RESUMEN
We present a combined report on the results of three editions of the Cell Tracking Challenge, an ongoing initiative aimed at promoting the development and objective evaluation of cell segmentation and tracking algorithms. With 21 participating algorithms and a data repository consisting of 13 data sets from various microscopy modalities, the challenge displays today's state-of-the-art methodology in the field. We analyzed the challenge results using performance measures for segmentation and tracking that rank all participating methods. We also analyzed the performance of all of the algorithms in terms of biological measures and practical usability. Although some methods scored high in all technical aspects, none obtained fully correct solutions. We found that methods that either take prior information into account using learning strategies or analyze cells in a global spatiotemporal video context performed better than other methods under the segmentation and tracking scenarios included in the challenge.
Asunto(s)
Algoritmos , Rastreo Celular/métodos , Interpretación de Imagen Asistida por Computador , Benchmarking , Línea Celular , HumanosRESUMEN
The integration of cell division in root growth and development requires mediation of developmental and physiological signals through regulation of cyclin-dependent kinase activity. Cells within the pericycle form de novo lateral root meristems, and D-type cyclins (CYCD), as regulators of the G1-to-S phase cell cycle transition, are anticipated to play a role. Here, we show that the D-type cyclin protein CYCD2;1 is nuclear in Arabidopsis thaliana root cells, with the highest concentration in apical and lateral meristems. Loss of CYCD2;1 has a marginal effect on unstimulated lateral root density, but CYCD2;1 is rate-limiting for the response to low levels of exogenous auxin. However, while CYCD2;1 expression requires sucrose, it does not respond to auxin. The protein Inhibitor-Interactor of CDK/Kip Related Protein2 (ICK2/KRP2), which interacts with CYCD2;1, inhibits lateral root formation, and ick2/krp2 mutants show increased lateral root density. ICK2/KRP2 can modulate the nuclear levels of CYCD2;1, and since auxin reduces ICK2/KRP2 protein levels, it affects both activity and cellular distribution of CYCD2;1. Hence, as ICK2/KRP2 levels decrease, the increase in lateral root density depends on CYCD2;1, irrespective of ICK2/CYCD2;1 nuclear localization. We propose that ICK2/KRP2 restrains root ramification by maintaining CYCD2;1 inactive and that this modulates pericycle responses to auxin fluctuations.
Asunto(s)
Proteínas de Arabidopsis/metabolismo , Arabidopsis/genética , Proteínas de Ciclo Celular/metabolismo , Ciclinas/metabolismo , Ácidos Indolacéticos/farmacología , Raíces de Plantas/crecimiento & desarrollo , Arabidopsis/crecimiento & desarrollo , Arabidopsis/metabolismo , Proteínas de Arabidopsis/genética , Ciclo Celular , Proteínas de Ciclo Celular/genética , Núcleo Celular/genética , Ciclinas/genética , Regulación de la Expresión Génica de las Plantas , Mutación , Raíces de Plantas/genética , Raíces de Plantas/metabolismo , Complejo de la Endopetidasa Proteasomal/metabolismoRESUMEN
Electrocoagulation is a promising technology to harvest microalgal biomass. However, the commonly used aluminum electrodes release undesired salts that decrease biomass value. In this study, alternative iron, zinc, and magnesium electrodes and operational parameters pH, time and current density were studied to harvest Nannochloropsis oceanica. For recovery efficiency and concentration factor the initial pH was most important using iron electrodes, while time and current density were more relevant using zinc and magnesium electrodes. Optimal parameters resulted in biomass recovery efficiencies > 95%, biomass was concentrated 2.8-7.2 times and contained 15.7-29.1% ashes. Elemental analysis revealed metal salts in harvested biomass resulting from electrode corrosion. Finally, ash contents could be reduced by 65% using EDTA as a chelating agent. The electrocoagulation harvested microalgal biomass enriched in essential metals may be a promising bioresource for agricultural growth inducers, or functional ingredients for feed.
Asunto(s)
Microalgas , Aluminio , Biomasa , Electrocoagulación , ElectrodosRESUMEN
Biomass harvesting is one of the most expensive steps of the whole microalgal production pipeline. Therefore, the present work aimed to understand the effect of salinity on the growth performance, biochemical composition and sedimentation velocity of Tetraselmis sp. CTP4, in order to establish an effective low-cost pilot-scale harvesting system for this strain. At lab scale, similar growth performance was obtained in cultures grown at salinities of 5, 10 and 20 g L-1 NaCl. In addition, identical settling velocities (2.4-3.6 cm h-1) were observed on all salinities under study, regardless of the growth stage. However, higher salinities (20 g L-1) promoted a significant increase in lipid contents in this strain compared to when this microalga was cultivated at 5 or 10 g L-1 NaCl. At pilot-scale, cultures were cultivated semi-continuously in 2.5-m3 tubular photobioreactors, fed every four days, and stored in a 1-m3 harvesting tank. Upon a 24-hour settling step, natural sedimentation of the microalgal cells resulted in the removal of 93% of the culture medium in the form of a clear liquid containing only vestigial amounts of biomass (0.07 ± 0.02 g L-1 dry weight; DW). The remaining culture was recovered as a highly concentrated culture (19.53 ± 4.83 g L-1 DW) and wet microalgal paste (272.7 ± 18.5 g L-1 DW). Overall, this method provided an effective recovery of 97% of the total biomass, decreasing significantly the harvesting costs.
RESUMEN
BACKGROUND AND OBJECTIVE: Surface topography of biomaterials has been shown to have an effect on cells behaviour. Cell-material interactions can be visually characterized by assessing both cell shape and spreading at initial time-points and, its migration patterns, as a response to the underlying topography. Whilst many have reported the study of cell migration and shape with fluorescence labelling, the focus on evaluating cells response to surface topography is to observe, under real-time conditions, interactions between cells and surfaces. In this manuscript we present a novel approach to automatically detect and remove periodic background patterns in brightfield microscopy images in order to perform automatic cell mobility analysis. METHODS: The developed software, MobilityAnalyser, performs automatic tracking of unmarked cells and allows the user to manually correct any incorrectly detected or tracked cell. Human Mesenchymal Stem Cells (hMSCs) trajectory, migration distance, velocity and persistence were evaluated over line and pillar micropatterned SiO2 films and on a flat SiO2 control substrate. RESULTS: The developed software proved to be effective in automatically removing background patterns of both line and pillar shapes and in performing cell detection and tracking. MobilityAnalyser accurately measured cell mobility in a fraction of the time required for manual analysis and eliminated user subjectivity. The results obtained with the software confirmed how different topographies affect cell trajectory, migration pathways and velocities, with a statistically significant increase for micropatterned surfaces, when compared with the flat control. The persistence parameter also proved the influence of both patterns on the directionality of cell movement. CONCLUSIONS: MobilityAnalyser is an automatic tool that removes periodic background patterns, detects and tracks cells, and provides cell mobility parameters that characterize the response of cells to different surface topographies. The software is freely available at: https://drive.google.com/open?id=1Fbb321ogLD19SlRjceMETNUqDHgpeBPl.
Asunto(s)
Movimiento Celular , Procesamiento de Imagen Asistido por Computador/métodos , Células Madre Mesenquimatosas/citología , Reconocimiento de Normas Patrones Automatizadas/métodos , Materiales Biocompatibles , Forma de la Célula , Bases de Datos Genéticas , Humanos , Microscopía , Transición de Fase , Dióxido de Silicio/química , Programas InformáticosRESUMEN
This paper presents a novel approach for visual scene modeling and classification, investigating the combined use of text modeling methods and local invariant features. Our work attempts to elucidate (1) whether a text-like bag-of-visterms representation (histogram of quantized local visual features) is suitable for scene (rather than object) classification, (2) whether some analogies between discrete scene representations and text documents exist, and (3) whether unsupervised, latent space models can be used both as feature extractors for the classification task and to discover patterns of visual co-occurrence. Using several data sets, we validate our approach, presenting and discussing experiments on each of these issues. We first show, with extensive experiments on binary and multi-class scene classification tasks using a 9,500-image data set, that the bag-of-visterms representation consistently outperforms classical scene classification approaches. In other data sets we show that our approach competes with or outperforms other recent, more complex, methods. We also show that Probabilistic Latent Semantic Analysis (PLSA) generates a compact scene representation, discriminative for accurate classification, and more robust than the bag-of-visterms representation when less labeled training data is available. Finally, through aspect-based image ranking experiments, we show the ability of PLSA to automatically extract visually meaningful scene patterns, making such representation useful for browsing image collections.
Asunto(s)
Algoritmos , Inteligencia Artificial , Bases de Datos Factuales , Interpretación de Imagen Asistida por Computador/métodos , Almacenamiento y Recuperación de la Información/métodos , Reconocimiento de Normas Patrones Automatizadas/métodos , Aumento de la Imagen/métodos , Procesamiento de Lenguaje Natural , Reproducibilidad de los Resultados , Sensibilidad y EspecificidadRESUMEN
In an attempt to improve the efficacy of neural stem/progenitor cell (NSPC) based therapies, fibrin hydrogels are being explored to provide a favourable microenvironment for cell survival and differentiation following transplantation. In the present work, the ability of fibrin to support the survival, proliferation, and neuronal differentiation of NSPCs derived from embryonic stem (ES) cells under monolayer culture was explored. Single mouse ES-NSPCs were cultured within fibrin (fibrinogen concentration: 6 mg/ml) under neuronal differentiation conditions up to 14 days. The ES-NSPCs retained high cell viability and proliferated within small-sized spheroids. Neuronal differentiation was confirmed by an increase in the levels of ßIII-tubulin and NF200 over time. At day 14, cell-matrix constructs mainly comprised NSPCs and neurons (46.5% ßIII-tubulin+ cells). Gamma-aminobutyric acid (GABA)ergic and dopaminergic/noradrenergic neurons were also observed, along with a network of synaptic proteins. The ES-NSPCs expressed matriptase and secreted MMP-2/9, with MMP-2 activity increasing along time. Fibronectin, laminin and collagen type IV deposition was also detected. Fibrin gels prepared with higher fibrinogen concentrations (8/10 mg/ml) were less permissive to neurite extension and neuronal differentiation, possibly owing to their smaller pore area and higher rigidity. Overall, it is shown that ES-NSPCs within fibrin are able to establish neuronal networks and to remodel fibrin through MMP secretion and extracellular matrix (ECM) deposition. This three-dimensional (3D) culture system was also shown to support cell viability, neuronal differentiation and ECM deposition of human ES-NSPCs. The settled 3D platform is expected to constitute a valuable tool to develop fibrin-based hydrogels for ES-NSPC delivery into the injured central nervous system. Copyright © 2016 John Wiley & Sons, Ltd.
Asunto(s)
Técnicas de Cultivo de Célula/métodos , Células Madre Embrionarias/citología , Matriz Extracelular/metabolismo , Fibrina/farmacología , Hidrogeles/farmacología , Red Nerviosa/fisiología , Células-Madre Neurales/citología , Animales , Recuento de Células , Línea Celular , Proliferación Celular/efectos de los fármacos , Supervivencia Celular/efectos de los fármacos , Células Cultivadas , Células Madre Embrionarias/efectos de los fármacos , Células Madre Embrionarias/metabolismo , Matriz Extracelular/efectos de los fármacos , Geles , Humanos , Metaloproteinasas de la Matriz/metabolismo , Ratones , Red Nerviosa/efectos de los fármacos , Células-Madre Neurales/efectos de los fármacos , Células-Madre Neurales/metabolismo , Fenotipo , Serina Endopeptidasas/metabolismoRESUMEN
Embryonic stem (ES)-derived neural stem/progenitor cells (ES-NSPCs) constitute a promising cell source for application in cell therapies for the treatment of central nervous system disorders. In this study, a rotary orbital hydrodynamic culture system was applied to single-cell suspensions of ES-NSPCs, to obtain homogeneously-sized ES-NSPC cellular aggregates (neurospheres). Hydrodynamic culture allowed the formation of ES-NSPC neurospheres with a narrower size distribution than statically cultured neurospheres, increasing orbital speeds leading to smaller-sized neurospheres and higher neurosphere yield. Neurospheres formed under hydrodynamic conditions (72 h at 55 rpm) showed higher cell compaction and comparable percentages of viable, dead, apoptotic and proliferative cells. Further characterization of cellular aggregates provided new insights into the effect of hydrodynamic shear on ES-NSPC behaviour. Rotary neurospheres exhibited reduced protein levels of N-cadherin and ß-catenin, and higher deposition of laminin (without impacting fibronectin deposition), matrix metalloproteinase-2 (MMP-2) activity and percentage of neuronal cells. In line with the increased MMP-2 activity levels found, hydrodynamically-cultured neurospheres showed higher outward migration on laminin. Moreover, when cultured in a 3D fibrin hydrogel, rotary neurospheres generated an increased percentage of neuronal cells. In conclusion, the application of a constant orbital speed to single-cell suspensions of ES-NSPCs, besides allowing the formation of homogeneously-sized neurospheres, promoted ES-NSPC differentiation and outward migration, possibly by influencing the expression of cell-cell adhesion molecules and the secretion of proteases/extracellular matrix proteins. These findings are important when establishing the culture conditions needed to obtain uniformly-sized ES-NSPC aggregates, either for use in regenerative therapies or in in vitro platforms for biomaterial development or pharmacological screening. Copyright © 2016 John Wiley & Sons, Ltd.
Asunto(s)
Técnicas de Cultivo de Célula/métodos , Hidrodinámica , Células Madre Embrionarias de Ratones , Células-Madre Neurales , Esferoides Celulares , Animales , Técnicas de Cultivo de Célula/instrumentación , Línea Celular , Ratones , Células Madre Embrionarias de Ratones/citología , Células Madre Embrionarias de Ratones/metabolismo , Células-Madre Neurales/citología , Células-Madre Neurales/metabolismo , Esferoides Celulares/citología , Esferoides Celulares/metabolismoRESUMEN
To enhance fibrin hydrogel affinity towards pluripotent stem cell-derived neural stem/progenitor cells (NSPCs) and its capacity to support NSPC migration and neurite extension, we explored the tethering of synthetic peptides engaging integrin α6ß1, a cell receptor enriched in NSPCs. Six α6ß1 integrin ligands were tested for their ability to support integrin α6ß1-mediated adhesion of embryonic stem cell-derived NSPCs (ES-NSPs) and sustain ES-NSPC viability, migration, and neuronal differentiation. Due to their better performance, peptides T1, HYD1, and A5G81 were immobilized into fibrin and functionalized gels characterized in terms of peptide binding efficiency, structure and viscoelastic properties. Tethering of T1 or HYD1 successfully enhanced cell outgrowth from ES-NSPC neurospheres (up to 2.4-fold increase), which exhibited a biphasic response to peptide concentration. Inhibition assays evidenced the involvement of α6ß1 and α3ß1 integrins in mediating radial outgrowth on T1-/HYD1-functionalized gels. Fibrin functionalization also promoted neurite extension of single ES-NSPCs in fibrin, without affecting cell proliferation and neuronal differentiation. Finally, HYD1-functionalized gels were found to provide a permissive environment for axonal regeneration, leading up to a 2.0-fold increase in neurite extension from rat dorsal root ganglia explants as compared to unmodified fibrin, and to significant improved locomotor function after spinal cord injury (complete transection), along with a trend toward a higher area positive for growth associated protein 43 (marker for axonal growth cone formation). Our results suggest that conjugation of α6ß1 integrin-binding motifs is of interest to increase the biofunctionality of hydrogels used in 3D platforms for ES-NSPC culture and potentially, in matrix-assisted ES-NSPC transplantation. STATEMENT OF SIGNIFICANCE: Impact statement: The transplantation of NSPCs derived from pluripotent stem cells holds much promise for the treatment of central nervous system disorders. Moreover, the combinatorial use of biodegradable hydrogels with NSPCs was shown to contribute to the establishment of a more permissive environment for survival and integration of transplanted cells. In this study, fibrin hydrogels functionalized with a synthetic peptide engaging integrin α6ß1 (HYD1) were shown to promote neurite extension of ES-NSPCs, which is fundamental for the formation of functional neuronal relay circuits after NSPC transplantation. Notably, HYD1-functionalized fibrin per se led to enhanced axonal growth ex vivo and to an improvement in locomotor function after implantation in a rat model of spinal cord injury. Conjugation of α6ß1 integrin-binding motifs may therefore be of interest to confer bioactivity to NSPC hydrogel vehicles.
Asunto(s)
Células Madre Embrionarias/metabolismo , Fibrina/química , Integrina alfa6beta1/metabolismo , Células-Madre Neurales/metabolismo , Neuritas/metabolismo , Animales , Línea Celular Tumoral , Células Madre Embrionarias/citología , Humanos , Ligandos , Ratones , Células-Madre Neurales/citología , Ratas , Ratas WistarRESUMEN
BACKGROUND: Blood and lymph vessel invasion are well-recognized markers of tumor aggressiveness, as these are the routes that lead to metastases. Thyroid tumors, depending on the histological variant, tend to have distinctive biological behaviors and use different vascular routes to metastasize, yet the mechanisms underlying the metastatic process are still poorly understood. OBJECTIVES: The aim of this study was to assess how the lymph vessel density (LVD) in different histological types of thyroid tumors, and in their surrounding tissue, correlate with the presence of lymph node metastases (LNM) and tumor pathological features. METHODS: Lymph vessels of papillary thyroid carcinomas (PTC), of the classical (CVPTC, n = 50) and follicular variants (FVPTC, n = 18), and medullary thyroid carcinomas (MTC, n = 34) were immunohistochemically stained against antigen D2-40. The stained area was quantified using a computerized morphometric analysis tool and correlated with the tumor pathological characteristics. RESULTS: LVD within all analyzed thyroid tumor subtypes was significantly lower than in the surrounding thyroid tissues (p < 0.001). Despite intratumoral LVD being significantly higher in CVPTC than in FVPTC, and peritumoral LVD being significantly higher in MTC than in PTC (p < 0.05), no correlations were found between LVD (either intratumoral or peritumoral) and the presence of lymph node metastasis. CONCLUSIONS: As no LVD differences were found amongst thyroid tumors with or without LNM, dissemination is more likely to depend on the tumor ability to invade the abundant lymph vessel network of the surrounding thyroid tissue than on the ability of the tumor to promote de novo lymphangiogenesis.
RESUMEN
Despite the importance of immune cell-biomaterial interactions for the regenerative outcome, few studies have investigated how distinct three-dimensional biomaterials modulate the immune cell-mediated mesenchymal stem/stromal cells (MSC) recruitment and function. Thus, this work compares the response of varied primary human immune cell populations triggered by different model scaffolds and describes its functional consequence on recruitment and motility of bone marrow MSC. It was found that polylactic acid (PLA) and chitosan scaffolds lead to an increase in the metabolic activity of macrophages but not of peripheral blood mononuclear cells (PBMC), natural killer (NK) cells or monocytes. PBMC and NK cells increase their cell number in PLA scaffolds and express a secretion profile that does not promote MSC recruitment. Importantly, chitosan increases IL-8, MIP-1, MCP-1 and RANTES secretion by macrophages while PLA stimulates IL-6, IL-8 and MCP-1 production, all chemokines that can lead to MSC recruitment. This secretion profile of macrophages in contact with biomaterials correlates with the highest MSC invasion. Furthermore, macrophages enhance stem cell motility within chitosan scaffolds by 44% but not in PLA scaffolds. Thus, macrophages are the cells that in contact with engineered biomaterials become activated to secrete bioactive molecules that stimulate MSC recruitment.
Asunto(s)
Movimiento Celular/inmunología , Quitosano/química , Células Asesinas Naturales/inmunología , Macrófagos/inmunología , Células Madre Mesenquimatosas/inmunología , Monocitos/inmunología , Poliésteres/química , Andamios del Tejido/química , Citocinas/inmunología , Humanos , Ensayo de MaterialesRESUMEN
Cardiac therapies are commonly tested preclinically in small-animal models of myocardial infarction. Following functional evaluation, post-mortem histological analysis is essential to assess morphological and molecular alterations underlying the effectiveness of treatment. However, non-methodical and inadequate sampling of the left ventricle often leads to misinterpretations and variability, making direct study comparisons unreliable. Protocols are provided for representative sampling of the ischemic mouse heart followed by morphometric analysis of the left ventricle. Extending the use of this sampling to other types of in situ analysis is also illustrated through the assessment of neovascularization and cellular engraftment in a cell-based therapy setting. This is of interest to the general cardiovascular research community as it details methods for standardization and simplification of histo-morphometric evaluation of emergent heart therapies. © 2015 by John Wiley & Sons, Inc.
Asunto(s)
Corazón/fisiopatología , Infarto del Miocardio/fisiopatología , Animales , Modelos Animales de Enfermedad , RatonesRESUMEN
We propose an automated algorithm for classifying diagnostic categories of otitis media (middle ear inflammation); acute otitis media, otitis media with effusion and no effusion. Acute otitis media represents a bacterial superinfection of the middle ear fluid and otitis media with effusion a sterile effusion that tends to subside spontaneously. Diagnosing children with acute otitis media is hard, leading to overprescription of antibiotics that are beneficial only for children with acute otitis media, prompting a need for an accurate and automated algorithm. To that end, we design a feature set understood by both otoscopists and engineers based on the actual visual cues used by otoscopists; we term this otitis media vocabulary. We also design a process to combine the vocabulary terms based on the decision process used by otoscopists; we term this otitis media grammar. The algorithm achieves 84% classification accuracy, in the range or outperforming clinicians who did not receive special training, as well as state-of-the-art classifiers.
RESUMEN
BACKGROUND: The cardiac regenerative potential of newly developed therapies is traditionally evaluated in rodent models of surgically induced myocardial ischemia. A generally accepted key parameter for determining the success of the applied therapy is the infarct size. Although regarded as a gold standard method for infarct size estimation in heart ischemia, histological planimetry is time-consuming and highly variable amongst studies. The purpose of this work is to contribute towards the standardization and simplification of infarct size assessment by providing free access to a novel semi-automated software tool. The acronym MIQuant was attributed to this application. METHODOLOGY/PRINCIPAL FINDINGS: Mice were subject to permanent coronary artery ligation and the size of chronic infarcts was estimated by area and midline-length methods using manual planimetry and with MIQuant. Repeatability and reproducibility of MIQuant scores were verified. The validation showed high correlation (r(midline length)â=â0.981; r(area)â=â0.970 ) and agreement (Bland-Altman analysis), free from bias for midline length and negligible bias of 1.21% to 3.72% for area quantification. Further analysis demonstrated that MIQuant reduced by 4.5-fold the time spent on the analysis and, importantly, MIQuant effectiveness is independent of user proficiency. The results indicate that MIQuant can be regarded as a better alternative to manual measurement. CONCLUSIONS: We conclude that MIQuant is a reliable and an easy-to-use software for infarct size quantification. The widespread use of MIQuant will contribute towards the standardization of infarct size assessment across studies and, therefore, to the systematization of the evaluation of cardiac regenerative potential of emerging therapies.
Asunto(s)
Infarto del Miocardio/diagnóstico , Programas Informáticos , Animales , Femenino , Masculino , Ratones , Ratones Endogámicos C57BLRESUMEN
Microscopy cell image analysis is a fundamental tool for biological research. In particular, multivariate fluorescence microscopy is used to observe different aspects of cells in cultures. It is still common practice to perform analysis tasks by visual inspection of individual cells which is time consuming, exhausting and prone to induce subjective bias. This makes automatic cell image analysis essential for large scale, objective studies of cell cultures. Traditionally the task of automatic cell analysis is approached through the use of image segmentation methods for extraction of cells' locations and shapes. Image segmentation, although fundamental, is neither an easy task in computer vision nor is it robust to image quality changes. This makes image segmentation for cell detection semi-automated requiring frequent tuning of parameters. We introduce a new approach for cell detection and shape estimation in multivariate images based on the sliding band filter (SBF). This filter's design makes it adequate to detect overall convex shapes and as such it performs well for cell detection. Furthermore, the parameters involved are intuitive as they are directly related to the expected cell size. Using the SBF filter we detect cells' nucleus and cytoplasm location and shapes. Based on the assumption that each cell has the same approximate shape center in both nuclei and cytoplasm fluorescence channels, we guide cytoplasm shape estimation by the nuclear detections improving performance and reducing errors. Then we validate cell detection by gathering evidence from nuclei and cytoplasm channels. Additionally, we include overlap correction and shape regularization steps which further improve the estimated cell shapes. The approach is evaluated using two datasets with different types of data: a 20 images benchmark set of simulated cell culture images, containing 1000 simulated cells; a 16 images Drosophila melanogaster Kc167 dataset containing 1255 cells, stained for DNA and actin. Both image datasets present a difficult problem due to the high variability of cell shapes and frequent cluster overlap between cells. On the Drosophila dataset our approach achieved a precision/recall of 95%/69% and 82%/90% for nuclei and cytoplasm detection respectively and an overall accuracy of 76%.
Asunto(s)
Núcleo Celular/ultraestructura , Citoplasma/ultraestructura , Procesamiento de Imagen Asistido por Computador/métodos , Microscopía Fluorescente/métodos , Actinas/química , Animales , Agregación Celular , Núcleo Celular/química , Forma de la Célula , Citoplasma/química , ADN/química , Bases de Datos Factuales , Drosophila melanogaster , Análisis Multivariante , Reproducibilidad de los ResultadosRESUMEN
To obtain development information of individual plant cells, it is necessary to perform in vivo imaging of the specimen under study, through time-lapse confocal microscopy. Automation of cell detection/marking process is important to provide research tools in order to ease the search for special events, such as cell division. In this paper we discuss an automatic cell detection approach for Arabidopsis thaliana based on segmentation, which selects the best cell candidates from a starting watershed-based image segmentation and improves the result by merging adjacent regions. The selection of individual cells is obtained using a support vector machine (SVM) classifier, based on a cell descriptor constructed from the shape and edge strength of the cells' contour. In addition we proposed a novel cell merging criterion based on edge strength along the line that connects adjacent cells' centroids, which is a valuable tool in the reduction of cell over-segmentation. The result is largely pruned of badly segmented and over-segmented cells, thus facilitating the study of cells. When comparing the results after merging with the basic watershed segmentation, we obtain 1.5% better coverage (increase in F-measure) and up to 27% better precision in correct cell segmentation.