Active Subdivision Surfaces for the Semiautomatic Segmentation of Biomedical Volumes.

We present a new family of active surfaces for the semiautomatic segmentation of volumetric objects in 3D biomedical images. We represent our deformable model by a subdivision surface encoded by a small set of control points and generated through a geometric refinement process. The subdivision operator confers important properties to the surface such as smoothness, reproduction of desirable shapes and interpolation of the control points. We deform the subdivision surface through the minimization of suitable gradient-based and region-based energy terms that we have designed for that purpose. In addition, we provide an easy way to combine these energies with convolutional neural networks. Our active subdivision surface satisfies the property of multiresolution, which allows us to adopt a coarse-to-fine optimization strategy. This speeds up the computations and decreases its dependence on initialization compared to singleresolution active surfaces. Performance evaluations on both synthetic and real biomedical data show that our active subdivision surface is robust in the presence of noise and outperforms current state-of-the-art methods. In addition, we provide a software that gives full control over the active subdivision surface via an intuitive manipulation of the control points.

Automatic image annotation for fluorescent cell nuclei segmentation.

Dataset annotation is a time and labor-intensive task and an integral requirement for training and testing deep learning models. The segmentation of images in life science microscopy requires annotated image datasets for object detection tasks such as instance segmentation. Although the amount of annotated image data has been steadily reduced due to methods such as data augmentation, the process of manual or semi-automated data annotation is the most labor and cost intensive task in the process of cell nuclei segmentation with deep neural networks. In this work we propose a system to fully automate the annotation process of a custom fluorescent cell nuclei image dataset. By that we are able to reduce nuclei labelling time by up to 99.5%. The output of our system provides high quality training data for machine learning applications to identify the position of cell nuclei in microscopy images. Our experiments have shown that the automatically annotated dataset provides coequal segmentation performance compared to manual data annotation. In addition, we show that our system enables a single workflow from raw data input to desired nuclei segmentation and tracking results without relying on pre-trained models or third-party training datasets for neural networks.

Single-nucleus RNA-seq identifies divergent populations of FSHD2 myotube nuclei.

FSHD is characterized by the misexpression of DUX4 in skeletal muscle. Although DUX4 upregulation is thought to be the pathogenic cause of FSHD, DUX4 is lowly expressed in patient samples, and analysis of the consequences of DUX4 expression has largely relied on artificial overexpression. To better understand the native expression profile of DUX4 and its targets, we performed bulk RNA-seq on a 6-day differentiation time-course in primary FSHD2 patient myoblasts. We identify a set of 54 genes upregulated in FSHD2 cells, termed FSHD-induced genes. Using single-cell and single-nucleus RNA-seq on myoblasts and differentiated myotubes, respectively, we captured, for the first time, DUX4 expressed at the single-nucleus level in a native state. We identified two populations of FSHD myotube nuclei based on low or high enrichment of DUX4 and FSHD-induced genes ("FSHD-Lo" and "FSHD Hi", respectively). FSHD-Hi myotube nuclei coexpress multiple DUX4 target genes including DUXA, LEUTX and ZSCAN4, and also upregulate cell cycle-related genes with significant enrichment of E2F target genes and p53 signaling activation. We found more FSHD-Hi nuclei than DUX4-positive nuclei, and confirmed with in situ RNA/protein detection that DUX4 transcribed in only one or two nuclei is sufficient for DUX4 protein to activate target genes across multiple nuclei within the same myotube. DUXA (the DUX4 paralog) is more widely expressed than DUX4, and depletion of DUXA suppressed the expression of LEUTX and ZSCAN4 in late, but not early, differentiation. The results suggest that the DUXA can take over the role of DUX4 to maintain target gene expression. These results provide a possible explanation as to why it is easier to detect DUX4 target genes than DUX4 itself in patient cells and raise the possibility of a self-sustaining network of gene dysregulation triggered by the limited DUX4 expression.

Robust classification of cell cycle phase and biological feature extraction by image-based deep learning.

Across the cell cycle, the subcellular organization undergoes major spatiotemporal changes that could in principle contain biological features that could potentially represent cell cycle phase. We applied convolutional neural network-based classifiers to extract such putative features from the fluorescence microscope images of cells stained for the nucleus, the Golgi apparatus, and the microtubule cytoskeleton. We demonstrate that cell images can be robustly classified according to G1/S and G2 cell cycle phases without the need for specific cell cycle markers. Grad-CAM analysis of the classification models enabled us to extract several pairs of quantitative parameters of specific subcellular features as good classifiers for the cell cycle phase. These results collectively demonstrate that machine learning-based image processing is useful to extract biological features underlying cellular phenomena of interest in an unbiased and data-driven manner.

Overview of nuclear bodies and their classification in the Terminologia Histologica.

BACKGROUND: Nuclear bodies (NB) are membrane-less subnuclear organelles that perform important functions in the cell, such as transcription, RNA splicing, processing and transport of ribosomal pre-RNA, epigenetic regulation, and others. The aim of the work was to analyse the classification of NB in the Terminologia Histologica (TH) and biological and bibliographical databases. MATERIALS AND METHODS: The semantic structure of the Nucleoplasm section in the TH was analysed and unsystematic bibliographical search was made in the PubMed, SciELO, EMBASE databases and European Bioinformatics Institute (EMBL-EBI) biology database to identify which structures are classified as NB. RESULTS: It was found that the terms Corpusculum convolutum, Macula interchromatinea and Corpusculum PML are not correctly classified in the TH, since they are subordinated under the term Chromatinum and not under Corpusculum nucleare. The bibliography consulted showed that 100%, 92.6% and 81.5% of articles mentioned Corpusculum convolutum, Macula interchromatinea and Corpusculum PML, respectively as nuclear bodies. CONCLUSIONS: It is suggested to relocate the terms Corpusculum convolutum, Macula interchromatinea and Corpusculum PML with the name of Corpusculum nucleare and the incorporation of two new entities to the Histological Terminology according to the information collected: paraspeckles and histone locus body.

Pixel-to-Pixel Learning With Weak Supervision for Single-Stage Nucleus Recognition in Ki67 Images.

OBJECTIVE: Nucleus recognition is a critical yet challenging step in histopathology image analysis, for example, in Ki67 immunohistochemistry stained images. Although many automated methods have been proposed, most use a multi-stage processing pipeline to categorize nuclei, leading to cumbersome, low-throughput, and error-prone assessments. To address this issue, we propose a novel deep fully convolutional network for single-stage nucleus recognition. METHODS: Instead of conducting direct pixel-wise classification, we formulate nucleus identification as a deep structured regression model. For each input image, it produces multiple proximity maps, each of which corresponds to one nucleus category and exhibits strong responses in central regions of the nuclei. In addition, by taking into consideration the nucleus distribution in histopathology images, we further introduce an auxiliary task, region of interest (ROI) extraction, to assist and boost the nucleus quantification with weak ROI annotation. The proposed network can be learned in an end-to-end, pixel-to-pixel manner for simultaneous nucleus detection and classification. RESULTS: We have evaluated this network on a pancreatic neuroendocrine tumor Ki67 image dataset, and the experiments demonstrate that our method outperforms recent state-of-the-art approaches. CONCLUSION: We present a new, pixel-to-pixel deep neural network with two sibling branches for effective nucleus recognition and observe that learning with another relevant task, ROI extraction, can further boost individual nucleus localization and classification. SIGNIFICANCE: Our method provides a clean, single-stage nucleus recognition pipeline for histopathology image analysis, especially a new perspective for Ki67 image quantification, which would potentially benefit individual object quantification in whole-slide images.

A high-throughput method for unbiased quantitation and categorization of nuclear morphology†.

The physical arrangement of chromatin in the nucleus is cell type and species-specific, a fact particularly evident in sperm, in which most of the cytoplasm has been lost. Analysis of the characteristic falciform ("hook shaped") sperm in mice is important in studies of sperm development, hybrid sterility, infertility, and toxicology. However, quantification of sperm shape differences typically relies on subjective manual assessment, rendering comparisons within and between samples difficult. We have developed an analysis program for morphometric analysis of asymmetric nuclei and characterized the sperm of mice from a range of inbred, outbred, and wild-derived mouse strains. We find that laboratory strains have elevated sperm shape variability both within and between samples in comparison to wild-derived inbred strains, and that sperm shape in F1 offspring from a cross between CBA and C57Bl6J strains is subtly affected by the direction of the cross. We further show that hierarchical clustering can discriminate distinct sperm shapes with greater efficiency and reproducibility than even experienced manual assessors, and is useful both to distinguish between samples and also to identify different morphological classes within a single sample. Our approach allows for the analysis of nuclear shape with unprecedented precision and scale and will be widely applicable to different species and different areas of biology.

Sparse Representation Over Learned Dictionaries on the Riemannian Manifold for Automated Grading of Nuclear Pleomorphism in Breast Cancer.

Breast cancer is found to be the most pervasive type of cancer among women. Computer aided detection and diagnosis of cancer at the initial stages can increase the chances of recovery and thus reduce the mortality rate through timely prognosis and adequate treatment planning. The nuclear atypia scoring or histopathological breast tumor grading remains to be a challenging problem due to the various artifacts and variabilities introduced during slide preparation and also because of the complexity in the structure of the underlying tissue patterns. Inspired by the success of symmetric positive definite (SPD) matrices in many of the challenging tasks in machine learning and computer vision, a sparse coding and dictionary learning on SPD matrices is proposed in this paper for the breast tumor grading. The proposed covariance-based SPD matrices form a Riemannian manifold and are represented as the sparse combination of Riemannian dictionary atoms. Non-linearity of the SPD manifold is tackled by embedding into the reproducing kernel Hilbert space using kernels derived from log-Euclidean metric, Jeffrey and Stein divergences and compared with the non-kernel-based affine invariant Riemannian metric. The novelty of the work lies in exploiting the kernel approach for the Hilbert space embedding of the Riemannian manifold, that can achieve a better discrimination of the breast cancer tissues, following a sparse representation over learned dictionaries and henceforth it outperforms many of the state-of-the-art algorithms in breast cancer grading in terms of quantitative and qualitative analysis.

Fast unsupervised nuclear segmentation and classification scheme for automatic allred cancer scoring in immunohistochemical breast tissue images.

BACKGROUND AND OBJECTIVE: This paper presents an improved scheme able to perform accurate segmentation and classification of cancer nuclei in immunohistochemical (IHC) breast tissue images in order to provide quantitative evaluation of estrogen or progesterone (ER/PR) receptor status that will assist pathologists in cancer diagnostic process. METHODS: The proposed segmentation method is based on adaptive local thresholding and an enhanced morphological procedure, which are applied to extract all stained nuclei regions and to split overlapping nuclei. In fact, a new segmentation approach is presented here for cell nuclei detection from the IHC image using a modified Laplacian filter and an improved watershed algorithm. Stromal cells are then removed from the segmented image using an adaptive criterion in order to get fast tumor nuclei recognition. Finally, unsupervised classification of cancer nuclei is obtained by the combination of four common color separation techniques for a subsequent Allred cancer scoring. RESULTS: Experimental results on various IHC tissue images of different cancer affected patients, demonstrate the effectiveness of the proposed scheme when compared to the manual scoring of pathological experts. A statistical analysis is performed on the whole image database between immuno-score of manual and automatic method, and compared with the scores that have reached using other state-of-art segmentation and classification strategies. According to the performance evaluation, we recorded more than 98% for both accuracy of detected nuclei and image cancer scoring over the truths provided by experienced pathologists which shows the best correlation with the expert's score (Pearson's correlation coefficient = 0.993, p-value < 0.005) and the lowest computational total time of 72.3 s/image (±1.9) compared to recent studied methods. CONCLUSIONS: The proposed scheme can be easily applied for any histopathological diagnostic process that needs stained nuclear quantification and cancer grading. Moreover, the reduced processing time and manual interactions of our procedure can facilitate its implementation in a real-time device to construct a fully online evaluation system of IHC tissue images.

Development of a Robust Algorithm for Detection of Nuclei and Classification of White Blood Cells in Peripheral Blood Smear Images.

Peripheral Blood Smear analysis plays a vital role in diagnosis of many diseases such as leukemia, anemia, malaria, lymphoma and infections. Unusual variations in color, shape and size of blood cells indicate abnormal condition. We used a total of 117 images from Leishman stained peripheral blood smears acquired at a magnification of 100X. In this paper we present a robust image processing algorithm for detection of nuclei and classification of white blood cells based on features of the nuclei. We used novel image enhancement method to manage illumination variations and TissueQuant method to manage color variations for the detection of nuclei. Dice similarity coefficient of 0.95 was obtained for nucleus detection. We also compared the proposed method with a state-of-the-art method and the proposed method was found to be better. Shape and texture features of the detected nuclei were used for classifying white blood cells. We considered classification of WBCs using two approaches such as 5-class and cell-by-cell approaches using neural network and hybrid-classifier respectively. We compared the results of both the approaches for classification of white blood cells. Cell-by-cell approach offered 1.4% higher sensitivity in comparison with the 5-class approach. We obtained an accuracy of 100% for lymphocyte and basophil detection. Hence, we conclude that lymphocytes and basophils can be accurately detected even when the analysis is limited to the features of nuclei whereas, accurate detection of other types of WBCs will require analysis of the cytoplasm too.

Her2Net: A Deep Framework for Semantic Segmentation and Classification of Cell Membranes and Nuclei in Breast Cancer Evaluation.

We present an efficient deep learning framework for identifying, segmenting, and classifying cell membranes and nuclei from human epidermal growth factor receptor-2 (HER2)-stained breast cancer images with minimal user intervention. This is a long-standing issue for pathologists because the manual quantification of HER2 is error-prone, costly, and time-consuming. Hence, we propose a deep learning-based HER2 deep neural network (Her2Net) to solve this issue. The convolutional and deconvolutional parts of the proposed Her2Net framework consisted mainly of multiple convolution layers, max-pooling layers, spatial pyramid pooling layers, deconvolution layers, up-sampling layers, and trapezoidal long short-term memory (TLSTM). A fully connected layer and a softmax layer were also used for classification and error estimation. Finally, HER2 scores were calculated based on the classification results. The main contribution of our proposed Her2Net framework includes the implementation of TLSTM and a deep learning framework for cell membrane and nucleus detection, segmentation, and classification and HER2 scoring. Our proposed Her2Net achieved 96.64% precision, 96.79% recall, 96.71% F-score, 93.08% negative predictive value, 98.33% accuracy, and a 6.84% false-positive rate. Our results demonstrate the high accuracy and wide applicability of the proposed Her2Net in the context of HER2 scoring for breast cancer evaluation.

Breast cancer cell nuclei classification in histopathology images using deep neural networks.

PURPOSE: Cell nuclei classification in breast cancer histopathology images plays an important role in effective diagnose since breast cancer can often be characterized by its expression in cell nuclei. However, due to the small and variant sizes of cell nuclei, and heavy noise in histopathology images, traditional machine learning methods cannot achieve desirable recognition accuracy. To address this challenge, this paper aims to present a novel deep neural network which performs representation learning and cell nuclei recognition in an end-to-end manner. METHODS: The proposed model hierarchically maps raw medical images into a latent space in which robustness is achieved by employing a stacked denoising autoencoder. A supervised classifier is further developed to improve the discrimination of the model by maximizing inter-subject separability in the latent space. The proposed method involves a cascade model which jointly learns a set of nonlinear mappings and a classifier from the given raw medical images. Such an on-the-shelf learning strategy makes obtaining discriminative features possible, thus leading to better recognition performance. RESULTS: Extensive experiments with benign and malignant breast cancer datasets are conducted to verify the effectiveness of the proposed method. Better performance was obtained when compared with other feature extraction methods, and higher recognition rate was achieved when compared with other seven classification methods. CONCLUSIONS: We propose an end-to-end DNN model for cell nuclei and non-nuclei classification of histopathology images. It demonstrates that the proposed method can achieve promising performance in cell nuclei classification, and the proposed method is suitable for the cell nuclei classification task.

Brillouin flow cytometry for label-free mechanical phenotyping of the nucleus.

The mechanical properties of the nucleus are closely related to many cellular functions; thus, measuring nuclear mechanical properties is crucial to our understanding of cell biomechanics and could lead to intrinsic biophysical contrast mechanisms to classify cells. Although many technologies have been developed to characterize cell stiffness, they generally require contact with the cell and thus cannot provide direct information on nuclear mechanical properties. In this work, we developed a flow cytometry technique based on an all-optical measurement to measure nuclear mechanical properties by integrating Brillouin spectroscopy with microfluidics. Brillouin spectroscopy probes the mechanical properties of material via light scattering, so it is inherently label-free, non-contact, and non-invasive. Using a measuring beam spot of submicron size, we can measure several regions within each cell as they flow, which enables us to classify cell populations based on their nuclear mechanical signatures at a throughput of ∼200 cells per hour. We show that Brillouin cytometry has sufficient sensitivity to detect physiologically-relevant changes in nuclear stiffness by probing the effect of drug-induced chromatin decondensation.

Accurate Detection of Dysmorphic Nuclei Using Dynamic Programming and Supervised Classification.

A vast array of pathologies is typified by the presence of nuclei with an abnormal morphology. Dysmorphic nuclear phenotypes feature dramatic size changes or foldings, but also entail much subtler deviations such as nuclear protrusions called blebs. Due to their unpredictable size, shape and intensity, dysmorphic nuclei are often not accurately detected in standard image analysis routines. To enable accurate detection of dysmorphic nuclei in confocal and widefield fluorescence microscopy images, we have developed an automated segmentation algorithm, called Blebbed Nuclei Detector (BleND), which relies on two-pass thresholding for initial nuclear contour detection, and an optimal path finding algorithm, based on dynamic programming, for refining these contours. Using a robust error metric, we show that our method matches manual segmentation in terms of precision and outperforms state-of-the-art nuclear segmentation methods. Its high performance allowed for building and integrating a robust classifier that recognizes dysmorphic nuclei with an accuracy above 95%. The combined segmentation-classification routine is bound to facilitate nucleus-based diagnostics and enable real-time recognition of dysmorphic nuclei in intelligent microscopy workflows.

Phylogeny, hybridization, and life history evolution of Rhinogobius gobies in Japan, inferred from multiple nuclear gene sequences.

Rhinogobius fishes (Gobiidae) are distributed widely in East and Southeast Asia, and represent the most species-rich group of freshwater gobies with diversified life histories (i.e., amphidromous, fluvial, and lentic). To reveal their phylogenetic relationships and life history evolution patterns, we sequenced six nuclear and three mitochondrial DNA (mtDNA) loci from 18 species, mainly from the mainland of Japan and the Ryukyu Archipelago. Our phylogenetic tree based on nuclear genes resolved three major clades, including several distinct subclades. The mtDNA and nuclear DNA phylogenies showed large discordance, which strongly suggested mitochondrial introgression through large-scale interspecific hybridization in these regions. On the basis of the molecular dating using geological data as calibration points, the hybridization occurred in the early to middle Pleistocene. Reconstruction of the ancestral states of life history traits based on nuclear DNA phylogeny suggests that the evolutionary change from amphidromous to freshwater life, accompanied by egg size change, occurred independently in at least three lineages. One of these lineages showed two life history alterations, i.e., from amphidromous (small egg) to fluvial (large egg) to lentic (small egg). Although more inclusive analysis using species outside Japan should be further conducted, the present results suggest the importance of the life history evolution associated with high adaptability to freshwater environments in the remarkable species diversification in this group. Such life history divergences may have contributed to the development of reproductive isolation.

Uterine leiomyomas with bizarre nuclei: a clinicopathologic study of 59 cases.

Leiomyoma with bizarre nuclei (LM-BN) is an uncommon tumor with histologic features (mononucleated or multinucleated bizarre cells that may have a diffuse distribution, prominent nucleoli, and karyorrhectic nuclei that may mimic atypical mitoses) that often causes confusion with leiomyosarcoma. Fifty-nine LM-BNs were collected from our consultation files over the years 2000 to 2011. Features recorded included patient age, therapy, tumor size, border, gross appearance, density and distribution of BN, mitotic count, karyorrhectic nuclei, prominent nucleoli, cells with conspicuous dense eosinophilic cytoplasm (rhabdoid-like), vascular changes and type of vasculature, and presence of necrosis and its nature. Follow-up information was obtained for all patients. Patients ranged in age from 25 to 75 (average 45) years (11 patients between 25 and 35 y, 20 between 36 and 45 y, 22 between 46 and 55 y, and 6 between 56 and 75 y). Forty-two underwent hysterectomy and 17 myomectomy. For 51 tumors gross findings were known. Forty (78%) had a solid white and whorled cut surface and 11 (22%) a yellow appearance. Five (10%) neoplasms showed prominent cystic degeneration, and hemorrhage and/or necrosis was seen in 9 (18%). Forty-five LM-BNs had a pushing margin with the surrounding myometrium, whereas 1 showed irregular borders. Margins could not be ascertained in the slides available in 13 cases. Twenty-eight (48%), 19 (32%), and 12 (20%) LM-BN showed low, intermediate, and high BN density. Eighteen (30%) tumors showed diffuse, 26 (44%) showed multifocal, and 15 (26%) had focal BN distribution. Mitotic counts ranged from 0 to 7/10 high-power fields (HPF) (average 1 to 2/10 HPF). Thirty-seven (63%) had <2/10 HPF, 19 (32%) had 2 to 5 mitoses/10 HPF, and in 3 tumors (5%) mitotic counts were 6, 7, and 7/10 HPF (2 with focal and 1 with diffuse BN). All but 4 LM-BNs showed karyorrhectic nuclei, striking in 12 neoplasms, mimicking atypical mitoses. Nineteen (32%) LMs had prominent eosinophilic nucleoli surrounded by a clear halo. Ischemic necrosis was detected in 21 (36%) LM-BN. Rhabdoid-like cells were noted in 24 (41%) tumors. All patients had no evidence of recurrence, ranging from 1 to 13 years (overall average 6 y; in patients with myomectomy 6.3 y with a range of 2.6 to 11 y). Our results corroborate that LM-BN is associated with a favorable outcome even in those patients only treated by myomectomy and highlights that a conservative approach can be undertaken in these patients, as many of them are of reproductive age. Because of the favorable outcome, the term LM-BN is preferable to alternative terminology including "atypical leiomyoma."

Fluorescence-activated sorting of fixed nuclei: a general method for studying nuclei from specific cell populations that preserves post-translational modifications.

Long-lasting brain alterations that underlie learning and memory are triggered by synaptic activity. How activity can exert long-lasting effects on neurons is a major question in neuroscience. Signalling pathways from cytoplasm to nucleus and the resulting changes in transcription and epigenetic modifications are particularly relevant in this context. However, a major difficulty in their study comes from the cellular heterogeneity of brain tissue. A promising approach is to directly purify identified nuclei. Using mouse striatum we have developed a rapid and efficient method for isolating cell type-specific nuclei from fixed adult brain (fluorescence-activated sorting of fixed nuclei; FAST-FIN). Animals are quickly perfused with a formaldehyde fixative that stops enzymatic reactions and maintains the tissue in the state it was at the time of death, including nuclear localisation of soluble proteins such as GFP and differences in nuclear size between cell types. Tissue is subsequently dissociated with a Dounce homogeniser and nuclei prepared by centrifugation in an iodixanol density gradient. The purified fixed nuclei can then be immunostained with specific antibodies and analysed or sorted by flow cytometry. Simple criteria allow distinction of neurons and non-neuronal cells. Immunolabelling and transgenic mice that express fluorescent proteins can be used to identify specific cell populations, and the nuclei from these populations can be efficiently isolated, even rare cell types such as parvalbumin-expressing interneurons. FAST-FIN allows the preservation and study of dynamic and labile post-translational protein modifications. It should be applicable to other tissues and species, and allow study of DNA and its modifications.

Automatic leukocyte nucleus segmentation by intuitionistic fuzzy divergence based thresholding.

The paper proposes a robust approach to automatic segmentation of leukocyte's nucleus from microscopic blood smear images under normal as well as noisy environment by employing a new exponential intuitionistic fuzzy divergence based thresholding technique. The algorithm minimizes the divergence between the actual image and the ideally thresholded image to search for the final threshold. A new divergence formula based on exponential intuitionistic fuzzy entropy has been proposed. Further, to increase its noise handling capacity, a neighborhood-based membership function for the image pixels has been designed. The proposed scheme has been applied on 110 normal and 54 leukemia (chronic myelogenous leukemia) affected blood samples. The nucleus segmentation results have been validated by three expert hematologists. The algorithm achieves an average segmentation accuracy of 98.52% in noise-free environment. It beats the competitor algorithms in terms of several other metrics. The proposed scheme with neighborhood based membership function outperforms the competitor algorithms in terms of segmentation accuracy under noisy environment. It achieves 93.90% and 94.93% accuracies for Speckle and Gaussian noises, respectively. The average area under the ROC curves comes out to be 0.9514 in noisy conditions, which proves the robustness of the proposed algorithm.

Debris removal in Pap-smear images.

Since its introduction in the 1940s the Pap-smear test has helped reduce the incidence of cervical cancer dramatically in countries where regular screening is standard. The automation of this procedure is an open problem that has been ongoing for over fifty years without reaching satisfactory results. Existing systems are discouragingly expensive and yet they are only able to make a correct distinction between normal and abnormal samples in a fraction of cases. Therefore, they are limited to acting as support for the cytotechnicians as they perform their manual screening. The main reason for the current limitations is that the automated systems struggle to overcome the complexity of the cell structures. Samples are covered in artefacts such as blood cells, overlapping and folded cells, and bacteria, that hamper the segmentation processes and generate large number of suspicious objects. The classifiers designed to differentiate between normal cells and pre-cancerous cells produce unpredictable results when classifying artefacts. In this paper, we propose a sequential classification scheme focused on removing unwanted objects, debris, from an initial segmentation result, intended to be run before the actual normal/abnormal classifier. The method has been evaluated using three separate datasets obtained from cervical samples prepared using both the standard Pap-smear approach as well as the more recent liquid based cytology sample preparation technique. We show success in removing more than 99% of the debris without loosing more than around one percent of the epithelial cells detected by the segmentation process.

The nuclear apparatus and chromosomal DNA of the microsporidian Nosema antheraeae.

The microsporidian Nosema antheraeae is a pathogen of the Chinese oak silkmoth Antheraea pernyi, the molecular karyotype of which is still poorly understood. Here the diplokaryon of N. antheraeae strain NP-YY has been visualized both by fluorescence and electron microscopy. In addition, pulsed-field gel electrophoresis (PFGE) showed that the haploid genome of N. antheraeae is approximately 9.3-9.5 million base pairs organized into 15 chromosomal bands. The mean fluorescence intensity of N. antheraeae and Nosema bombycis DNA measured by flow cytometry confirmed that the genome size of these two species was congruent with measurements obtained by PFGE. These initial results on the chromosome organization of N. antheraeae provide a foundation for the comparative genomics of N. antheraeae with other species of Nosema.