Inhaltsverzeichnis
Auswahl der wissenschaftlichen Literatur zum Thema „Automatic cell types annotation“
Geben Sie eine Quelle nach APA, MLA, Chicago, Harvard und anderen Zitierweisen an
Machen Sie sich mit den Listen der aktuellen Artikel, Bücher, Dissertationen, Berichten und anderer wissenschaftlichen Quellen zum Thema "Automatic cell types annotation" bekannt.
Neben jedem Werk im Literaturverzeichnis ist die Option "Zur Bibliographie hinzufügen" verfügbar. Nutzen Sie sie, wird Ihre bibliographische Angabe des gewählten Werkes nach der nötigen Zitierweise (APA, MLA, Harvard, Chicago, Vancouver usw.) automatisch gestaltet.
Sie können auch den vollen Text der wissenschaftlichen Publikation im PDF-Format herunterladen und eine Online-Annotation der Arbeit lesen, wenn die relevanten Parameter in den Metadaten verfügbar sind.
Zeitschriftenartikel zum Thema "Automatic cell types annotation"
1
Shao, Xin, Jie Liao, Xiaoyan Lu, Rui Xue, Ni Ai und Xiaohui Fan. „scCATCH: Automatic Annotation on Cell Types of Clusters from Single-Cell RNA Sequencing Data“. iScience 23, Nr. 3 (März 2020): 100882. http://dx.doi.org/10.1016/j.isci.2020.100882.
Der volle Inhalt der Quelle
2
Doddahonnaiah, Deeksha, Patrick J. Lenehan, Travis K. Hughes, David Zemmour, Enrique Garcia-Rivera, A. J. Venkatakrishnan, Ramakrishna Chilaka et al. „A Literature-Derived Knowledge Graph Augments the Interpretation of Single Cell RNA-seq Datasets“. Genes 12, Nr. 6 (10.06.2021): 898. http://dx.doi.org/10.3390/genes12060898.
Der volle Inhalt der QuelleAnnotation:
Technology to generate single cell RNA-sequencing (scRNA-seq) datasets and tools to annotate them have advanced rapidly in the past several years. Such tools generally rely on existing transcriptomic datasets or curated databases of cell type defining genes, while the application of scalable natural language processing (NLP) methods to enhance analysis workflows has not been adequately explored. Here we deployed an NLP framework to objectively quantify associations between a comprehensive set of over 20,000 human protein-coding genes and over 500 cell type terms across over 26 million biomedical documents. The resultant gene-cell type associations (GCAs) are significantly stronger between a curated set of matched cell type-marker pairs than the complementary set of mismatched pairs (Mann Whitney p = 6.15 × 10−76, r = 0.24; cohen’s D = 2.6). Building on this, we developed an augmented annotation algorithm (single cell Annotation via Literature Encoding, or scALE) that leverages GCAs to categorize cell clusters identified in scRNA-seq datasets, and we tested its ability to predict the cellular identity of 133 clusters from nine datasets of human breast, colon, heart, joint, ovary, prostate, skin, and small intestine tissues. With the optimized settings, the true cellular identity matched the top prediction in 59% of tested clusters and was present among the top five predictions for 91% of clusters. scALE slightly outperformed an existing method for reference data driven automated cluster annotation, and we demonstrate that integration of scALE can meaningfully improve the annotations derived from such methods. Further, contextualization of differential expression analyses with these GCAs highlights poorly characterized markers of well-studied cell types, such as CLIC6 and DNASE1L3 in retinal pigment epithelial cells and endothelial cells, respectively. Taken together, this study illustrates for the first time how the systematic application of a literature-derived knowledge graph can expedite and enhance the annotation and interpretation of scRNA-seq data.
3
Pham, Son, Tri Le, Tan Phan, Minh Pham, Huy Nguyen, Loc Lam, Nam Phung et al. „484 Bioturing browser: interactively explore public single cell sequencing data“. Journal for ImmunoTherapy of Cancer 8, Suppl 3 (November 2020): A520. http://dx.doi.org/10.1136/jitc-2020-sitc2020.0484.
Der volle Inhalt der QuelleAnnotation:
BackgroundSingle-cell sequencing technology has opened an unprecedented ability to interrogate cancer. It reveals significant insights into the intratumoral heterogeneity, metastasis, therapeutic resistance, which facilitates target discovery and validation in cancer treatment. With rapid advancements in throughput and strategies, a particular immuno-oncology study can produce multi-omics profiles for several thousands of individual cells. This overflow of single-cell data poses formidable challenges, including standardizing data formats across studies, performing reanalysis for individual datasets and meta-analysis.MethodsN/AResultsWe present BioTuring Browser, an interactive platform for accessing and reanalyzing published single-cell omics data. The platform is currently hosting a curated database of more than 10 million cells from 247 projects, covering more than 120 immune cell types and subtypes, and 15 different cancer types. All data are processed and annotated with standardized labels of cell types, diseases, therapeutic responses, etc. to be instantly accessed and explored in a uniform visualization and analytics interface. Based on this massive curated database, BioTuring Browser supports searching similar expression profiles, querying a target across datasets and automatic cell type annotation. The platform supports single-cell RNA-seq, CITE-seq and TCR-seq data. BioTuring Browser is now available for download at www.bioturing.com.ConclusionsN/A
4
Lian, Qiuyu, Hongyi Xin, Jianzhu Ma, Liza Konnikova, Wei Chen, Jin Gu und Kong Chen. „Artificial-cell-type aware cell-type classification in CITE-seq“. Bioinformatics 36, Supplement_1 (01.07.2020): i542—i550. http://dx.doi.org/10.1093/bioinformatics/btaa467.
Der volle Inhalt der QuelleAnnotation:
Abstract Motivation Cellular Indexing of Transcriptomes and Epitopes by sequencing (CITE-seq), couples the measurement of surface marker proteins with simultaneous sequencing of mRNA at single cell level, which brings accurate cell surface phenotyping to single-cell transcriptomics. Unfortunately, multiplets in CITE-seq datasets create artificial cell types (ACT) and complicate the automation of cell surface phenotyping. Results We propose CITE-sort, an artificial-cell-type aware surface marker clustering method for CITE-seq. CITE-sort is aware of and is robust to multiplet-induced ACT. We benchmarked CITE-sort with real and simulated CITE-seq datasets and compared CITE-sort against canonical clustering methods. We show that CITE-sort produces the best clustering performance across the board. CITE-sort not only accurately identifies real biological cell types (BCT) but also consistently and reliably separates multiplet-induced artificial-cell-type droplet clusters from real BCT droplet clusters. In addition, CITE-sort organizes its clustering process with a binary tree, which facilitates easy interpretation and verification of its clustering result and simplifies cell-type annotation with domain knowledge in CITE-seq. Availability and implementation http://github.com/QiuyuLian/CITE-sort. Supplementary information Supplementary data is available at Bioinformatics online.
5
Patino, Cesar A., Prithvijit Mukherjee, Vincent Lemaitre, Nibir Pathak und Horacio D. Espinosa. „Deep Learning and Computer Vision Strategies for Automated Gene Editing with a Single-Cell Electroporation Platform“. SLAS TECHNOLOGY: Translating Life Sciences Innovation 26, Nr. 1 (15.01.2021): 26–36. http://dx.doi.org/10.1177/2472630320982320.
Der volle Inhalt der QuelleAnnotation:
Single-cell delivery platforms like microinjection and nanoprobe electroporation enable unparalleled control over cell manipulation tasks but are generally limited in throughput. Here, we present an automated single-cell electroporation system capable of automatically detecting cells with artificial intelligence (AI) software and delivering exogenous cargoes of different sizes with uniform dosage. We implemented a fully convolutional network (FCN) architecture to precisely locate the nuclei and cytosol of six cell types with various shapes and sizes, using phase contrast microscopy. Nuclear staining or reporter fluorescence was used along with phase contrast images of cells within the same field of view to facilitate the manual annotation process. Furthermore, we leveraged the near-human inference capabilities of the FCN network in detecting stained nuclei to automatically generate ground-truth labels of thousands of cells within seconds, and observed no statistically significant difference in performance compared to training with manual annotations. The average detection sensitivity and precision of the FCN network were 95±1.7% and 90±1.8%, respectively, outperforming a traditional image-processing algorithm (72±7.2% and 72±5.5%) used for comparison. To test the platform, we delivered fluorescent-labeled proteins into adhered cells and measured a delivery efficiency of 90%. As a demonstration, we used the automated single-cell electroporation platform to deliver Cas9–guide RNA (gRNA) complexes into an induced pluripotent stem cell (iPSC) line to knock out a green fluorescent protein–encoding gene in a population of ~200 cells. The results demonstrate that automated single-cell delivery is a useful cell manipulation tool for applications that demand throughput, control, and precision.
6
Balzategui, Julen, Luka Eciolaza und Daniel Maestro-Watson. „Anomaly Detection and Automatic Labeling for Solar Cell Quality Inspection Based on Generative Adversarial Network“. Sensors 21, Nr. 13 (25.06.2021): 4361. http://dx.doi.org/10.3390/s21134361.
Der volle Inhalt der QuelleAnnotation:
Quality inspection applications in industry are required to move towards a zero-defect manufacturing scenario, with non-destructive inspection and traceability of 100% of produced parts. Developing robust fault detection and classification models from the start-up of the lines is challenging due to the difficulty in getting enough representative samples of the faulty patterns and the need to manually label them. This work presents a methodology to develop a robust inspection system, targeting these peculiarities, in the context of solar cell manufacturing. The methodology is divided into two phases: In the first phase, an anomaly detection model based on a Generative Adversarial Network (GAN) is employed. This model enables the detection and localization of anomalous patterns within the solar cells from the beginning, using only non-defective samples for training and without any manual labeling involved. In a second stage, as defective samples arise, the detected anomalies will be used as automatically generated annotations for the supervised training of a Fully Convolutional Network that is capable of detecting multiple types of faults. The experimental results using 1873 Electroluminescence (EL) images of monocrystalline cells show that (a) the anomaly detection scheme can be used to start detecting features with very little available data, (b) the anomaly detection may serve as automatic labeling in order to train a supervised model, and (c) segmentation and classification results of supervised models trained with automatic labels are comparable to the ones obtained from the models trained with manual labels.
7
Friedmann, Drew, Albert Pun, Eliza L. Adams, Jan H. Lui, Justus M. Kebschull, Sophie M. Grutzner, Caitlin Castagnola, Marc Tessier-Lavigne und Liqun Luo. „Mapping mesoscale axonal projections in the mouse brain using a 3D convolutional network“. Proceedings of the National Academy of Sciences 117, Nr. 20 (01.05.2020): 11068–75. http://dx.doi.org/10.1073/pnas.1918465117.
Der volle Inhalt der QuelleAnnotation:
The projection targets of a neuronal population are a key feature of its anatomical characteristics. Historically, tissue sectioning, confocal microscopy, and manual scoring of specific regions of interest have been used to generate coarse summaries of mesoscale projectomes. We present here TrailMap, a three-dimensional (3D) convolutional network for extracting axonal projections from intact cleared mouse brains imaged by light-sheet microscopy. TrailMap allows region-based quantification of total axon content in large and complex 3D structures after registration to a standard reference atlas. The identification of axonal structures as thin as one voxel benefits from data augmentation but also requires a loss function that tolerates errors in annotation. A network trained with volumes of serotonergic axons in all major brain regions can be generalized to map and quantify axons from thalamocortical, deep cerebellar, and cortical projection neurons, validating transfer learning as a tool to adapt the model to novel categories of axonal morphology. Speed of training, ease of use, and accuracy improve over existing tools without a need for specialized computing hardware. Given the recent emphasis on genetically and functionally defining cell types in neural circuit analysis, TrailMap will facilitate automated extraction and quantification of axons from these specific cell types at the scale of the entire mouse brain, an essential component of deciphering their connectivity.
8
Mai, Yun, Kyeryoung Lee, Zongzhi Liu, Meng Ma, Christopher Gilman, Minghao Li, Mingwei Zhang et al. „Phenotyping of clinical trial eligibility text from cancer studies into computable criteria in electronic health records.“ Journal of Clinical Oncology 39, Nr. 15_suppl (20.05.2021): 6592. http://dx.doi.org/10.1200/jco.2021.39.15_suppl.6592.
Der volle Inhalt der QuelleAnnotation:
6592 Background: Clinical trial phenotyping is the process of extracting clinical features and patient characteristics from eligibility criteria. Phenotyping is a crucial step that precedes automated cohort identification from patient electronic health records (EHRs) against trial criteria. We establish a clinical trial phenotyping pipeline to transform clinical trial eligibility criteria into computable criteria and enable high throughput cohort selection in EHRs. Methods: Formalized clinical trial criteria attributes were acquired from a natural-language processing (NLP)-assisted approach. We implemented a clinical trial phenotyping pipeline that included three components: First, a rule-based knowledge engineering component was introduced to annotate the trial attributes into a computable and customizable granularity from EHRs. The second component involved normalizing annotated attributes using standard terminologies and pre-defined reference tables. Third, a knowledge base of computable criteria attributes was built to match patients to clinical trials. We evaluated the pipeline performance by independent manual review. The inter-rater agreement of the annotation was measured on a random sample of the knowledge base. The accuracy of the pipeline was evaluated on a subset of randomly selected matched patients for a subset of randomly selected attributes. Results: Our pipeline phenotyped 2954 clinical trials from five cancer types including Non-Small Cell Lung Cancer, Small Cell Lung Cancer, Prostate Cancer, Breast Cancer, and Multiple Myeloma. We built a knowledge base of 256 computable attributes that included comorbidities, comorbidity-related treatment, previous lines of therapy, laboratory tests, and performance such as ECOG and Karnofsky score. Among 256 attributes, 132 attributes were encoded using standard terminologies and 124 attributes were normalized to customized concepts. The inter-rater agreement of the annotation measured by Cohen’s Kappa coefficient was 0.83. We applied the knowledge base to our EHRs and efficiently identified 33258 potential subjects for cancer clinical trials. Our evaluation on the patient matching indicated the F1 score was 0.94. Conclusions: We established a clinical trial phenotyping pipeline and built a knowledge base of computable criteria attributes that enabled efficient screening of EHRs for patients meeting clinical trial eligibility criteria, providing an automated way to efficiently and accurately identify clinical trial cohorts. The application of this knowledge base to patient matching from EHR data across different institutes demonstrates its generalization capability. Taken together, this knowledge base will be particularly valuable in computer-assisted clinical trial subject selection and clinical trial protocol design in cancer studies based on real-world evidence.
9
Englbrecht, Fabian, Iris E. Ruider und Andreas R. Bausch. „Automatic image annotation for fluorescent cell nuclei segmentation“. PLOS ONE 16, Nr. 4 (16.04.2021): e0250093. http://dx.doi.org/10.1371/journal.pone.0250093.
Der volle Inhalt der QuelleAnnotation:
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.
10
Magidey, Ksenia, Ksenya Kveler, Rachelly Normand, Tongwu Zhang, Michael Timaner, Ziv Raviv, Brian James et al. „A Unique Crosstalk between Tumor Cells and Hematopoietic Stem Cells Reveals a Myeloid Differentiation Pattern Signature Contributing to Metastasis“. Blood 134, Supplement_1 (13.11.2019): 2465. http://dx.doi.org/10.1182/blood-2019-128126.
Der volle Inhalt der QuelleAnnotation:
Metastasis is the major cause of death in cancer patients. Recent studies have demonstrated that the crosstalk between different host and tumor cells in the tumor microenvironment regulates tumor progression and metastasis. Specifically, immune cell myeloid skewing is a prominent promoter of metastasis. While previous studies have demonstrated that the recruitment of myeloid cells to tumors is a critical step in dictating tumor fate, the reservoir of these cells in the bone marrow (BM) compartment and their differentiation pattern has not been explored. Here we utilized a unique model system consisting of tumor cell clones with low and high metastatic potential (met-low and met-high, respectively) derived from melanoma and breast carcinoma cell lines. Hematopoietic stem cells (HSCs) and their early progenitor subset were defined as Lin-/Sca1+/CD117+, representing LSK cells. BM transplantation experiments using GFP-positive LSK cells derived from met-low and met-high tumor bearing mice were carried out to study lineage differentiation. The genetic signatures of LSK cells were analyzed by single cell RNA-sequencing (scRNA-seq). This analysis included unbiased automated annotation of individual cell types by correlating single-cell gene expression with reference transcriptomic data sets (SingleR algorithm) in order to evaluate the proportions of cell types in BM and reveal cell type-specific differentially expressed genes. Expression patterns of proteins originated from tumor cells were analyzed using a range of multi-omics techniques including nanostring, protein array, and mass spectrometry analysis. Tumor proteomic data was integrated with differential receptor expression patterns in BM cell types to reveal novel crosstalk between tumor cells and HSCs in the BM compartment. Mice bearing met-high tumors exhibited a significant increase in the percentage of LSK cells in the BM in comparison to tumor-free mice or mice bearing met-low tumors. These results were confirmed by functional CFU assays of peripheral blood of met-high compared to met-low tumor bearing mice. In addition, mice that underwent BM transplantation with GFP-positive LSK cells obtained from met-high inoculated donors exhibited an increased percentage of circulating GFP-positive myeloid cells in comparison to counterpart mice transplanted with LSK cells from met-low inoculated donors. Moreover, scRNA-seq analysis of LSK cells obtained from the BM of met-low and met-high tumor bearing mice revealed that met-high tumors induce the enrichment of monocyte-dendritic progenitor population (MDP), confirmed also by flow cytometry. To uncover the possible factors involved in myeloid programming of LSK cells, we performed a proteomic screen of tumor conditioned medium and integrated the results with the scRNA-seq data analysis. This analysis revealed that the IL-6-IL-6R axis is highly active in LSK-derived MDP cells from mice bearing met-high tumors. An adoptive transfer experiment using MDP-GFP+ cells obtained from BM of met-high tumor bearing mice demonstrated that met-high tumors directly dictate HSC fate decision towards myeloid bias, resulting in increased metastasis. Evidently, blocking IL-6 in mice bearing met-high tumors reduced the number of MDP cells, and consequently decreased metastasis. Our study reveals a unique crosstalk between tumor cells and HSCs. It provides new insight into the mechanism by which tumors contribute to the presence of supporting stroma. Specifically, tumors secreting IL-6 dictate a specific genetic signature in HSCs that programs them towards myeloid differentiation, thereby inducing a metastatic switch. Disclosures No relevant conflicts of interest to declare.
Dissertationen zum Thema "Automatic cell types annotation"
1
Raoux, Corentin. „Review and Analysis of single-cell RNA sequencing cell-type identification and annotation tools“. Thesis, KTH, Skolan för kemi, bioteknologi och hälsa (CBH), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-297852.
Der volle Inhalt der QuelleAnnotation:
Single-cell RNA-sequencing makes possible to study the gene expression at the level of individual cells. However, one of the main challenges of the single-cell RNA-sequencing analysis today, is the identification and annotation of cell types. The current method consists in manually checking the expression of genes using top differentially expressed genes and comparing them with related cell-type markers available in scientific publications. It is therefore time-consuming and labour intensive. Nevertheless, in the last two years,numerous automatic cell-type identification and annotation tools which use different strategies have been created. But, the lack of specific comparisons of those tools in the literature and especially for immuno-oncologic and oncologic purposes makes difficult for laboratories and companies to know objectively what are the best tools for annotating cell types. In this project, a review of the current tools and an evaluation of R tools were carried out.The annotation performance, the computation time and the ease of use were assessed. After this preliminary results, the best selected R tools seem to be ClustifyR (fast and rather precise) and SingleR (precise) for the correlation-based tools, and SingleCellNet (precise and rather fast) and scPred (precise but a lot of cell types remains unassigned) for the supervised classificationtools. Finally, for the marker-based tools, MAESTRO and SCINA are rather robust if they are provided with high quality markers.
2
Wedin, Mattias, und Isak Bengtsson. „A Comparative Study on Machine Learning Models for Automatic Classification of Cell Types from Digitally Reconstructed Neurons“. Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-301744.
Der volle Inhalt der QuelleAnnotation:
For the last decade, the use of machine learning in neuroscientific research has become a popular topic. For instance, image recognition has been used together with machine learning to detect and also help improve the diagnostics of diseases. This study compares the accuracy of a Convolutional Neural Network (CNN), a support vector classifier and a random forest classifier to investigate which are better suited for classification of cell types based on digitally reconstructed images from mice. All models were trained on both a larger unbalanced dataset containing 49 different cell types and a smaller balanced dataset containing only 3 types. Each model was evaluated on how accurate they could classify all cell types but also their accuracy on individual cell types. The results showed that the convolutional neural network had the best mean accuracy, with 51 and 83 percent on respective datasets. When looking at classification of individual cell types, all the models had good accuracy on at least a few cell types, but still, the CNN had the best individual accuracy and also consistency. In conclusion, the results showcase that a convolutional neural network is probably better suited when classifying cell types from digitally reconstructed images, but the other methods could also perform well on some of the cell types. However, further research is needed to reach a higher accuracy and reliability of the results.Under det senaste decenniet har användningen av maskininlärning i neurovetenskaplig forskning blivit ett populärt ämne. Exempelvis har bildigenkänning med hjälp av maskininlärning använts för att upptäcka och även förbättra diagnostisering av sjukdomar. I denna studie jämförs noggrannheten i ett Convolutional Neural Network (CNN), en support vector classifier och en random forest classifier för att undersöka vilka som är bättre lämpade för klassificering av celltyper utifrån digitalt rekonstruerade bilder av hjärnceller från möss. Alla modeller tränades på både ett större obalanserad dataset som innehöll 49 olika celltyper och en mindre balanserat dataset som endast innehöll 3 typer. Varje modell utvärderades på hur väl de kunde klassificera alla celltyper men också deras noggrannhet på enskilda celltyper. Resultaten visade att CNN hade bästa medelprecision, med 51 och 83 procent på respektive datamängder. Vid klassificeringen av enskilda celltyper hade alla modeller god noggrannhet på åtminstone några celltyper, även här hade CNN den bästa individuella noggrannheten och var mer konsekvent. Sammanfattningsvis visar resultaten att ett convolutional neural network förmodligen är bättre lämpad vid klassificerar av celltyper från digitalt rekonstruerade bilder av hjärnceller, men även de andra metoderna kan vara lämpliga vid vissa celltyper. Vidare forskning inom ämnet är dock nödvändigt för att nå en högre precision och pålitlighet av resultatet.
3
Neves, João. „Automatic annotation of cellular data“. Master's thesis, 2013. http://hdl.handle.net/10400.6/3696.
Der volle Inhalt der QuelleAnnotation:
Life scientists often need to count cells in microscopy images, which is very tedious and a time consuming task. Henceforth, automatic approaches can be a solution to this problem. Several works have been devised for this issue, but the majority of these approaches degrade their performance in case of cell overlapping. In this dissertation we propose a method to determine the position of macrophages and parasites in uorescence images of Leishmania-infected macrophages. The proposed strategy is mainly based on blob detection, clustering and separation using concave regions of the cells' contour. By carrying out a comparison with other approaches that also addressed this type of images, we concluded that the proposed methodology achieves better performance in the automatic annotation of Leishmania infections.A anotação de células é uma tarefa comum a diversas áreas da investigação biomédica. Normalmente, esta tarefa é realizada de forma manual, sendo um processo demorado, cansativo e propício a erros. Neste trabalho, focamos o nosso interesse na anotação de imagens de uorescência com infeções de Leishmania, que representa um destes casos. Leishmania são parasitas unicelulares que infectam mamíferos, sendo responsáveis por um conjunto de doenças conhecidas por leishmanioses. Leishmania usam vertebrados como hospedeiros residindo dentro dos seus macrófagos. Por conseguinte, um modelo adequado para o estudo destes parasitas é infectar in vitro culturas de macrófagos. A capacidade de sobrevivência/replicação da Leishmania nessas condições arti - ciais pode então ser avaliada por parâmetros, como, por exemplo, a percentagem de macrófagos infectados, o número médio de parasitas por macrófagos infectados e o índice de infeção. Essas métricas são geralmente determinadas pela contagem de parasitas e macrófagos ao microscópio. Ambos os tipos de células podem ser facilmente distinguidos com base no seu tamanho e cor, resultante de diferentes a nidades de corantes uorescentes. A passagem desta tarefa do microscópio para o computador já foi conseguida através de aplicações como o CellNote, contudo, apesar de mais fácil e interativa, a anotação continua a ser manual. A evolução da abordagem manual para um processo automático representa um passo natural e lógico, constituindo o principal objetivo deste trabalho. Para isto iniciámos a investigação pela revisão dos principais métodos de deteção e contagem celular. As características das imagens com infeções de Leishmania impossibilitam a utilização dos métodos estudados, de tal modo que optámos por desenvolver uma nova abordagem, capaz de lidar com as várias especi cidades destas imagens. Também durante o processo de revis ão de literatura analisámos os dois métodos previamente propostos para realizar a anotação automática de infeções de Leishmania. Estes revelaram um desempenho abaixo do requerido pelos parasitologistas, justi cando também o desenvolvimento de uma nova abordagem. Durante a concepção do sistema investigámos diversas técnicas de deteção celular, onde a deteção de blobs se destacou pelos resultados positivos. Para segmentar as regiões citoplasmáticas optámos pela utilização de algoritmos de clustering. Estes não foram capazes de solucionar casos em que existia sobreposição de estruturas celulares, motivando assim o método de separação desenvolvido. Este método baseia-se maioritariamente na análise de contorno, sendo as suas concavidades geradoras de separação entre citoplasmas. Através da combinação destas fases foi possível detetar macrófagos e parasitas com mais precisão. Para con rmar esta conclusão testámos não só a nossa abordagem mas também as duas abordagens previamente desenvolvidas para este problema. Os desempenhos alcançados evidenciam não só uma melhoria comparativamente às restantes abordagens como também mostram que a nossa abordagem assegura resultados satisfatórios comparativamente aos obtidos manualmente. Em suma, o trabalho desenvolvido produziu um sistema capaz de realizar a anotação automática de imagens de uorescência com infeções de Leishmania, tendo originado um artigo aceite para publicação na conferência International Conference on Image Analysis and Recognition (ICIAR) 2013.
Bücher zum Thema "Automatic cell types annotation"
1
Lüdeling, Anke, Julia Ritz, Manfred Stede und Amir Zeldes. Corpus Linguistics and Information Structure Research. Herausgegeben von Caroline Féry und Shinichiro Ishihara. Oxford University Press, 2015. http://dx.doi.org/10.1093/oxfordhb/9780199642670.013.013.
Der volle Inhalt der QuelleAnnotation:
This chapter describes the contributions that Corpus Linguistics (the study of linguistic phenomena by means of systematically exploiting collections of naturally-occurring linguistic data) can make to IS research. It discusses issues of designing a corpus that can serve as a basis for qualitative or quantitative studies, and then turns to the central issue of data annotation: what corpora are available that have been annotated with IS-related annotations, and how can such annotations be evaluated? In case a corpus does not have direct IS annotation, can other types of annotations, especially in the form of multi-layer annotation, be used as indirect evidence for the presence of IS phenomena? Next, the present state of the art in automatic IS annotation (by means of techniques from computational linguistics) is sketched, and finally, several sample studies that exploit IS annotations are introduced briefly.
Buchteile zum Thema "Automatic cell types annotation"
1
Busse, Beatrix. „Toward Developing a Procedure for Automatically Identifying Speech, Writing, and Thought Presentation“. In Speech, Writing, and Thought Presentation in 19th-Century Narrative Fiction, 155–64. Oxford University Press, 2020. http://dx.doi.org/10.1093/oso/9780190212360.003.0006.
Der volle Inhalt der QuelleAnnotation:
The sixth chapter illustrates how the automatic annotation of the different modes of speech, writing, and thought presentation in 19th-century narrative fiction may be performed on the basis of repetitive lexico-grammatical features and by setting up rules based on the manual annotation of the corpus and facilitating it in larger data sets. The chapter proposes a number of formal diagnostic features for the identification of discourse presentation as well as procedures to help their automatic detection. The procedures described serve as basis for a tool for the automatic identification of discourse presentation which can be adopted to programs like Wmatrix (Rayson 2018) and WordSmith Tools (Scott 2017). The chapter furthermore critically reflects on the limits of automated procedures and the necessity to manually check the annotations and include contextual information for unambiguous identification of different types of discourse presentation.
2
Zhou, Xiangrong, und Hiroshi Fujita. „Automatic Organ Localization on X-Ray CT Images by Using Ensemble-Learning Techniques“. In Machine Learning in Computer-Aided Diagnosis, 403–18. IGI Global, 2012. http://dx.doi.org/10.4018/978-1-4666-0059-1.ch019.
Der volle Inhalt der QuelleAnnotation:
Location of an inner organ in a CT image is the basic information that is required for medical image analysis such as image segmentation, lesion detection, content-based image retrieval, and anatomical annotation. A general approach/scheme for the localization of different inner organs that can be adapted to suit various types of medical image formats is required. However, this is a very challenging problem and can hardly be solved by using traditional image processing techniques. This chapter introduces an ensemble-learning-based approach that can be used to solve organ localization problems. This approach can be used to generate a fast and efficient organ-localization scheme from a limited number of training samples that include both original images and target locations. This approach has been used for localizing five different human organs in CT images, and the accuracy, robustness, and computational efficiency of the designed scheme were validated by experiments.
3
Jan, Rafiya, und Afaq Alam Khan. „Emotion Mining Using Semantic Similarity“. In Natural Language Processing, 1115–38. IGI Global, 2020. http://dx.doi.org/10.4018/978-1-7998-0951-7.ch053.
Der volle Inhalt der QuelleAnnotation:
Social networks are considered as the most abundant sources of affective information for sentiment and emotion classification. Emotion classification is the challenging task of classifying emotions into different types. Emotions being universal, the automatic exploration of emotion is considered as a difficult task to perform. A lot of the research is being conducted in the field of automatic emotion detection in textual data streams. However, very little attention is paid towards capturing semantic features of the text. In this article, the authors present the technique of semantic relatedness for automatic classification of emotion in the text using distributional semantic models. This approach uses semantic similarity for measuring the coherence between the two emotionally related entities. Before classification, data is pre-processed to remove the irrelevant fields and inconsistencies and to improve the performance. The proposed approach achieved the accuracy of 71.795%, which is competitive considering as no training or annotation of data is done.
4
Singhal, Vanika, und Preety Singh. „Selected Shape and Texture Features for Automatic Detection of Acute Lymphoblastic Leukemia“. In Biomedical Signal and Image Processing in Patient Care, 162–83. IGI Global, 2018. http://dx.doi.org/10.4018/978-1-5225-2829-6.ch009.
Der volle Inhalt der QuelleAnnotation:
Acute Lymphoblastic Leukemia is a cancer of blood caused due to increase in number of immature lymphocyte cells. Detection is done manually by skilled pathologists which is time consuming and depends on the skills of the pathologist. The authors propose a methodology for discrimination of a normal lymphocyte cell from a malignant one by processing the blood sample image. Automatic detection process will reduce the diagnosis time and not be limited by human interpretation. The lymphocyte images are classified based on two types of extracted features: shape and texture. To identify prominent shape features, Correlation based Feature Selection is applied. Principal Component Analysis is applied on the texture features to reduce their dimensionality. Support Vector Machine is used for classification. It is observed that 16 shape features are able to give a classification accuracy of 92.3% and that changes in the geometrical properties of the nucleus emerge as significant features contributing towards detecting a malignant lymphocyte.
5
Gustafsson, Mika, und Michael Hörnquist. „Integrating Various Data Sources for Improved Quality in Reverse Engineering of Gene Regulatory Networks“. In Handbook of Research on Computational Methodologies in Gene Regulatory Networks, 476–97. IGI Global, 2010. http://dx.doi.org/10.4018/978-1-60566-685-3.ch020.
Der volle Inhalt der QuelleAnnotation:
In this chapter we outline a methodology to reverse engineer GRNs from various data sources within an ODE framework. The methodology is generally applicable and is suitable to handle the broad error distribution present in microarrays. The main effort of this chapter is the exploration of a fully data driven approach to the integration problem in a “soft evidence” based way. Integration is here seen as the process of incorporation of uncertain a priori knowledge and is therefore only relied upon if it lowers the prediction error. An efficient implementation is carried out by a linear programming formulation. This LP problem is solved repeatedly with small modifications, from which we can benefit by restarting the primal simplex method from nearby solutions, which enables a computational efficient execution. We perform a case study for data from the yeast cell cycle, where all verified genes are putative regulators and the a priori knowledge consists of several types of binding data, text-mining and annotation knowledge.
6
Grossberg, Stephen. „Laminar Computing by Cerebral Cortex“. In Conscious Mind, Resonant Brain, 353–69. Oxford University Press, 2021. http://dx.doi.org/10.1093/oso/9780190070557.003.0010.
Der volle Inhalt der QuelleAnnotation:
The cerebral cortex computes the highest forms of biological intelligence in all sensory and cognitive modalities. Neocortical cells are organized into circuits that form six cortical layers in all cortical areas that carry out perception and cognition. Variations in cell properties within these layers and their connections have been used to classify the cerebral cortex into more than fifty divisions, or areas, to which distinct functions have been attributed. Why the cortex has a laminar organization for the control of behavior has, however, remained a mystery until recently. Also mysterious has been how variations on this ubiquitous laminar cortical design can give rise to so many different types of intelligent behavior. This chapter explains how Laminar Computing contributes to biological intelligence, and how layered circuits of neocortical cells support all the various kinds of higher-order biological intelligence, including vision, language, and cognition, using variations of the same canonical laminar circuit. This canonical circuit can be used in general-purpose VLSI chips that can be specialized to carry out different kinds of biological intelligence, and seamlessly joined together to control autonomous adaptive algorithms and mobile robots. These circuits show how preattentive automatic bottom-up processing and attentive task-selective top-down processing are joined together in the deeper cortical layers to form a decision interface. Here, bottom-up and top-down constraints cooperate and compete to generate the best decisions, by combining properties of fast feedforward and feedback processing, analog and digital computing, and preattentive and attentive learning, including laminar ART properties such as analog coherence.
Konferenzberichte zum Thema "Automatic cell types annotation"
1
Bryant, Christopher, Mariano Felice und Ted Briscoe. „Automatic Annotation and Evaluation of Error Types for Grammatical Error Correction“. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Stroudsburg, PA, USA: Association for Computational Linguistics, 2017. http://dx.doi.org/10.18653/v1/p17-1074.
Der volle Inhalt der Quelle
2
Chowdhury, Aritra, Sujoy K. Biswas und Simone Bianco. „Active deep learning reduces annotation burden in automatic cell segmentation“. In Digital and Computational Pathology, herausgegeben von John E. Tomaszewski und Aaron D. Ward. SPIE, 2021. http://dx.doi.org/10.1117/12.2579537.
Der volle Inhalt der Quelle
3
Dyachkov, V. V., I. A. Khomchenkova, P. S. Pleshak und N. M. Stoynova. „ANNOTATING AND EXPLORING CODE-SWITCHING IN FOUR CORPORA OF MINORITY LANGUAGES OF RUSSIA“. In International Conference on Computational Linguistics and Intellectual Technologies "Dialogue". Russian State University for the Humanities, 2020. http://dx.doi.org/10.28995/2075-7182-2020-19-228-240.
Der volle Inhalt der QuelleAnnotation:
This paper describes code-switching with Russian in four spoken corpora of minority languages of Russia: two Uralic ones (Hill Mari and Moksha) and two Tungusic ones (Nanai and Ulch). All narrators are bilinguals, fluent both in the indigenous language (IL) and in Russian; all the corpora are comparable in size and genres (small field collections of spontaneous oral texts, produced under the instruction to speak IL); the languages are comparable in structural (dis)similarity with Russian. The only difference concerns language dominance and the degree of language shift across the communities. The aim of the paper is to capture how the degree of language shift influences the strategy of code-switching attested in each of the corpora using a minimal additional annotation of code-switching. We added to each corpus a uniform annotation of code-switching of two types: first, a simple semi-automatic word-by-word language annotation (IL vs. Russian), second, a manual annotation of structural code-switching types (for smaller sub-corpora). We compared several macro-parameters of code-switching by applying some existing simple measures of code-switching to the data of annotation 1. Then we compared the rates of different structural types of code-switching, basing on annotation 2. The results of the study, on the one hand, verify and enhance the existing generalizations on how language shift influences code-switching strategies, on the other hand, they show that even a very simple annotation of code-switching integrated to an existing field records collection appears to be very informative in code-switching studies.
4
Yeker, Cengiz, und Ibrahim Zeid. „The Development of an Automatic Three-Dimensional Mesh Generator via Modified Ray Casting“. In ASME 1992 International Computers in Engineering Conference and Exposition. American Society of Mechanical Engineers, 1992. http://dx.doi.org/10.1115/cie1992-0023.
Der volle Inhalt der QuelleAnnotation:
Abstract A fully automatic three-dimensional mesh generation method is developed by modifying the well-known ray casting technique. The method is capable of meshing objects modeled using the CSG representation scheme. The input to the method consists of solid geometry information, and mesh attributes such as element size. The method starts by casting rays in 3D space to classify the empty and full parts of the solid. This information is then used to create a cell structure that closely models the solid object. The next step is to further process the cell structure to make it more succinct, so that the cells close to the boundary of the solid object can model the topology with enough fidelity. Moreover, neighborhood relations between cells in the structure are developed and implemented. These relations help produce better conforming meshes. Each cell in the cell structure is identified with respect to a set of pre-defined types of cells. After the identification process, a normalization process is developed and applied to the cell structure in order to ensure that the finite elements generated from each cell conform to each other and to other elements produced from neighboring cells. The last step is to mesh each cell in the structure with valid finite elements.
5
Bobbitt, Brock, Stephen Garner, Brenton Cox, John Martens und Mark Fecke. „Manual vs. Automatic Boiler Controls: A Historical Perspective From Relevant Codes and Standards“. In ASME 2017 Power Conference Joint With ICOPE-17 collocated with the ASME 2017 11th International Conference on Energy Sustainability, the ASME 2017 15th International Conference on Fuel Cell Science, Engineering and Technology, and the ASME 2017 Nuclear Forum. American Society of Mechanical Engineers, 2017. http://dx.doi.org/10.1115/power-icope2017-3616.
Der volle Inhalt der QuelleAnnotation:
Advances in computer hardware over the past several decades have helped to expand the capabilities of boiler control systems in power generating applications. These greater capabilities have supported a proliferation of computer controlled boiler functions and, in many cases, replaced human operator functions with automated functions. Nevertheless, the human operator remains a central piece in many modern boiler control systems. One reason the operator is still present in the control room is that computer controls and human operators each have distinct advantages. Consequently, a boiler control system design should balance the best integration of automatic and operator control functions while balancing various requirements and design goals. The following question should then be answered: what roles or functions should be given to the operator vs. to the computer controls? We will address this question by considering the guidance of relevant codes and standards, which have historically influenced control system design for large boilers in power generating applications. An analysis is performed on current and historically relevant standards and codes, including NFPA 85 and its predecessors, to consider how the guidance has changed along with control system technology. The analysis examines provisions directed toward manual and automatic controls to better understand the types of operations that are best-suited for manual functions versus automatic functions. Over time, NFPA 85 and its predecessors responded to the growing automation capabilities by requiring more automatic controls. While the emphasis placed on automatic controls for safety functions has grown, these standards suggest a balance or combination of automatic and manual controls for safety functions. These concepts are considered relative to those of Inherently Safe Design commonly applied in the chemical process industry.
6
Rupnowski, Peter, Michael Ulsh und Bhushan Sopori. „High Throughput and High Resolution In-Line Monitoring of PEMFC Materials by Means of Visible Light Diffuse Reflectance Imaging and Computer Vision“. In ASME 2015 13th International Conference on Fuel Cell Science, Engineering and Technology collocated with the ASME 2015 Power Conference, the ASME 2015 9th International Conference on Energy Sustainability, and the ASME 2015 Nuclear Forum. American Society of Mechanical Engineers, 2015. http://dx.doi.org/10.1115/fuelcell2015-49212.
Der volle Inhalt der QuelleAnnotation:
In this paper we present results from our recent work in which polymer electrolyte membrane fuel cell electrodes with intentionally introduced known defects were imaged and analyzed using a fuel cell scanner recently developed at the National Renewable Energy Laboratory. The defect types considered included particle debris, scuffs, scores, slits, and laser perforated pinholes. The debris defects were analyzed on samples from three different production stages, whereas the other defect types were introduced in a membrane tacked on a catalyst-coated diffusion media. We are showing that the fuel cell scanner can generate good quality, high resolution images of both baseline and defect-containing material. Based on the scanned images, an automatic, computer vision algorithm is developed that identifies presence and location of debris particles. The presented results clearly indicate that the in-line visible-light-diffuse-reflectance-based system can be successfully employed to monitor quality and to detect critical defects in fuel cell electrodes that are transported with high speed in a high volume manufacturing facility.
7
Cheng, Peng, Chasen Tongsh, Jinqiao Liang, Zhi Liu, Qing Du und Kui Jiao. „Experimental Investigation of Proton Exchange Membrane Fuel Cell With Platinum and Nafion Along the In-Plane Direction“. In ASME 2020 International Mechanical Engineering Congress and Exposition. American Society of Mechanical Engineers, 2020. http://dx.doi.org/10.1115/imece2020-23430.
Der volle Inhalt der QuelleAnnotation:
Abstract In this study, an experimental study has been performed to investigate the effect of in-plane distribution of Pt and Nafion in membrane electrode assembly (MEA) on proton exchange membrane (PEM) fuel cell. Two types of MEAs, such as the gradient and uniform distributions of Pt catalyst and Nafion, are compared under various operating conditions including cathode flow rate, MEA preparation method, Pt loading and relative humidity (RH). The catalyst ink is sprayed onto Nafion membrane or gas diffusion layer (GDL) through a pneumatic automatic spraying device manufactured by ourselves. MEA is prepared by hot pressing. The results show that as flow rate decreases, the MEA with gradient distribution will show a higher voltage at a high current density for catalyst coated membrane (CCM) method. For CCM method, gradient distribution can optimize cell performance under low cathode flow rate, but the optimization effect is weakened when flow rate is too low. Compared with CCM method, the gas diffusion electrode (GDE) method makes the difference value of Ohmic resistance between gradient and uniform distribution very larger, resulting in poor performance improvement. For GDE method, gradient distribution shows no optimization for cell performance under different Pt loadings and RH, but a smaller average Pt loading and fully-humidified reactants can reduce the performance distinction between uniform and gradient distribution. The gradient design of Pt and Nafion along the in-plane direction is a promising strategy to improve the performance of PEM fuel cell. Reasonably controlling the gradient distribution of Pt in the plane direction of cathode can reduce the amount of Pt catalysts and improve efficiency.
8
Kim, Jinseon, Minsoo Kim, Minju Shin, Incheol Nam, Daesun Kim, Hongsun Hwang, Sangjae Rhee, Kangyong Cho und Seongjin Jang. „A Study on Error Corrected Code Failure-Induced Latent Defect in between High-k MIM Capacitors“. In ISTFA 2017. ASM International, 2017. http://dx.doi.org/10.31399/asm.cp.istfa2017p0424.
Der volle Inhalt der QuelleAnnotation:
Abstract For fault management, various types of error-correcting codes (ECC) have been widely used for most computers and memory. From a memory perspective, the ECC technique is generally adopted for DRAM modules to correct data corruption among multiple chips, not in-chip level. Recently, increased soft single-bit failures have accelerated introduction of the ECC technique into DRAM components. For reliability, fault generation technique by high voltage at high temperature, also known as burn-in stress, has been widely used in the IC manufacturing process. In DRAM, burn-in stress is also useful to screen latent defects or to predict device lifetime. In this paper, we studied un-correctable errors which occurred due to various types of storage node bridge defects in ECC DRAM. 12 faulty cells among 1,000 cells are observed after burn-in stress. Retention time of each cell is measured with automatic test equipment under the various temperature conditions, and activation energy were extracted from measurement results. Results of activation energy show that there were two types of faults, one was metal-metal hard bridge (0.14eV) and the other was dielectric-dielectric soft bridge (0.35eV), in comparison with normal cells (0.53eV). Moreover, soft bridge was carefully analyzed with TEM and nanoprobing showing that activation energy analysis was well-matched.
9
Tischner, Oliver, und A. H. Soni. „Development of a Methodology for Cost Estimation in Robot Assembly“. In ASME 1998 Design Engineering Technical Conferences. American Society of Mechanical Engineers, 1998. http://dx.doi.org/10.1115/detc98/flex-6043.
Der volle Inhalt der QuelleAnnotation:
Abstract The developments in today’s industries put the companies under increasing pressure concerning time and costs. This forces them to, among other measures, rationalize and automates the manufacturing systems, including the assembly systems. To reduce the risks of investments and enhance the investment planning, accurate calculation methodologies for assembly planning systems are necessary. There are a number of ways to lay out an assembly system. An assembly system may be designed for a manual operation, an automatic operation, or a flexible operation. Industrial robots are extensively used in such flexible assembly systems. Production volume and cost per assembled part depend heavily on how such a flexible cell is designed and on the robot being used. Boothroyd and Dewhurst have proposed an approach to arrive at evaluating robot integrated assembly cells. This approach is based on the manipulation of the part before presenting it for an assembly and the number of robot arms in the assembly cell. It does not account for the flexibility (number of robot axes, specific types of robots) the various industrial robots offer. Consequently, any evaluation made on this basis is expected to provide inaccurate answers.
10
Lu, Roberto F. „Design and Configuration of Machine Vision Robotic Cells in a Manufacturing System“. In ASME 2004 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference. ASMEDC, 2004. http://dx.doi.org/10.1115/detc2004-57234.
Der volle Inhalt der QuelleAnnotation:
Most fixed automations in traditional manufacturing systems are not equipped to manage product variations efficiently. This paper presents a design and configuration for a machine-vision-equipped robotic packing cell that is capable of managing a wide range of product sizes. Product size information is gathered at an earlier stage in the manufacturing process and then transferred electronically to the robot cell. Different controllers are needed to manage robot cell functions related to incoming product, machine vision, robot control, robot manipulator, and multiple layers of safety control information. Each controller, due to the nature of its function, has different advantages in processing different data types. In order to achieve the highest possible robot manipulator utilization rate, the assignment of information processing among controllers needs to be thoughtfully planned, especially for the critical mathematical routines. Coordination and calibration between charged-coupled device (CCD) cameras and robots in existing manufacturing facilities are configured with considerations for building vibrations, lighting conditions, and signal processing assignments among the available devices. System efficiency is improved when the vision signal, robot logical signal, and robot manipulator signal processing units are running cohesively in parallel. The capability of the machine-vision-assisted robot end effector automatic path adjustment, to pick up and pack different sizes of products dynamically, allows a higher level of flexibility and efficiency. This paper describes a feasible design and configuration for an integrated machine vision robotic cell in a manufacturing system.