Segmentation of overlapping leucocyte images with phase detection and spiral interpolation

Leucocyte segmentation is one of the most crucial functionalities for an automatic leucocyte recognition system. In this paper, an algorithm is proposed to segment the leucocytes from the overlapping cell images. It consists of two main steps. The first step involves generation of a combined image based on the saturation and green channels (CIBSGC) by means of the different distribution characteristics of the leucocyte nucleus. A weight coefficient is used to adjust the CIBSGC for extracting the nucleus and estimating the location of the leucocyte. Second, a method of phase detection and spiral interpolation identifies the overlapping regions of cells and determines the leucocyte edge curve. The performance is evaluated by three parameters: sensitivity, positive predictive value and pixel number error. Experimental results validate that the proposed algorithm can successfully segment the overlapping leucocyte with the satisfactory performance for two cell image datasets under different recording conditions.     

Segmentation of the Clustered Cells with Optimized Boundary Detection in Negative Phase Contrast Images

Cell image segmentation plays a central role in numerous biology studies and clinical applications. As a result, the development of cell image segmentation algorithms with high robustness and accuracy is attracting more and more attention. In this study, an automated cell image segmentation algorithm is developed to get improved cell image segmentation with respect to cell boundary detection and segmentation of the clustered cells for all cells in the field of view in negative phase contrast images. A new method which combines the thresholding method and edge based active contour method was proposed to optimize cell boundary detection. In order to segment clustered cells, the geographic peaks of cell light intensity were utilized to detect numbers and locations of the clustered cells. In this paper, the working principles of the algorithms are described. The influence of parameters in cell boundary detection and the selection of the threshold value on the final segmentation results are investigated. At last, the proposed algorithm is applied to the negative phase contrast images from different experiments. The performance of the proposed method is evaluated. Results show that the proposed method can achieve optimized cell boundary detection and highly accurate segmentation for clustered cells.     

High resolution segmentation of cervical cells.

A major problem in the automation of cervical cytology screening is the segmentation of cell images. This paper presents the present status of the work on that problem at the University of Uppsala. A dual resolution system is used. Suspect malignant cells are located at 4 mu resolution. Each such cell is rescanned at 0.5 mu resolution at two different wavelengths, 530 and 570 nm. The nucleus and the cytoplasm are isolated each by two independent methods. For the nucleus adaptive thresholding in the histogram of the 570 nm image and a contouring in a radially transformed version of that image is used. For the cytoplasm a two dimensional thresholding in the 2D histogram and a contouring in a radially transformed version of the 530 nm image is used. If the two nuclear masks agree the surrounding area is checked for disturbing objects. If also the cytoplasm masks agree and are without disturbing objects the whole cell is accepted. The result of the cytoplasm masks agree and are without disturbing objects the whole cell is accepted. The result of the segmentation is thus three categories; free cells, free nuclei and rejected objects. The shape of the objects belonging to the former two categories is checked and irregularly shaped ones are rejected as probably consisting of several overlapping nuclei. Cells passing also this test are classified as normal or malignant. The experience from using this algorithm is discussed and areas for further research are pointed out.     

Cellular quantitative analysis of neuroblastoma tumor and splitting overlapping cells

Background

Neuroblastoma Tumor (NT) is one of the most aggressive types of infant cancer. Essential to accurate diagnosis and prognosis is cellular quantitative analysis of the tumor. Counting enormous numbers of cells under an optical microscope is error-prone. There is therefore an urgent demand from pathologists for robust and automated cell counting systems. However, the main challenge in developing these systems is the inability of them to distinguish between overlapping cells and single cells, and to split the overlapping cells. We address this challenge in two stages by: 1) distinguishing overlapping cells from single cells using the morphological differences between them such as area, uniformity of diameters and cell concavity; and 2) splitting overlapping cells into single cells. We propose a novel approach by using the dominant concave regions of cells as markers to identify the overlap region. We then find the initial splitting points at the critical points of the concave regions by decomposing the concave regions into their components such as arcs, chords and edges, and the distance between the components is analyzed using the developed seed growing technique. Lastly, a shortest path determination approach is developed to determine the optimum splitting route between two candidate initial splitting points.

Results

We compare the cell counting results of our system with those of a pathologist as the ground-truth. We also compare the system with three state-of-the-art methods, and the results of statistical tests show a significant improvement in the performance of our system compared to state-of-the-art methods. The F-measure obtained by our system is 88.70%. To evaluate the generalizability of our algorithm, we apply it to images of follicular lymphoma, which has similar histological regions to NT. Of the algorithms tested, our algorithm obtains the highest F-measure of 92.79%.

Conclusion

We develop a novel overlapping cell splitting algorithm to enhance the cellular quantitative analysis of infant neuroblastoma. The performance of the proposed algorithm promises a reliable automated cell counting system for pathology laboratories. Moreover, the high performance obtained by our algorithm for images of follicular lymphoma demonstrates the generalization of the proposed algorithm for cancers with similar histological regions and histological structures.     

A Framework for White Blood Cell Segmentation in Microscopic Blood Images Using Digital Image Processing

Evaluation of blood smear is a commonly clinical test these days. Most of the time, the hematologists are interested on white blood cells (WBCs) only. Digital image processing techniques can help them in their analysis and diagnosis. For example, disease like acute leukemia is detected based on the amount and condition of the WBC. The main objective of this paper is to segment the WBC to its two dominant elements: nucleus and cytoplasm. The segmentation is conducted using a proposed segmentation framework that consists of an integration of several digital image processing algorithms. Twenty microscopic blood images were tested, and the proposed framework managed to obtain 92% accuracy for nucleus segmentation and 78% for cytoplasm segmentation. The results indicate that the proposed framework is able to extract the nucleus and cytoplasm region in a WBC image sample.     

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.     

Segmentation of parotid glands from registered CT and MR images

PurposeTo develop an automatic multimodal method for segmentation of parotid glands (PGs) from pre-registered computed tomography (CT) and magnetic resonance (MR) images and compare its results to the results of an existing state-of-the-art algorithm that segments PGs from CT images only.MethodsMagnetic resonance images of head and neck were registered to the accompanying CT images using two different state-of-the-art registration procedures. The reference domains of registered image pairs were divided on the complementary PG regions and backgrounds according to the manual delineation of PGs on CT images, provided by a physician. Patches of intensity values from both image modalities, centered around randomly sampled voxels from the reference domain, served as positive or negative samples in the training of the convolutional neural network (CNN) classifier. The trained CNN accepted a previously unseen (registered) image pair and classified its voxels according to the resemblance of its patches to the patches used for training. The final segmentation was refined using a graph-cut algorithm, followed by the dilate-erode operations.ResultsUsing the same image dataset, segmentation of PGs was performed using the proposed multimodal algorithm and an existing monomodal algorithm, which segments PGs from CT images only. The mean value of the achieved Dice overlapping coefficient for the proposed algorithm was 78.8%, while the corresponding mean value for the monomodal algorithm was 76.5%.ConclusionsAutomatic PG segmentation on the planning CT image can be augmented with the MR image modality, leading to an improved RT planning of head and neck cancer.     

Quantitation of Satellite Cell Proliferation in Vivo Using Image Analysis

A nonisotopic, double fluorescence technique was developed to study myogenic satellite cell proliferation in posthatch turkey skeletal muscle. Labeled satellite cell nuclei were identified on enzymatically isolated myofiber segments using a mouse monoclonal antibody (anti-BrdU) followed by fluorescein-5-isothiocyanate (FITC) conjugated goat anti-mouse IgG secondary antibody. Myofiber nuclei (myonuclei + satellite cell nuclei) were counterstained with propidium iodide (PI). The myofiber segment length, myofiber segment diameter, and the number of PI and FITC labeled nuclei contained in each segment was determined using a Nikon fluorescence microscope, a SIT video camera and Image-1 software. Data collected by three different operators of the image analysis system revealed 5.0 ± 1.4 satellite cell nuclei per 1000 myofiber nuclei and 5284 ± 462 μm³ of cytoplasm surrounding each myofiber nucleus in the pectoralis thoracicus of 9-week-old tom turkeys. BrdU immunohistochemistry coupled with the new approach of PI staining of whole myofiber mounts is an effective combination to allow the use of an efficient semi-automated image analysis protocol.     

Segmentation of Fluorescence Microscopy Images for Quantitative Analysis of Cell Nuclear Architecture

Considerable advances in microscopy, biophysics, and cell biology have provided a wealth of imaging data describing the functional organization of the cell nucleus. Until recently, cell nuclear architecture has largely been assessed by subjective visual inspection of fluorescently labeled components imaged by the optical microscope. This approach is inadequate to fully quantify spatial associations, especially when the patterns are indistinct, irregular, or highly punctate. Accurate image processing techniques as well as statistical and computational tools are thus necessary to interpret this data if meaningful spatial-function relationships are to be established. Here, we have developed a thresholding algorithm, stable count thresholding (SCT), to segment nuclear compartments in confocal laser scanning microscopy image stacks to facilitate objective and quantitative analysis of the three-dimensional organization of these objects using formal statistical methods. We validate the efficacy and performance of the SCT algorithm using real images of immunofluorescently stained nuclear compartments and fluorescent beads as well as simulated images. In all three cases, the SCT algorithm delivers a segmentation that is far better than standard thresholding methods, and more importantly, is comparable to manual thresholding results. By applying the SCT algorithm and statistical analysis, we quantify the spatial configuration of promyelocytic leukemia nuclear bodies with respect to irregular-shaped SC35 domains. We show that the compartments are closer than expected under a null model for their spatial point distribution, and furthermore that their spatial association varies according to cell state. The methods reported are general and can readily be applied to quantify the spatial interactions of other nuclear compartments.     

Biological Image Segmentation Using Region-Scalable Fitting Energy with B-Spline Level Set Implementation and Watershed

ObjectivesImage segmentation plays an important role in the analysis and understanding of the cellular process. However, this task becomes difficult when there is intensity inhomogeneity between regions, and it is more challenging in the presence of the noise and clustered cells. The goal of the paper is propose an image segmentation framework that tackles the above cited problems.Material and methodsA new method composed of two steps is proposed: First, segment the image using B-spline level set with Region-Scalable Fitting (RSF) active contour model, second apply the Watershed algorithm based on new object markers to refine the segmentation and separate clustered cells. The major contributions of the paper are: 1) Use of a continuous formulation of the level set in the B-spline basis, 2) Develop the energy function and its derivative by introducing the RSF model to deal with intensity inhomogeneity, 3) For the Watershed, propose a relevant choice of markers that considers the cell properties.ResultsExperimental results are performed on widely used synthetic images, in addition to simulated and real biological images, without and with additive noise. They attest the high quality of segmentation of the proposed method in terms of quantitative and qualitative evaluation.ConclusionThe proposed method is able to tackle many difficulties at the same time: overlapped intensities, noise, different cell sizes and clustered cells. It provides an efficient tool for image segmentation especially biological ones.     

Theoretical Limits on Errors and Acquisition Rates in Localizing Switchable Fluorophores

A variety of recent imaging techniques are able to beat the diffraction limit in fluorescence microcopy by activating and localizing subsets of the fluorescent molecules in the specimen, and repeating this process until all of the molecules have been imaged. In these techniques there is a tradeoff between speed (activating more molecules per imaging cycle) and error rates (activating more molecules risks producing overlapping images that hide information on molecular positions), and so intelligent image processing approaches are needed to identify and reject overlapping images. We introduce here a formalism for defining error rates, derive a general relationship between error rates, image acquisition rates, and the performance characteristics of the image processing algorithms, and show that there is a minimum acquisition time irrespective of algorithm performance. We also consider algorithms that can infer molecular positions from images of overlapping blurs, and derive the dependence of the minimum acquisition time on algorithm performance.     

Network inference through synergistic subnetwork evolution

Study of signaling networks is important for a better understanding of cell behaviors e.g., growth, differentiation, metabolism, proptosis, and gaining deeper insights into the molecular mechanisms of complex diseases. While there have been many successes in developing computational approaches for identifying potential genes and proteins involved in cell signaling, new methods are needed for identifying network structures that depict underlying signal cascading mechanisms. In this paper, we propose a new computational approach for inferring signaling network structures from overlapping gene sets related to the networks. In the proposed approach, a signaling network is represented as a directed graph and is viewed as a union of many active paths representing linear and overlapping chains of signal cascading activities in the network. Gene sets represent the sets of genes participating in active paths without prior knowledge of the order in which genes occur within each path. From a compendium of unordered gene sets, the proposed algorithm reconstructs the underlying network structure through evolution of synergistic active paths. In our context, the extent of edge overlapping among active paths is used to define the synergy present in a network. We evaluated the performance of the proposed algorithm in terms of its convergence and recovering true active paths by utilizing four gene set compendiums derived from the KEGG database. Evaluation of results demonstrate the ability of the algorithm in reconstructing the underlying networks with high accuracy and precision.     

A Fast Color Image Encryption Algorithm Using 4-Pixel Feistel Structure

Algorithms using 4-pixel Feistel structure and chaotic systems have been shown to resolve security problems caused by large data capacity and high correlation among pixels for color image encryption. In this paper, a fast color image encryption algorithm based on the modified 4-pixel Feistel structure and multiple chaotic maps is proposed to improve the efficiency of this type of algorithm. Two methods are used. First, a simple round function based on a piecewise linear function and tent map are used to reduce computational cost during each iteration. Second, the 4-pixel Feistel structure reduces round number by changing twist direction securely to help the algorithm proceed efficiently. While a large number of simulation experiments prove its security performance, additional special analysis and a corresponding speed simulation show that these two methods increase the speed of the proposed algorithm (0.15s for a 256*256 color image) to twice that of an algorithm with a similar structure (0.37s for the same size image). Additionally, the method is also faster than other recently proposed algorithms.     

Sequential Partially Overlapping Gene Arrangement in the Tricistronic S1 Genome Segments of Avian Reovirus and Nelson Bay Reovirus: Implications for Translation Initiation

Previous studies of the avian reovirus strain S1133 (ARV-S1133) S1 genome segment revealed that the open reading frame (ORF) encoding the final sigmaC viral cell attachment protein initiates over 600 nucleotides distal from the 5' end of the S1 mRNA and is preceded by two predicted small nonoverlapping ORFs. To more clearly define the translational properties of this unusual polycistronic RNA, we pursued a comparative analysis of the S1 genome segment of the related Nelson Bay reovirus (NBV). Sequence analysis indicated that the 3'-proximal ORF present on the NBV S1 genome segment also encodes a final sigmaC homolog, as evidenced by the presence of an extended N-terminal heptad repeat characteristic of the coiled-coil region common to the cell attachment proteins of reoviruses. Most importantly, the NBV S1 genome segment contains two conserved ORFs upstream of the final sigmaC coding region that are extended relative to the predicted ORFs of ARV-S1133 and are arranged in a sequential, partially overlapping fashion. Sequence analysis of the S1 genome segments of two additional strains of ARV indicated a similar overlapping tricistronic gene arrangement as predicted for the NBV S1 genome segment. Expression analysis of the ARV S1 genome segment indicated that all three ORFs are functional in vitro and in virus-infected cells. In addition to the previously described p10 and final sigmaC gene products, the S1 genome segment encodes from the central ORF a 17-kDa basic protein (p17) of no known function. Optimizing the translation start site of the ARV p10 ORF lead to an approximately 15-fold increase in p10 expression with little or no effect on translation of the downstream final sigmaC ORF. These results suggest that translation initiation complexes can bypass over 600 nucleotides and two functional overlapping upstream ORFs in order to access the distal final sigmaC start site.     

A thresholding method for automatic cell image segmentation.

An algorithm for automatic segmentation of PAP-stained cell images and its digital implementation is described. First, the image is filtered in order to eliminate the granularily and small objects in the image which may upset the segmentation procedure. In a second step, information on gradient and compactness is extracted from the filtered image and stored in three histograms as functions of the extinction. From these histograms, two extinction thresholds are computed. These thresholds are suitable to separate the nucleus from the cytoplasm, and the cytoplasm from the background in the filtered image. Masks are determined in this way, and finally used to analyse the nucleus and the cytoplasm in the original image.     

Integrating image quality in 2nu-SVM biometric match score fusion

This paper proposes an intelligent 2nu-support vector machine based match score fusion algorithm to improve the performance of face and iris recognition by integrating the quality of images. The proposed algorithm applies redundant discrete wavelet transform to evaluate the underlying linear and non-linear features present in the image. A composite quality score is computed to determine the extent of smoothness, sharpness, noise, and other pertinent features present in each subband of the image. The match score and the corresponding quality score of an image are fused using 2nu-support vector machine to improve the verification performance. The proposed algorithm is experimentally validated using the FERET face database and the CASIA iris database. The verification performance and statistical evaluation show that the proposed algorithm outperforms existing fusion algorithms.     

Novel cell segmentation and online SVM for cell cycle phase identification in automated microscopy

MOTIVATION: Automated identification of cell cycle phases captured via fluorescent microscopy is very important for understanding cell cycle and for drug discovery. In this article, we propose a novel cell detection method that utilizes both the intensity and shape information of the cell for better segmentation quality. In contrast to conventional off-line learning algorithms, an Online Support Vector Classifier (OSVC) is thus proposed, which removes support vectors from the old model and assigns new training examples weighted according to their importance to accommodate the ever-changing experimental conditions. RESULTS: We image three cell lines using fluorescent microscopy under different experiment conditions, including one treated with taxol. Then, we segment and classify the cell types into interphase, prophase, metaphase and anaphase. Experimental results show the effectiveness of the proposed system in image segmentation and cell phase identification. AVAILABILITY: The software and test datasets are available from the authors.     

Automated image detection and segmentation in blood smears.

A simple technique which automatically detects and then segments nucleated cells in Wright's giemsa-stained blood smears is presented. Our method differs from others in 1) the simplicity of our algorithms; 2) inclusion of touching (as well as nontouching) cells; and 3) use of these algorithms to segment as well as to detect nucleated cells employing conventionally prepared smears. Our method involves: 1) acquisition of spectral images; 2) preprocessing the acquired images; 3) detection of single and touching cells in the scene; 4) segmentation of the cells into nuclear and cytoplasmic regions; and 5) postprocessing of the segmented regions. The first two steps of this algorithm are employed to obtain high-quality images, to remove random noise, and to correct aberration and shading effects. Spectral information of the image is used in step 3 to segment the nucleated cells from the rest of the scene. Using the initial cell masks, nucleated cells which are just touching are detected and separated. Simple features are then extracted and conditions applied such that single nucleated cells are finally selected. In step 4, the intensity variations of the cells are then used to segment the nucleus from the cytoplasm. The success rate in segmenting the nucleated cells is between 81 and 93%. The major errors in segmentation of the nucleus and the cytoplasm in the recognized nucleated cells are 3.5% and 2.2%, respectively.     

White Blood Cells Image Classification Using Deep Learning with Canonical Correlation Analysis

White Blood Cells play an important role in observing the health condition of an individual. The opinion related to blood disease involves the identification and characterization of a patient's blood sample. Recent approaches employ Convolutional Neural Network (CNN), Recurrent Neural Network (RNN) and merging of CNN and RNN models to enrich the understanding of image content. From beginning to end, training of big data in medical image analysis has encouraged us to discover prominent features from sample images. A single cell patch extraction from blood sample techniques for blood cell classification has resulted in the good performance rate. However, these approaches are unable to address the issues of multiple cells overlap. To address this problem, the Canonical Correlation Analysis (CCA) method is used in this paper. CCA method views the effects of overlapping nuclei where multiple nuclei patches are extracted, learned and trained at a time. Due to overlapping of blood cell images, the classification time is reduced, the dimension of input images gets compressed and the network converges faster with more accurate weight parameters. Experimental results evaluated using publicly available database show that the proposed CNN and RNN merging model with canonical correlation analysis determines higher accuracy compared to other state-of-the-art blood cell classification techniques.