antibody (Vicam, Watertown, MA). The beads were transferred to selective liquid media containing carbohydrate (dulcitol or xylose), amino acid (lysine or ornithine), and H2S indicator, and incubated at 42 degrees C in the BioSys instrument (MicroSys, Ann Arbor, MI). Salmonella positive samples were identified by black discoloration of the media during incubation, while negative samples remained colorless. These color changes were recorded by the instrument. All the artificially contaminated samples tested positive within 15-18 h, while control samples remained negative during 24 h incubation. The results agreed with standard identification procedures. A total of 24 h was required to detect 2 to 25 CFU of the pathogen in 25 g or ml of eggs and milk, and up to 36 h in chicken, compared to 72 h in the standard methods.     

Feature-based image segmentation in human vision

Experiments are described which indicate that the integration of high-precision shape information along a bright line is blocked by the presence of certain image features. All the features involved have three properties: (1) they are points where contours are not smooth (i.e. not twice differentiable) within the limits set by the finite space constants of visual processes; (2) they are all points that are emphasized in the responses of certain classes of circularly symmetric bandpass spatial filter; and (3) they are all significant for three-dimensional shape analysis. The results are interpreted as implying an inflexible segmentation of the contour image before detailed shape analysis.     

A direct fluorescence technique for the rapid detection of sheathed microfilariae in blood smears

Thick and thin blood smears containing microfilariae of Wuchereria bancrofti, Loa loa, Brugia malayi, Brugia pahangi, Brugia patei or Acanthocheilonema vileae were prepared from either cryopreserved blood samples or from freshly collected blood, fixed in methanoi and treated with a fluoresceinated lectin wheat germ agglutinin. Sheathed microfilariae of W. bancrofti, L. loa, B. malayi, B. pahangi and B. patei in the blood smears could be easily detected and counted using a fluorescence assay. The unsheathed microfilaria of Acanthocheilonema viteae did not fluoresce. The possibility of adapting this technique, which does not require the use of parasite specific antibody for the sensitive, parasitological detection offilarial infections, is discussed.     

Automated image analysis for array hybridization experiments.

MOTIVATION: Image analysis is a major part of data evaluation for array hybridization experiments in molecular biology. The program presented here is designed to analyze automatically images from hybridization experiments with various arrangements: different kinds of probes (oligonucleotides or complex probes), different supports (nylon filters or glass slides), different labeling of probes (radioactively or fluorescently). The program is currently applied to oligonucleotide fingerprinting projects and complex hybridizations. The only precondition for the use of the program is that the targets are arrayed in a grid, which can be approximately transformed to an orthogonal equidistant grid by a projective mapping. RESULTS: We demonstrate that our program can cope with the following problems: global distortion of the grid, missing of grid nodes, local deviation of the spot from its specified grid position. This is checked by different quality measures. The image analysis of oligonucleotide fingerprint experiments on an entire genetic library is used, in clustering procedures, to group related clones together. The results show that the program yields automatically generated high quality input data for follow up analysis such as clustering procedures. AVAILABILITY: The executable files will be available upon request for academics.     

Quantification of hematozoa in blood smears

Ten thin blood smears from mourning doves (Zenaida macroura) infected with Haemoproteus maccallumi were examined by each of two observers using identical techniques and microscopy in an attempt to delineate the factors necessary to provide an accurate estimate of the number of parasites/n erythrocytes. The number of erythrocytes examined must be actually counted, not estimated from extrapolated partial counts or from the number of fields of view examined. Doubling the number of erythrocytes counted (1) decreased the overdispersed frequency distribution patterns in only 25% of the replicate counts for numbers of H. maccallumi/100 erythrocytes for a series of 2,000 versus 4,000 erythrocytes counted; and (2) did not significantly increase the accuracy for determining parasite intensities. Thus, the number of erythrocytes that must be counted to determine parasite intensities could be considerably reduced from the 10,000 or 20,000 estimated for most studies, and still provide an accurate determination of the number of parasites/n erythrocytes in datasets collected from hosts with moderate to high levels of parasitemia. This resulted in a decreased amount of time expended by the observer on each blood smear examined. With two equivalently trained individuals, differences between observers examining the same blood smears were minimal. This study suggests an approach by which a more standardized methodology for quantifying blood parasite intensities could be developed.     

Adaptive color basis transformation. An aid in image segmentation

Multispectral images of stained cells enable the use of color differences to segment and/or to discriminate between image components, such as cell types and cellular subcomponents. When the spectral characteristics of the image components do not change over the area of a slide or from slide to slide, one can create a constant weighted linear combination of spectral images to generate one-dimensional or two-dimensional images that have the desired contrast between the image components that must be discriminated. However, when the spectral characteristics are not constant, i.e., when they vary from image to image, a constant weighted linear combination cannot be employed; instead, an appropriate solution must be found for each selected image. This is usually a time-consuming, manual procedure that cannot be employed in a fully automated process of discriminating and segmenting stained cells. This paper describes an algorithm that uses principal components decomposition basis vectors to generate a nonstatic weighted linear combination of color images that can be used by an automated system. This algorithm relies on a semiconstant relationship between the areas (sizes) of the image components that are to be discriminated and/or segmented. The technique has been successfully applied as an aid in the segmentation of images of stained cervical smears; the images were acquired with a three-chip CCD camera that generates three broad-band color images.     

Computer-aided image analysis for the differentiation of mononuclear cells in peripheral blood smears from leukemic patients

Different leukemias originating from the lymphatic system and from the myeloid tissue of the bone marrow were selected to develop and test algorithms to cytophotometrically define leukemic cells. Two of these cases were of low-grade, one of intermediate-grade and one of high-grade malignancy. The malignant cell types of each leukemic form could be identified and characterized by assessing the chromatin texture of the nucleus in the leukemic cells. With this method, normal peripheral white blood cells could be differentiated from leukemic ones. The results correlate directly with established hematologic parameters as they are described in the literature. The investigation demonstrated the usefulness of computer methods in the differentiation of closely related cell structures.