CNN based classification of 5 cell types by diffraction images

2019 ◽  
Author(s):  
Jiahong Jin ◽  
Jun Qing Lu ◽  
Yuhua Wen ◽  
Peng Tian ◽  
Xin-Hua Hu
Keyword(s):  
Cell Types

scholarly journals Morphological and Ultrastructural Characterization of Hemocytes in an Insect Model, the Hematophagous Dipetalogaster maxima (Hemiptera: Reduviidae)

Insects ◽  
2021 ◽  
Vol 12 (7) ◽  
pp. 640
Author(s):  
Natalia R. Moyetta ◽  
Fabián O. Ramos ◽  
Jimena Leyria ◽  
Lilián E. Canavoso ◽  
Leonardo L. Fruttero
Keyword(s):  
Cell Biology ◽  
Cell Types ◽  
Transmission Electron ◽  
Ultrastructural Characterization ◽  
Current Classification ◽  
Contrast Microscopy ◽  
First Time ◽  
Controversial Aspect

Hemocytes, the cells present in the hemolymph of insects and other invertebrates, perform several physiological functions, including innate immunity. The current classification of hemocyte types is based mostly on morphological features; however, divergences have emerged among specialists in triatomines, the insect vectors of Chagas’ disease (Hemiptera: Reduviidae). Here, we have combined technical approaches in order to characterize the hemocytes from fifth instar nymphs of the triatomine Dipetalogaster maxima. Moreover, in this work we describe, for the first time, the ultrastructural features of D. maxima hemocytes. Using phase contrast microscopy of fresh preparations, five hemocyte populations were identified and further characterized by immunofluorescence, flow cytometry and transmission electron microscopy. The plasmatocytes and the granulocytes were the most abundant cell types, although prohemocytes, adipohemocytes and oenocytes were also found. This work sheds light on a controversial aspect of triatomine cell biology and physiology setting the basis for future in-depth studies directed to address hemocyte classification using non-microscopy-based markers.

scholarly journals A Deep Learning Approach for the Classification of Neuronal Cell Types

2018 ◽  
Author(s):  
Alessio P. Buccino ◽  
Torbjorn V. Ness ◽  
Gaute T. Einevoll ◽  
Gert Cauwenberghs ◽  
Philipp D. Hafliger
Keyword(s):  
Deep Learning ◽  
Neuronal Cell ◽  
Cell Types ◽  
Learning Approach

scholarly journals Molecular Stratification of Chronic Kidney Disease

2021 ◽  
Author(s):  
Anna Reznichenko ◽  
Viji Nair ◽  
Sean Eddy ◽  
Mark Tomilo ◽  
Timothy Slidel ◽  
...  
Keyword(s):  
Chronic Kidney Disease ◽  
Kidney Disease ◽  
Cell Types ◽  
Biological Pathways ◽  
Self Organizing Maps ◽  
Molecular Stratification ◽  
Indirect Measures ◽  
Genome Wide ◽  
Neural Network Algorithm

Current classification of chronic kidney disease (CKD) into stages based on the indirect measures of kidney functional state, estimated glomerular filtration rate and albuminuria, is agnostic to the heterogeneity of underlying etiologies, histopathology, and molecular processes. We used genome-wide transcriptomics from patients kidney biopsies, directly reflecting kidney biological processes, to stratify patients from three independent CKD cohorts. Unsupervised Self-Organizing Maps (SOM), an artificial neural network algorithm, assembled CKD patients into four novel subgroups, molecular categories, based on the similarity of their kidney transcriptomics profiles. The unbiased, molecular categories were present across CKD stages and histopathological diagnoses, highlighting heterogeneity of conventional clinical subgroups at the molecular level. CKD molecular categories were distinct in terms of biological pathways, transcriptional regulation and associated kidney cell types, indicating that the molecular categorization is founded on biologically meaningful mechanisms. Importantly, our results revealed that not all biological pathways are equally activated in all patients; instead, different pathways could be more dominant in different subgroups and thereby differentially influencing disease progression and outcomes. This first kidney-centric unbiased categorization of CKD paves the way to an integrated clinical, morphological and molecular diagnosis. This is a key step towards enabling precision medicine for this heterogeneous condition with the potential to advance biological understanding, clinical management, and drug development, as well as establish a roadmap for molecular reclassification of CKD and other complex diseases.

scholarly journals Klasifikasi Sel Darah Putih dan Sel Limfoblas Menggunakan Metode Multilayer Perceptron Backpropagation

2019 ◽  
Vol 9 (2) ◽  
pp. 173
Author(s):  
Apri Nur Liyantoko ◽  
Ika Candradewi ◽  
Agus Harjoko
Keyword(s):  
Blood Cell ◽  
White Blood Cell ◽  
Blood Cells ◽  
White Blood Cells ◽  
Back Propagation ◽  
Cell Types ◽  
Diagnostic Process ◽  
The Subject ◽  
Processing Techniques

 Leukemia is a type of cancer that is on white blood cell. This disease are characterized by abundance of abnormal white blood cell called lymphoblast in the bone marrow. Classification of blood cell types, calculation of the ratio of cell types and comparison with normal blood cells can be the subject of diagnosing this disease. The diagnostic process is carried out manually by hematologists through microscopic image. This method is likely to provide a subjective result and time-consuming.The application of digital image processing techniques and machine learning in the process of classifying white blood cells can provide more objective results. This research used thresholding method as segmentation and  multilayer method of back propagation perceptron with variations in the extraction of textural features, geometry, and colors. The results of segmentation testing in this study amounted to 68.70%. Whereas the classification test shows that the combination of feature extraction of GLCM features, geometry features, and color features gives the best results. This test produces an accuration value 91.43%, precision value of 50.63%, sensitivity 56.67%, F1Score 51.95%, and specitifity 94.16%.

scholarly journals Current Status of Histogenetic and Morphogenetic Concepts of Salivary Gland Tumorigenesis

1993 ◽  
Vol 4 (5) ◽  
pp. 639-677 ◽  
Author(s):  
Irving Dardick ◽  
Aileen P. Burford-Mason
Keyword(s):  
Salivary Gland ◽  
Acinar Cells ◽  
Neoplastic Transformation ◽  
Cell Types ◽  
Salivary Gland Tumors ◽  
Current Status ◽  
Normal Gland ◽  
Routine Diagnosis ◽  
Diagnosis And Classification

Because of their complexity and relative infrequency, salivary gland tumors commonly result in diagnostic problems. Histogenetic and morphogenetic concepts of tumorigenesis in these glands are reviewed and their relevance to routine diagnosis and classification of salivary gland tumors evaluated. Evidence is presented from animal and human studies that under steady-state and pathophysiological conditions, all cell types present in the normal gland, including acinar cells, are capable of rapidly entering the cell cycle and are, therefore, possible targets for neoplastic transformation.

scholarly journals Classification of Different Cancer Cell Types by Species Specificity for Cell Elasticity

2019 ◽  
Vol 116 (3) ◽  
pp. 375a-376a
Author(s):  
Sangwoo Kwon ◽  
Se Jik Han ◽  
Kyung Sook Kim
Keyword(s):  
Cancer Cell ◽  
Cell Types ◽  
Species Specificity ◽  
Cell Elasticity

scholarly journals Northstar enables automatic classification of known and novel cell types from tumor samples

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Fabio Zanini ◽  
Bojk A. Berghuis ◽  
Robert C. Jones ◽  
Benedetta Nicolis di Robilant ◽  
Rachel Yuan Nong ◽  
...  
Keyword(s):  
Cell Types ◽  
Neoplastic Cell ◽  
Computational Approach ◽  
Pancreatic Tumors ◽  
Published Data ◽  
Cell Type ◽  
Disease Heterogeneity ◽  
Manual Task ◽  
Insight Into

Abstract Single cell transcriptomics is revolutionising our understanding of tissue and disease heterogeneity, yet cell type identification remains a partially manual task. Published algorithms for automatic cell annotation are limited to known cell types and fail to capture novel populations, especially cancer cells. We developed northstar, a computational approach to classify thousands of cells based on published data within seconds while simultaneously identifying and highlighting new cell states such as malignancies. We tested northstar on data from glioblastoma, melanoma, and seven different healthy tissues and obtained high accuracy and robustness. We collected eleven pancreatic tumors and identified three shared and five private neoplastic cell populations, offering insight into the origins of neuroendocrine and exocrine tumors. Northstar is a useful tool to assign known and novel cell type and states in the age of cell atlases.

scholarly journals Continuous Free-Flow Fractionation of Cellular Constituents in Rat Bone Marrow

Blood ◽  
1965 ◽  
Vol 25 (1) ◽  
pp. 63-72 ◽  
Author(s):  
HOWARD C. MEL ◽  
LINDA T. MITCHELL ◽  
BO THORELL
Keyword(s):  
Bone Marrow ◽  
Cell Types ◽  
Single Cell Suspension ◽  
Physical Classification ◽  
Normal Rat ◽  
Good Repeatability ◽  
Different Cell Types ◽  
Stable Flow ◽  
Rat Bone

Abstract A single-cell suspension of normal rat bone marrow is prepared mechanically. This suspension is continuously fractionated in free solution, under sedimentation rate conditions, using 1 g. only. With a sample flow of 2.2 x 106 cells/minute and a 32-minute steady-state residence time in the stable-flow free boundary (STAFLO) flow-cell, the cells exit almost entirely into 7 of the 12 collection bottles. Maximum numbers of different cell types are observed, with good repeatability, in approximately descending order from top to bottom as follows: erythrocytes, "erythroblasts," "immatures," "myelocytes," and mature granulocytes. Major changes are effected relative to the starting marrow composition, and large relative enrichments are achieved for certain cell types. In addition to the rapid, mild, preparative aspect of this study, nominal sedimentation rates can be assigned for the different collection fractions, in the range of 3 x 105 to 4 x 106 svedbergs, thus making a start on this kind of simple physical classification of the cellular elements in this complex tissue.

scholarly journals APPLICATION OF AUTO REGRESSIVE MODELS OF WAVELET SUB-BANDS FOR CLASSIFYING TERAHERTZ PULSE MEASUREMENTS

2007 ◽  
Vol 15 (04) ◽  
pp. 551-571 ◽  
Author(s):  
XIAOXIA YIN ◽  
BRIAN W.-H. NG ◽  
DEREK ABBOTT ◽  
BRADLEY FERGUSON ◽  
SILLAS HADJILOUCAS
Keyword(s):  
Wavelet Transforms ◽  
Moving Average ◽  
Cell Types ◽  
Classification Systems ◽  
Arma Models ◽  
Security Applications ◽  
Powder Samples ◽  
Auto Regressive ◽  
Normal Human

This paper presents an approach for automatic classification of pulsed Terahertz (THz), or T-ray, signals highlighting their potential in biomedical, pharmaceutical and security applications. T-ray classification systems supply a wealth of information about test samples and make possible the discrimination of heterogeneous layers within an object. In this paper, a novel technique involving the use of Auto Regressive (AR) and Auto Regressive Moving Average (ARMA) models on the wavelet transforms of measured T-ray pulse data is presented. Two example applications are examined — the classification of normal human bone (NHB) osteoblasts against human osteosarcoma (HOS) cells and the identification of six different powder samples. A variety of model types and orders are used to generate descriptive features for subsequent classification. Wavelet-based de-noising with soft threshold shrinkage is applied to the measured T-ray signals prior to modeling. For classification, a simple Mahalanobis distance classifier is used. After feature extraction, classification accuracy for cancerous and normal cell types is 93%, whereas for powders, it is 98%.

Sign in / Sign up

Export Citation Format

Share Document