Automatic segmentation of cell nuclei in Feulgen-stained histological sections of prostate cancer and quantitative evaluation of segmentation results

Digital image analysis of cell nuclei is useful to obtain quantitative information for the diagnosis and prognosis of cancer. However, the lack of a reliable automatic nuclear segmentation is a limiting factor for high-throughput nuclear image analysis. We have developed a method for automatic segmentation of nuclei in Feulgen-stained histological sections of prostate cancer. A local adaptive thresholding with an object perimeter gradient verification step detected the nuclei and was combined with an active contour model that featured an optimized initialization and worked within a restricted region to improve convergence of the segmentation of each nucleus. The method was tested on 30 randomly selected image frames from three cases, comparing the results from the automatic algorithm to a manual delineation of 924 nuclei. The automatic method segmented a few more nuclei compared to the manual method, and about 73% of the manually segmented nuclei were also segmented by the automatic method. For each nucleus segmented both manually and automatically, the accuracy (i.e., agreement with manual delineation) was estimated. The mean segmentation sensitivity/specificity were 95%/96%. The results from the automatic method were not significantly different from the ground truth provided by manual segmentation. This opens the possibility for large-scale nuclear analysis based on automatic segmentation of nuclei in Feulgen-stained histological sections.     

Automatic quantification of microvessels using unsupervised image analysis.

An automatic method for quantification of images of microvessels by computing area proportions and number of objects is presented. The objects are segmented from the background using dynamic thresholding of the average component size histogram. To be able to count the objects, fragmented objects are connected, all objects are filled, and touching objects are separated using a watershed segmentation algorithm. The method is fully automatic and robust with respect to illumination and focus settings. A test set consisting of images grabbed with different focus and illumination for each field of view, was used to test the method, and the proposed method showed less variation than the intraoperator variation using manual threshold. Further, the method showed good correlation to manual object counting (r = 0.80) on an other test set.     

Color image analysis for quantifying renal tumor angiogenesis

OBJECTIVE: To segment and quantify microvessels in renal tumor angiogenesis based on a color image analysis method and to improve the accuracy and reproducibility of quantifying microvessel density. STUDY DESIGN: The segmentation task was based on a supervised learning scheme. First, 12 color features (RGB, HSI, I1I2I3 and L*a*b*) were extracted from a training set. The feature selection procedure selected I2L*S features as the best color feature vector. Then we segmented microvessels using the discriminant function made using the minimum error rate classification rule of Bayesian decision theory. In the quantification step, after applying a connected component-labeling algorithm, microvessels with discontinuities were connected and touching microvessels separated. We tested the proposed method on 23 images. RESULTS: The results were evaluated by comparing them with manual quantification of the same images. The comparison revealed that our computerized microvessel counting correlated highly with manual counting by an expert (r = 0.95754). The association between the number of microvessels after the initial segmentation and manual quantification was also assessed using Pearson's correlation coefficient (r = 0.71187). The results indicate that our method is better than conventional computerized image analysis methods. CONCLUSION: Our method correlated highly with quantification by an expert and could become a way to improve the accuracy, feasibility and reproducibility of quantifying microvessel density. We anticipate that it will become a useful diagnostic tool for angiogenesis studies.     

Label-free imaging and classification of live P. falciparum enables high performance parasitemia quantification without fixation or staining

Manual microscopic inspection of fixed and stained blood smears has remained the gold standard for Plasmodium parasitemia analysis for over a century. Unfortunately, smear preparation consumes time and reagents, while manual microscopy is skill-dependent and labor-intensive. Here, we demonstrate that deep learning enables both life stage classification and accurate parasitemia quantification of ordinary brightfield microscopy images of live, unstained red blood cells. We tested our method using both a standard light microscope equipped with visible and near-ultraviolet (UV) illumination, and a custom-built microscope employing deep-UV illumination. While using deep-UV light achieved an overall four-category classification of Plasmodium falciparum blood stages of greater than 99% and a recall of 89.8% for ring-stage parasites, imaging with near-UV light on a standard microscope resulted in 96.8% overall accuracy and over 90% recall for ring-stage parasites. Both imaging systems were tested extrinsically by parasitemia titration, revealing superior performance over manually-scored Giemsa-stained smears, and a limit of detection below 0.1%. Our results establish that label-free parasitemia analysis of live cells is possible in a biomedical laboratory setting without the need for complex optical instrumentation. We anticipate future extensions of this work could enable label-free clinical diagnostic measurements, one day eliminating the need for conventional blood smear analysis.     

Automatic image segmentation of nuclear stained breast tissue sections using color active contour model and an improved watershed method

Automatic image segmentation of immunohistologically stained breast tissue sections helps pathologists to discover the cancer disease earlier. The detection of the real number of cancer nuclei in the image is a very tedious and time consuming task. Segmentation of cancer nuclei, especially touching nuclei, presents many difficulties to separate them by traditional segmentation algorithms. This paper presents a new automatic scheme to perform both classification of breast stained nuclei and segmentation of touching nuclei in order to get the total number of cancer nuclei in each class. Firstly, a modified geometric active contour model is used for multiple contour detection of positive and negative nuclear staining in the microscopic image. Secondly, a touching nuclei method based on watershed algorithm and concave vertex graph is proposed to perform accurate quantification of the different stains. Finally, benign nuclei are identified by their morphological features and they are removed automatically from the segmented image for positive cancer nuclei assessment. The proposed classification and segmentation schemes are tested on two datasets of breast cancer cell images containing different level of malignancy. The experimental results show the superiority of the proposed methods when compared with other existing classification and segmentation methods. On the complete image database, the segmentation accuracy in term of cancer nuclei number is over than 97%, reaching an improvement of 3–4% over earlier methods.     

Three-dimensional DNA image cytometry by confocal scanning laser microscopy in thick tissue blocks.

A method for the quantification of nuclear DNA in thick tissue blocks by confocal scanning laser microscopy is presented. Tissues were stained en bloc for DNA by chromomycin A3. Three-dimensional images, 60 microns deep, were obtained by stacking up confocal fluorescent images obtained with an MRC-500 (Bio-Rad, Richmond, CA). The effects due to bleaching and attenuation by depth of fluorescence emission were corrected mathematically. The DNA contents were estimated by summing up the detected emission intensities (discretized into pixel gray levels) from each segmented nucleus. Applications to an adult rat liver and to a human in situ carcinoma of theesophagus are shown to demonstrate, respectively, the precision of the method and its potential usefulness in histopathology. Comparisons are made with DNA histograms obtained on the same materials by image cytometry on smears and by flow cytometry. Ploidy peaks obtained with the confocal method, although wider than with other methods, are well separated. Confocal image cytometry offers the invaluable advantage of preserving the tissue architecture and therefore allowing, for instance, the selection of histological regions and the evaluation of the degree of heterogeneity of a tumor.     

The Correlation Between Texture Features and Fibrous Cap Thickness of Lipid-Rich Atheroma Based on Optical Coherence Tomography Imaging

Fibrous cap thickness (FCT) is seen as critical to plaque vulnerability. Therefore, the development of automatic algorithms for the quantification of FCT is for estimating cardiovascular risk of patients. Intravascular optical coherence tomography (IVOCT) is currently the only in vivo imaging modality with which FCT, the critical component of plaque vulnerability, can be assessed accurately. This study was aimed to discussion the correlation between the texture features of OCT images and the FCT in lipid-rich atheroma. Methods: Firstly, a full automatic segmentation algorithm based on unsupervised fuzzy c means (FCM) clustering with geometric constrains was developed to segment the ROIs of IVOCT images. Then, 32 features, which are associated with the structural and biochemical changes of tissue, were carried out to describe the properties of ROIs. The FCT in grayscale IVOCT images were manually measured by two independent observers. In order to analysis the correlation between IVOCT image features and manual FCT measurements, linear regression approach was performed. Results: Inter-observer agreement of the twice manual FCT measurements was excellent with an intraclass correlation coefficient (ICC) of 0.99. The correlation coefficient between each individual feature set and mean FCT of OCT images were 0.68 for FOS, 0.80 for GLCM, 0.74 for NGTDM, 0.72 for FD, 0.62 for IM and 0.58 for SP. The fusion image features of automatic segmented ROIs and FCT measurements improved the results significantly with a high correlation coefficient (r= 0.91, p<0.001). Conclusion The OCT images features demonstrated the perfect performances and could be used for automatic qualitative analysis and the identification of high-risk plaques instead manual FCT measurements.     

The granulocyte nucleus and lamin B receptor: avoiding the ovoid

The major human blood granulocyte, the neutrophil, is an essential component of the innate immunity system, emigrating from blood vessels and migrating through tight tissue spaces to the site of bacterial or fungal infection where they kill and phagocytose invading microbes. Since the late nineteenth century, it has been recognized that the human neutrophil nucleus is distinctly not ovoid as in other cell types, but possesses a lobulated (segmented) shape. This deformable nucleus enhances rapid migration. Recent studies have demonstrated that lamin B receptor (LBR) is necessary for the non-ovoid shape. LBR is an integral membrane protein of the nuclear envelope. A single dominant mutation in humans leads to neutrophils with hypolobulated nuclei (Pelger–Huet anomaly); homozygosity leads to ovoid granulocyte nuclei. Interestingly, LBR is also an enzyme involved in cholesterol metabolism. Homozygosity for null mutations is frequently lethal and associated with severe skeletal deformities. In addition to the necessity for LBR, formation of the mature granulocyte nucleus also depends upon lamin composition and microtubule integrity. These observations are part of a larger question on the relationships between nuclear shape and cellular function.     

Genetic algorithm for shift-uncertainty correction in 1-D NMR-based metabolite identifications and quantifications

MOTIVATION: The analysis of metabolic processes is becoming increasingly important to our understanding of complex biological systems and disease states. Nuclear magnetic resonance spectroscopy (NMR) is a particularly relevant technology in this respect, since the NMR signals provide a quantitative measure of the metabolite concentrations. However, due to the complexity of the spectra typical of biological samples, the demands of clinical and high-throughput analysis will only be fully met by a system capable of reliable, automatic processing of the spectra. An initial step in this direction has been taken by Targeted Profiling (TP), employing a set of known and predicted metabolite signatures fitted against the signal. However, an accurate fitting procedure for (1)H NMR data is complicated by shift uncertainties in the peak systems caused by measurement imperfections. These uncertainties have a large impact on the accuracy of identification and quantification and currently require compensation by very time consuming manual interactions. Here, we present an approach, termed Extended Targeted Profiling (ETP), that estimates shift uncertainties based on a genetic algorithm (GA) combined with a least squares optimization (LSQO). The estimated shifts are used to correct the known metabolite signatures leading to significantly improved identification and quantification. In this way, use of the automated system significantly reduces the effort normally associated with manual processing and paves the way for reliable, high-throughput analysis of complex NMR spectra. RESULTS: The results indicate that using simultaneous shift uncertainty correction and least squares fitting significantly improves the identification and quantification results for (1)H NMR data in comparison to the standard targeted profiling approach and compares favorably with the results obtained by manual expert analysis. Preservation of the functional structure of the NMR spectra makes this approach more realistic than simple binning strategies.     

The human granulocyte nucleus: Unusual nuclear envelope and heterochromatin composition

The human blood granulocyte (neutrophil) is adapted to find and destroy infectious agents. The nucleus of the human neutrophil has a segmented appearance, consisting of a linear or branched array of three or four lobes. Adequate levels of lamin B receptor (LBR) are necessary for differentiation of the lobulated nucleus. The levels of other components of the nuclear envelope may also be important for nuclear shape determination. In the present study, immunostaining and immunoblotting procedures explored the levels of various components of the nuclear envelope and heterochromatin, comparing freshly isolated human neutrophils with granulocytic forms of HL-60 cells, a tissue culture model system. In comparison to granulocytic HL-60 cells, blood neutrophil nuclear envelopes contain low-to-negligible amounts of LBR, lamins A/C, B1 and B2, LAP2β and emerin. Surprisingly, a “mitotic” chromosome marker, H3(S10)phos, is elevated in neutrophil nuclei, compared to granulocytic HL-60 cells. Furthermore, neutrophil nuclei appear to be more fragile to methanol fixation, than observed with granulocytic HL-60 cells. Thus, the human neutrophil nucleus appears to be highly specialized, possessing a paucity of nuclear envelope-stabilizing proteins. In consequence, the neutrophil nucleus appears to be very malleable, supporting rapid migration through tight tissue spaces.     

通过光学相干断层扫描图像进行自动视网膜分割评估黄斑水肿的投影面积

在本文中,我们提出了一种自动视网膜分割方法,以评估光学相干断层扫描（OCT）图像中黄斑水肿（ME）在视网膜特定层上的投影面积。首先使用基于权重矩阵的优化的最短路径最快算法对十个视网膜层边界进行分割,这有效降低了算法对血管阴影的敏感性。然而,ME的存在将导致水肿区域的分割不准确。因此,我们使用强度阈值方法提取每个OCT图像中的水肿区域,并将该区域中的值设置为零,并确保获得的分割边界可以自动穿过而不是绕过水肿区域。我们使用最小值投影来计算ME在不同层的投影面积。为了测试我们的方法,我们使用了从Topcon的OCT机器收集的数据。在轴向和B扫描方向上测得的黄斑区域分辨率分别为11.7微米和46.8微米。与手动分割相比,视网膜层边界分割的平均绝对误差和标准偏差为4.5±3.2微米。因此,所提出的方法为评估水肿提供了一种自动,无创和定量的工具。     

Parasitemia in PCR‐detected Plasmodium and Haemoproteus infections in birds

Most comparative studies of avian blood parasites based on visual inspection of smears have reported Haemoproteus infections to be more prevalent than Plasmodium infections in both tropical and temperate locations. Recently, molecular techniques have increased our ability to detect infections often missed on blood smears. Here we quantify the bias in prevalence resulting from unrecognized infections by examining blood smears of infected passerine birds from the West Indies (312 individuals) and the Ozark Mountains of southern Missouri (134 individuals) for which we could identify parasites based on cytochrome b sequences. In the West Indian sample, 63 of 179 Haemoproteus infections (35%) and 121 of 133 Plasmodium infections (91%) were not detected among ca. 2,800 red blood cells examined per smear. In the Missouri sample, 19 of 77 Haemoproteus infections (25%) and 31 of 57 Plasmodium infections (54%) were not detected among ca. 10,000 red blood cells examined. Clearly, visual inspection of blood smears at this level of effort fails to recognize many malaria parasite infections ascertained by PCR screening, and this bias for Plasmodium parasites exceeds that for Haemoproteus parasites. The lower prevalence of Plasmodium compared to Haemoproteus reported in comparative studies based on blood smears likely reflects differences in detection rather than infection rates. Estimates obtained from visual inspection of blood smears would appear to be more indicative of parasite virulence and how well host individuals control infections than of the prevalence of infections in host populations.     

NMR study of xenotropic murine leukemia virus-related virus protease in a complex with amprenavir

Liver steatosis was once believed to be a benign condition, with rare progression to chronic liver disease. Thus, in both clinical and experimental practice, it is fundamental to have a reliable and objective method for its precise quantification. An image analysis algorithm was developed and validated for automatically and rapidly quantifying hepatic fat microvesicles. The image processing algorithms automatically segmented interstitial steatosis areas and analyzed the threshold region. Automatic quantifications did not significantly differ from manual evaluations of means of the same areas. Comparison of our image analysis quantifications with staging of histologic evaluations of liver steatosis presented significant correlations that are based on the distribution patterns and on the area quantity of steatosis, respectively. The use of algorithms for analysis and image processing is a sensitive, precise, objective and reproducible method of quantifying hepatic fat microvesicles, which complements semi-quantitative histologic evaluation systems.     

Network representation of protein interactions: Theory of graph description and analysis

A methodological framework is presented for the graph theoretical interpretation of NMR data of protein interactions. The proposed analysis generalizes the idea of network representations of protein structures by expanding it to protein interactions. This approach is based on regularization of residue‐resolved NMR relaxation times and chemical shift data and subsequent construction of an adjacency matrix that represents the underlying protein interaction as a graph or network. The network nodes represent protein residues. Two nodes are connected if two residues are functionally correlated during the protein interaction event. The analysis of the resulting network enables the quantification of the importance of each amino acid of a protein for its interactions. Furthermore, the determination of the pattern of correlations between residues yields insights into the functional architecture of an interaction. This is of special interest for intrinsically disordered proteins, since the structural (three‐dimensional) architecture of these proteins and their complexes is difficult to determine. The power of the proposed methodology is demonstrated at the example of the interaction between the intrinsically disordered protein osteopontin and its natural ligand heparin.     

Neutrophil marrow release. A system analysis.

Neutrophil marrow egress is governed by several processes. The most important are cell maturation, functional behavior of marrow sinusoids and humoral or neuro-vascular factors. Neutrophil release cannot be observed directly but is reflected in the size, cellular composition and kinetics of the nonproliferating pool of granulocytopoiesis in bone marrow and of blood neutrophil pool. These experimentally determined parameters were used as the basis of a mathematical model study. The model describes two catenated compartments, the nonproliferating pool of granulocytopoiesis in marrow and the total blood granulocyte pool. Cell transit from one pool to the other was assumed to be age-dependent. It was expressed by a positive sloping sigmoidal function that defines the egress potential fo the cells that increases with cell maturation. During maturation granulocytopoietic cells develop intense motility which determines the morphology of the cells on smears. Relationship between cell motility and its morphology was defined by functions determining the age-dependent probabilities of cell fixation as metamyelocytes, band- and segmented forms, respectively. The parameters of this model could be so adjusted that all experimental data were matched within experimental errors. Thus, qualitative and quantitative information on neutrophil marrow egress was obtained for normal and pathological states of granulocytopoiesis.     

Haptic Exploratory Behavior During Object Discrimination: A Novel Automatic Annotation Method

In order to acquire information concerning the geometry and material of handheld objects, people tend to execute stereotypical hand movement patterns called haptic Exploratory Procedures (EPs). Manual annotation of haptic exploration trials with these EPs is a laborious task that is affected by subjectivity, attentional lapses, and viewing angle limitations. In this paper we propose an automatic EP annotation method based on position and orientation data from motion tracking sensors placed on both hands and inside a stimulus. A set of kinematic variables is computed from these data and compared to sets of predefined criteria for each of four EPs. Whenever all criteria for a specific EP are met, it is assumed that that particular hand movement pattern was performed. This method is applied to data from an experiment where blindfolded participants haptically discriminated between objects differing in hardness, roughness, volume, and weight. In order to validate the method, its output is compared to manual annotation based on video recordings of the same trials. Although mean pairwise agreement is less between human-automatic pairs than between human-human pairs (55.7% vs 74.5%), the proposed method performs much better than random annotation (2.4%). Furthermore, each EP is linked to a specific object property for which it is optimal (e.g., Lateral Motion for roughness). We found that the percentage of trials where the expected EP was found does not differ between manual and automatic annotation. For now, this method cannot yet completely replace a manual annotation procedure. However, it could be used as a starting point that can be supplemented by manual annotation.     

Classification of Leukemia and Leukemoid Using VGG-16 Convolutional Neural Network Architecture

Leukemoid reaction like leukemia indicates noticeable increased count of WBCs (White Blood Cells) but the cause of it is due to severe inflammation or infections in other body regions. In automatic diagnosis in classifying leukemia and leukemoid reactions, ALL IDB2 (Acute Lymphoblastic Leukemia-Image Data Base) dataset has been used which comprises 110 training images of blast cells and healthy cells. This paper aimed at an automatic process to distinguish leukemia and leukemoid reactions from blood smear images using Machine Learning. Initially, automatic detection and counting of WBC is done to identify leukocytosis and then an automatic detection of WBC blasts is performed to support classification of leukemia and leukemoid reactions. Leukocytosis is commonly observed both in leukemia and leukemoid hence physicians may have chance of wrong diagnosis of malignant leukemia for the patients with leukemoid reactions. BCCD (blood cell count detection) Dataset has been used which has 364 blood smear images of which 349 are of single WBC type. The Image segmentation algorithm of Hue Saturation Value color based on watershed has been applied. VGG16 (Visual Geometric Group) CNN (Convolution Neural Network) architecture based deep learning technique is being incorporated for classification and counting WBC type from segmented images. The VGG16 architecture based CNN used for classification and segmented images obtained from first part were tested to identify WBC blasts.     

Automatic segmentation and supervised learning-based selection of nuclei in cancer tissue images

Analysis of preferential localization of certain genes within the cell nuclei is emerging as a new technique for the diagnosis of breast cancer. Quantitation requires accurate segmentation of 100-200 cell nuclei in each tissue section to draw a statistically significant result. Thus, for large-scale analysis, manual processing is too time consuming and subjective. Fortuitously, acquired images generally contain many more nuclei than are needed for analysis. Therefore, we developed an integrated workflow that selects, following automatic segmentation, a subpopulation of accurately delineated nuclei for positioning of fluorescence in situ hybridization-labeled genes of interest. Segmentation was performed by a multistage watershed-based algorithm and screening by an artificial neural network-based pattern recognition engine. The performance of the workflow was quantified in terms of the fraction of automatically selected nuclei that were visually confirmed as well segmented and by the boundary accuracy of the well-segmented nuclei relative to a 2D dynamic programming-based reference segmentation method. Application of the method was demonstrated for discriminating normal and cancerous breast tissue sections based on the differential positioning of the HES5 gene. Automatic results agreed with manual analysis in 11 out of 14 cancers, all four normal cases, and all five noncancerous breast disease cases, thus showing the accuracy and robustness of the proposed approach. ? Published 2012 Wiley Periodicals, Inc.     

Segmentation of stained blood cell images measured at high scanning density with high magnification and high numerical aperture optics

In hematological morphology, it is necessary to resolve and analyze the smallest possible cellular details appearing in the light microscope. A prerequisite for computer-aided analysis of subtle morphological features is measuring the cells at a high scanning density with high magnification and high numerical aperture optics. Contrary to visual observations, the information content in a measured picture can be increased by setting the condensor's numerical aperture (NA) greater than the objective's NA. The complexity and heterogeneity of such cell images necessitate a new segmentation method that conserves the morphological information required in the subsequent image analysis, feature extraction, and cell classification. In our segmentation strategy, characteristic color difference thresholds for each nucleus and cytoplasm are combined with geometric operations, probability functions, and a cell model. All thresholds are repeatedly recalculated during the successive improvements of the image masks. None of the thresholds are fixed. This strategy segments blood cell images containing touching cells and large variations in staining, texture, size, and shape. Biological inconsistencies in the calculated cell masks are eliminated by comparing each mask with the cell model criteria integrated into the entire segmentation process. All 20,000 leukocyte images from 120 smears in our leukemia project were segmented with this method.