scholarly journals Automated Counting of Cancer Cells by Ensembling Deep Features

Cells ◽  
2019 ◽  
Vol 8 (9) ◽  
pp. 1019 ◽  
Author(s):  
Liu ◽  
Junker ◽  
Murakami ◽  
Hu
Keyword(s):  
High Throughput ◽  
Pearson Correlation ◽  
Image Features ◽  
Cell Counting ◽  
Single Type ◽  
Imaging Features ◽  
Neural Network Models ◽  
Regression Problem ◽  
Microscopic Images ◽  
Cell Counts

High-content and high-throughput digital microscopes have generated large image sets in biological experiments and clinical practice. Automatic image analysis techniques, such as cell counting, are in high demand. Here, cell counting was treated as a regression problem using image features (phenotypes) extracted by deep learning models. Three deep convolutional neural network models were developed to regress image features to their cell counts in an end-to-end way. Theoretically, ensembling imaging phenotypes should have better representative ability than a single type of imaging phenotype. We implemented this idea by integrating two types of imaging phenotypes (dot density map and foreground mask) extracted by two autoencoders and regressing the ensembled imaging phenotypes to cell counts afterwards. Two publicly available datasets with synthetic microscopic images were used to train and test the proposed models. Root mean square error, mean absolute error, mean absolute percent error, and Pearson correlation were applied to evaluate the models’ performance. The well-trained models were also applied to predict the cancer cell counts of real microscopic images acquired in a biological experiment to evaluate the roles of two colorectal-cancer-related genes. The proposed model by ensembling deep imaging features showed better performance in terms of smaller errors and larger correlations than those based on a single type of imaging feature. Overall, all models’ predictions showed a high correlation with the true cell counts. The ensembling-based model integrated high-level imaging phenotypes to improve the estimation of cell counts from high-content and high-throughput microscopic images.

scholarly journals CellCountCV—A Web-Application for Accurate Cell Counting and Automated Batch Processing of Microscopic Images Using Fully Convolutional Neural Networks

Sensors ◽  
2020 ◽  
Vol 20 (13) ◽  
pp. 3653
Author(s):  
Denis Antonets ◽  
Nikolai Russkikh ◽  
Antoine Sanchez ◽  
Victoria Kovalenko ◽  
Elvira Bairamova ◽  
...  
Keyword(s):  
Neural Networks ◽  
Endoplasmic Reticulum ◽  
Endoplasmic Reticulum Stress ◽  
Web Application ◽  
Experimental Studies ◽  
Living Cells ◽  
Cell Counting ◽  
Microscopic Images ◽  
Cellular Models ◽  
Cell Counts

In vitro cellular models are promising tools for studying normal and pathological conditions. One of their important applications is the development of genetically engineered biosensor systems to investigate, in real time, the processes occurring in living cells. At present, there are fluorescence, protein-based, sensory systems for detecting various substances in living cells (for example, hydrogen peroxide, ATP, Ca2+ etc.,) or for detecting processes such as endoplasmic reticulum stress. Such systems help to study the mechanisms underlying the pathogenic processes and diseases and to screen for potential therapeutic compounds. It is also necessary to develop new tools for the processing and analysis of obtained microimages. Here, we present our web-application CellCountCV for automation of microscopic cell images analysis, which is based on fully convolutional deep neural networks. This approach can efficiently deal with non-convex overlapping objects, that are virtually inseparable with conventional image processing methods. The cell counts predicted with CellCountCV were very close to expert estimates (the average error rate was < 4%). CellCountCV was used to analyze large series of microscopic images obtained in experimental studies and it was able to demonstrate endoplasmic reticulum stress development and to catch the dose-dependent effect of tunicamycin.

scholarly journals MiR-140-3p inhibits the cell viability and promotes apoptosis of synovial fibroblasts in rheumatoid arthritis through targeting sirtuin 3

2021 ◽  
Vol 16 (1) ◽  
Author(s):  
Beibei Zu ◽  
Lin Liu ◽  
Jingya Wang ◽  
Meirong Li ◽  
Junxia Yang
Keyword(s):  
Rheumatoid Arthritis ◽  
Cell Viability ◽  
Cell Apoptosis ◽  
Caspase 3 ◽  
Pearson Correlation ◽  
Fibrous Tissue ◽  
Synovial Fibroblasts ◽  
Cell Counting ◽  
Sirtuin 3 ◽  
Fibrous Tissues

Abstract Background Synovial fibroblasts (SFs) with the abnormal expressions of miRNAs are the key regulator in rheumatoid arthritis (RA). Low-expressed miR-140-3p was found in RA tissues. Therefore, we attempted to investigate the effect of miR-140-3p on SFs of RA. Methods RA and normal synovial fibrous tissue were gathered. The targets of miR-140-3p were found by bioinformatics and luciferase analysis. Correlation between the expressions of miR-140-3p with sirtuin 3 (SIRT3) was analyzed by Pearson correlation analysis. After transfection, cell viability and apoptosis were detected by cell counting kit-8 and flow cytometry. The expressions of miR-140-3p, SIRT3, Ki67, Bcl-2, Bax, and cleaved Caspase-3 were detected by RT-qPCR or western blot. Results Low expression of miR-140-3p and high expression of SIRT3 were found in RA synovial fibrous tissues. SIRT3 was a target of miR-140-3p. SIRT3 expression was negatively correlated to the expression of miR-140-3p. MiR-140-3p mimic inhibited the MH7A cell viability and the expressions of SIRT3, Ki67, and Bcl-2 and promoted the cell apoptosis and the expressions of Bax and cleaved Caspase-3; miR-140-3p inhibitor showed an opposite effect to miR-140-3p mimic on MH7A cells. SIRT3 overexpression not only promoted the cell viability and inhibited cell apoptosis of MH7A cells but also reversed the effect of miR-140-3p mimic had on MH7A cells. Conclusions The results in this study revealed that miR-140-3p could inhibit cell viability and promote apoptosis of SFs in RA through targeting SIRT3.

scholarly journals Extensive Countrywide Field Investigation of Somatic Cell Counts and Total Bacterial Counts in Bulk-Tank Raw Milk in Sheep Flocks in Greece

Foods ◽  
2021 ◽  
Vol 10 (2) ◽  
pp. 268
Author(s):  
Daphne T. Lianou ◽  
Charalambia K. Michael ◽  
Natalia G. C. Vasileiou ◽  
Efthymia Petinaki ◽  
Peter J. Cripps ◽  
...  
Keyword(s):  
Somatic Cell ◽  
Geometric Mean ◽  
Cell Counting ◽  
Lactation Period ◽  
Mechanical Ventilators ◽  
Bulk Tank Milk ◽  
Bacterial Counts ◽  
Somatic Cell Counts ◽  
Cell Counts ◽  
Bulk Tank

Objectives were to investigate somatic cell counts (SCC) and total bacterial counts (TBC) in the raw bulk-tank milk of sheep flocks in Greece, to study factors potentially influencing increased SCC and TBC in the bulk-tank milk of sheep and to evaluate possible associations of SCC and TBC with milk content. Throughout Greece, 325 dairy sheep flocks were visited for collection of milk sampling for somatic cell counting, microbiological examination and composition measurement. Geometric mean SCC were 0.488 × 106 cells mL−1; geometric mean TBC were 398 × 103 cfu mL−1; 228 staphylococcal isolates were recovered form 206 flocks (63.4%). Multivariable analyses revealed annual incidence risk of clinical mastitis, age of the farmer and month into lactation period (among 53 variables) to be significant for SCC > 1.0 × 106 cells mL−1 and month into lactation period at sampling and availability of mechanical ventilators (among 58 variables) to be significant for TBC > 1500 × 103 cfu mL−1. Negative correlation of SCC with fat, total protein and lactose and positive correlation of SCC with added water were found. With SCC > 1.0 × 106 cells mL−1, significant reduction of protein content (2%) was observed, whilst in flocks with SCC > 1.5 × 106 cells mL−1, significantly lower annual milk production per ewe (42.9%) was recorded.

scholarly journals The Graphical Representation of Cell Count Representation; a New Procedure for the Diagnosis of Periprosthetic Joint Infections

Antibiotics ◽  
2021 ◽  
Vol 10 (4) ◽  
pp. 346
Author(s):  
Bernd Fink ◽  
Marius Hoyka ◽  
Elke Weissbarth ◽  
Philipp Schuster ◽  
Irina Berger
Keyword(s):  
Cell Count ◽  
Graphical Representation ◽  
Diagnostic Value ◽  
Cell Counting ◽  
Wear Particles ◽  
Type Iv ◽  
Joint Infections ◽  
Cell Counts ◽  
Matrix Assessment ◽  
Wbc Count

Aim: This study was designed to answer the question whether a graphical representation increase the diagnostic value of automated leucocyte counting of the synovial fluid in the diagnosis of periprosthetic joint infections (PJI). Material and methods: Synovial aspirates from 322 patients (162 women, 160 men) with revisions of 192 total knee and 130 hip arthroplasties were analysed with microbiological cultivation, determination of cell counts and assay of the biomarker alpha-defensin (170 cases). In addition, microbiological and histological analysis of the periprosthetic tissue obtained during the revision surgery was carried out using the ICM classification and the histological classification of Morawietz and Krenn. The synovial aspirates were additionally analysed to produce dot plot representations (LMNE matrices) of the cells and particles in the aspirates using the hematology analyser ABX Pentra XL 80. Results: 112 patients (34.8%) had an infection according to the ICM criteria. When analysing the graphical LMNE matrices from synovia cell counting, four types could be differentiated: the type “wear particles” (I) in 28.3%, the type “infection” (II) in 24.8%, the “combined” type (III) in 15.5% and “indeterminate” type (IV) in 31.4%. There was a significant correlation between the graphical LMNE-types and the histological types of Morawietz and Krenn (p < 0.001 and Cramer test V value of 0.529). The addition of the LMNE-Matrix assessment increased the diagnostic value of the cell count and the cut-off value of the WBC count could be set lower by adding the LMNE-Matrix to the diagnostic procedure. Conclusion: The graphical representation of the cell count analysis of synovial aspirates is a new and helpful method for differentiating between real periprosthetic infections with an increased leukocyte count and false positive data resulting from wear particles. This new approach helps to increase the diagnostic value of cell count analysis in the diagnosis of PJI.

scholarly journals Radiomics in radiation oncology—basics, methods, and limitations

2020 ◽  
Vol 196 (10) ◽  
pp. 848-855
Author(s):  
Philipp Lohmann ◽  
Khaled Bousabarah ◽  
Mauritius Hoevels ◽  
Harald Treuer
Keyword(s):  
Mathematical Models ◽  
Quantitative Imaging ◽  
Human Perception ◽  
Image Features ◽  
Radiotherapy Planning ◽  
Large Field ◽  
Imaging Features ◽  
Imaging Data ◽  
Complete Evaluation ◽  
Vast Number

Abstract Over the past years, the quantity and complexity of imaging data available for the clinical management of patients with solid tumors has increased substantially. Without the support of methods from the field of artificial intelligence (AI) and machine learning, a complete evaluation of the available image information is hardly feasible in clinical routine. Especially in radiotherapy planning, manual detection and segmentation of lesions is laborious, time consuming, and shows significant variability among observers. Here, AI already offers techniques to support radiation oncologists, whereby ultimately, the productivity and the quality are increased, potentially leading to an improved patient outcome. Besides detection and segmentation of lesions, AI allows the extraction of a vast number of quantitative imaging features from structural or functional imaging data that are typically not accessible by means of human perception. These features can be used alone or in combination with other clinical parameters to generate mathematical models that allow, for example, prediction of the response to radiotherapy. Within the large field of AI, radiomics is the subdiscipline that deals with the extraction of quantitative image features as well as the generation of predictive or prognostic mathematical models. This review gives an overview of the basics, methods, and limitations of radiomics, with a focus on patients with brain tumors treated by radiation therapy.

Primary clinical study of radiomics for diagnosing simple bone cyst of the jaw

2021 ◽  
pp. 20200384
Author(s):  
Zhe-Yi Jiang ◽  
Tian-Jun Lan ◽  
Wei-Xin Cai ◽  
Qian Tao
Keyword(s):  
Bone Cyst ◽  
Maxillofacial Surgery ◽  
Correlation Coefficients ◽  
Texture Features ◽  
Image Features ◽  
Control Group ◽  
Imaging Features ◽  
Bone Cysts ◽  
Difference Matrix ◽  
Occurrence Matrix

Objective: To screen the radiomic features of simple bone cysts of the jaws and explore the potential application of radiomics in pre-operative diagnosis of jaw simple bone cysts. Methods: The investigators designed and implemented a case–control study. 19 patients with simple bone cysts who were admitted to the Department of Maxillofacial Surgery, Sun Yat-sen University Affiliated Stomatology Hospital from 2013 to 2019 were included in this study. Their clinical data and cone-beam computed tomography (CBCT) images were examined. The control group consisted of patients with odontogenic keratocyst. CBCT imaging features were analyzed and compared between the patient and control groups. Results: Overall, 10,323 image features were extracted through feature analysis. A subset of 25 radiomic features obtained after feature selection were analyzed further. These 25 features were significantly different between the 2 groups (p < 0.05). The absolute value of correlation coefficient was 0.487–0.775. Gray-level co-occurrence matrix (GLCM) contrast, neighborhood gray tone difference matrix (NGTDM) contrast, and GLCM variance were the features with the highest correlation coefficients. Conclusions: Pre-operative radiomics analysis showed the differences between simple bone cysts and odontogenic keratocysts, can help to diagnose simple bone cysts. Three specific texture features—GLCM contrast, NGTDM contrast, and GLCM variance—may be the characteristic imaging features of simple bone cysts of the jaw.

Pregnancy-associated plasma protein-a is associated with subclinical atherosclerosis in men with HIV infection

2018 ◽  
Vol 67 (5) ◽  
pp. 821-825
Author(s):  
Suleyman Sezai Yildiz ◽  
Sukru Cetin ◽  
Kudret Keskin ◽  
Alper Gunduz ◽  
Gokhan Cetinkal ◽  
...  
Keyword(s):  
Logistic Regression ◽  
T Cell ◽  
Plasma Protein ◽  
Roc Analysis ◽  
Subclinical Atherosclerosis ◽  
Pearson Correlation ◽  
Protein A ◽  
Cd4 T Cell ◽  
Cell Counts ◽  
Asymptomatic Hiv

The pathophysiology of an early and accelerated atherosclerotic process is complex and multifactorial in HIV-infected men compared with HIV-non-infected men. Several biomarkers have been well studied in the detection of the early stage of atherosclerosis, but studies are limited in HIV-infected men. The objective of this study was to investigate the association between serum pregnancy-associated plasma protein-A (PAPP-A) and carotid intima-media wall thickness (CIMT) in asymptomatic HIV-infected men. This a case–control study group comprising 118 HIV-infected men and 60 age-matched and gender-matched HIV-non-infected men. Serum PAPP-A was measured using an ELISA kit and carotid IMT was evaluated by Doppler ultrasonography in all subjects. Statistical analysis included receiver-operating characteristic (ROC) analysis, Pearson correlation and logistic regression analysis. Serum PAPP-A level was significantly higher in HIV +CIMT+ group compared with HIV +CIMT group and HIV–CIMT- group. We found a positive correlation between PAPP-A and increased CIMT (r=0.737, p<0.0001), and a negative correlation between nadir CD4 T cell counts and increased CIMT (r=−0.526, p<0.001). In multivariate logistic regression analyses, PAPP-A, nadir CD4 T cell count and age were significantly associated with subclinical atherosclerosis (p<0.001, p=0.006 and p=0.032, respectively). In ROC analysis, PAPP-A levels of >3.70 µg/mL were associated with subclinical atherosclerosis in HIV+ men with a specificity of 100% and a sensitivity of 71% (area under the curve: 0.949, 95% CI 0.875 to 1.000, p<0.001). Serum PAPP-A level was strongly correlated with increased CIMT in HIV-infected men. PAPP-A might be used as an early biomarker to identify atherosclerosis in asymptomatic HIV-infected men.

scholarly journals Management of Aphakia with Visual Axis Opacification after Congenital Cataract Surgery Based on UBM Image Features Analysis

2020 ◽  
Vol 2020 ◽  
pp. 1-7
Author(s):  
Wensi Chen ◽  
Shiping He ◽  
Daoman Xiang
Keyword(s):  
Cataract Surgery ◽  
Mixed Type ◽  
Congenital Cataract ◽  
Ultrasound Biomicroscopy ◽  
Image Features ◽  
Imaging Features ◽  
Visual Axis ◽  
Anterior Vitrectomy ◽  
Congenital Cataract Surgery

Objective. The purpose of this study was to study the imaging features of ultrasound biomicroscopy (UBM) in the aphakia with visual axis opacification (VAO) after congenital cataract surgery. Methods. From May 2015 to May 2018, aphakia patients with VAO who underwent congenital cataract surgery were examined by high-resolution bag/balloon UBM technique, and the results of UBM imaging were analyzed. According to UBM imaging features, different types of VAO were classified. Results. A total of 38 children (55 eyes) with VAO were included. 17 patients were bilateral, and 21 patients were unilateral. Patients with VAO were classified into 3 groups according to the UBM imaging features: membranous fibrosis VOA (17 cases, 28 eyes), cortical regeneration VOA (15 cases, 20 eyes), and mixed VOA (6 cases, 7 eyes). The patients in the membranous fibrosis group underwent Nd:YAG laser posterior capsulotomy, those in the cortical regeneration group underwent anterior vitrectomy, and those in the mixed type group underwent anterior vitrectomy with RF capsulotomy tip. After surgery, VAO were removed in all patients. During the follow-up period, in the membranous fibrotic VAO group, iris adhesion and pupillary occlusion were found in 2 eyes, and anterior vitrectomy combined with separation of iris adhesion was performed. In cortical regenerative and mixed type VAO groups, anterior vitrectomy was performed without opacity in the axial region. The total recurrence rate of VAO was 3.46%. Conclusion. After congenital cataract surgery, the UBM imaging features of aphakia with VAO are helpful to evaluate the condition of VAO before reoperation so as to choose the optimal surgical method to achieve better therapeutic effect.

Optical Somatic Cell Counting and Total Protein Analysis in a Dairy Herd Improvement Program1

1977 ◽  
Vol 40 (10) ◽  
pp. 671-675 ◽  
Author(s):  
N. WANG ◽  
G. H. RICHARDSON
Keyword(s):  
Somatic Cell ◽  
Total Protein ◽  
Potassium Dichromate ◽  
Somatic Cells ◽  
Dairy Herd ◽  
Cell Counting ◽  
Ambient Conditions ◽  
Fresh Milk ◽  
Cell Counts ◽  
Cheese Industry

Milk sample preparation for Optical Somatic Cell Counter II operation was simplified by using a diluter to add fixative, mix, and dilute samples. Potassium dichromate preservative tablets produced a mean increase of 7,000 in somatic cell counts in fresh milk. Samples held at 20–23 C beyond 2 days or at 4–7 C beyond 4 days showed a reduction in somatic cell count. The mean somatic cells in 3 Holstein herds tested over a 6-month period was 3.8 × 105/ml. A 22-month survey of 52.6 thousand Utah Dairy Herd Improvement samples which were shipped under ambient conditions and then held at 5 C until tested, indicated 75% below 400,000 and 2.7% above 1.6 million somatic cells/ml. Casein, noncasein protein, total protein, fat and milk weight data were also obtained on the three herds. Multiple correlations were obtained. The best correlations suggested that testing for total protein and somatic cells in a central laboratory would estimate casein and noncasein protein. Such tests are most valuable for the cheese industry.

Sign in / Sign up

Export Citation Format

Share Document