scholarly journals High-throughput image labeling and quality control for clinical trials using machine learning

2018 ◽  
Vol 5 (4) ◽  
pp. 161
Author(s):  
Robert J. Harris ◽  
Pangyu Teng ◽  
Mahesh Nagarajan ◽  
Liza Shrestha ◽  
Xiang Lu ◽  
...  
Keyword(s):  
Clinical Trial ◽  
Quality Control ◽  
High Throughput ◽  
Human Error ◽  
Image Data ◽  
Neural Net ◽  
Image Series ◽  
High Throughput Method ◽  
Automated Methods ◽  
Optimal Series

<p class="abstract"><strong>Background:</strong> Manually importing and analyzing image data can be time-consuming, prone to human error, and costly for large clinical trial datasets. This can lead to delays in quality control (QC) feedback to imaging sites and in obtaining data analysis results. Herein we describe the creation and application of a high-throughput review process for import, classification, labeling and QC of large multimodal clinical trial image datasets.</p><p class="abstract"><strong>Methods:</strong> Automated methods were used to remove patient identifying information, extract image header data, and filter image data for usability. A convolutional neural net was applied to estimate anatomy for CT images. Internal scores were assigned for each image series to identify the optimal series for labeling and reading of each anatomical region. Image QC reports were automatically generated for all patients.</p><p class="abstract"><strong>Results:</strong> In combined studies for which 204,492 series were received, 27,841 series were identified as usable and 13,415 series were labeled. Using this high-throughput method, total work-hours required per time point were reduced by an approximate factor of ten when compared to traditional review and labeling methods. Our anatomic classification system identified 95.7% of image series correctly, with the remaining series being manually corrected before labeling and analysis.</p><p class="abstract"><strong>Conclusions: </strong>A high-throughput image analysis pipeline was implemented in a large combined dataset of clinical trial image series. This pipeline can be applied across other studies and modalities for fast image data characterization, labeling and QC.</p>

A new high-throughput method to make a quality control on tattoo inks

2019 ◽  
Vol 206 ◽  
pp. 547-551 ◽  
Author(s):  
S. Persechino ◽  
C. Toniolo ◽  
A. Ciccola ◽  
I. Serafini ◽  
A. Tammaro ◽  
...  
Keyword(s):  
Quality Control ◽  
High Throughput ◽  
High Throughput Method ◽  
Tattoo Inks

A Fluorescent High Throughput Method To Identify Potential Skin Sensitizers

Planta Medica ◽  
2016 ◽  
Vol 82 (05) ◽  
Author(s):  
C Avonto ◽  
AG Chittiboyina ◽  
D Rua ◽  
IA Khan
Keyword(s):  
High Throughput ◽  
High Throughput Method

scholarly journals High Throughput Centrifugal Electrospinning of Polyacrylonitrile Nanofibers for Carbon Fiber Nonwovens

Polymers ◽  
2021 ◽  
Vol 13 (8) ◽  
pp. 1313
Author(s):  
Andreas Hoffmann ◽  
Alexander J. C. Kuehne
Keyword(s):  
High Throughput ◽  
Carbon Nanofiber ◽  
Fiber Diameter ◽  
Carbon Precursor ◽  
Production Methods ◽  
High Throughput Method ◽  
Radial Forces ◽  
Fiber Deposition ◽  
The Impact ◽  
Pan Fibers

Carbon nanofiber nonwovens are promising materials for electrode or filtration applications; however, their utilization is obviated by a lack of high throughput production methods. In this study, we utilize a highly effective high-throughput method for the fabrication of polyacrylonitrile (PAN) nanofibers as a nonwoven on a dedicated substrate. The method employs rotational-, air pressure- and electrostatic forces to produce fibers from the inner edge of a rotating bell towards a flat collector. We investigate the impact of all above-mentioned forces on the fiber diameter, morphology, and bundling of the carbon-precursor PAN fibers. The interplay of radial forces with collector-facing forces has an influence on the uniformity of fiber deposition. Finally, the obtained PAN nanofibers are converted to carbon nonwovens by thermal treatment.

scholarly journals A neural network-based algorithm for high-throughput characterisation of viscoelastic properties of flowing microcapsules

Soft Matter ◽  
2021 ◽  
Author(s):  
Tao Lin ◽  
Zhen Wang ◽  
Wen Wang ◽  
Yi Sui
Keyword(s):  
Neural Network ◽  
High Throughput ◽  
Viscoelastic Properties ◽  
Dynamic Deformation ◽  
Membrane Elasticity ◽  
Hybrid Neural Network ◽  
High Throughput Method

We have developed a high-throughput method, by combining a hybrid neural network with a mechanistic capsule model, to predict membrane elasticity and viscosity of microcapsules from their dynamic deformation in a branched microchannel.

scholarly journals Development of a High-Throughput Method to Study the Inhibitory Effect of Phytochemicals on Trimethylamine Formation

Nutrients ◽  
2021 ◽  
Vol 13 (5) ◽  
pp. 1466
Author(s):  
Lisard Iglesias-Carres ◽  
Lauren A. Essenmacher ◽  
Kathryn C. Racine ◽  
Andrew P. Neilson
Keyword(s):  
Chlorogenic Acid ◽  
Gallic Acid ◽  
High Throughput ◽  
Anaerobic Fermentation ◽  
Inhibitory Effect ◽  
Healthy Human ◽  
High Throughput Method ◽  
Lyase Activity ◽  
Inhibitory Potential ◽  
Potential Maximum

Choline is metabolized by the gut microbiota into trimethylamine (TMA), the precursor of pro-atherosclerotic molecule trimethylamine N-oxide (TMAO). A reduction in TMA formation has shown cardioprotective effects, and some phytochemicals may reduce TMA formation. This study aimed to develop an optimized, high-throughput anaerobic fermentation methodology to study the inhibition of choline microbial metabolism into TMA by phenolic compounds with healthy human fecal starter. Optimal fermentation conditions were: 20% fecal slurry (1:10 in PBS), 100 µM choline, and 12 h fermentation. Additionally, 10 mM of 3,3-dimethyl-1-butanol (DMB) was defined as a positive TMA production inhibitor, achieving a ~50% reduction in TMA production. Gallic acid and chlorogenic acid reported higher TMA inhibitory potential (maximum of 80–90% TMA production inhibition), with IC50 around 5 mM. Neither DMB nor gallic acid or chlorogenic acid reduced TMA production through cytotoxic effects, indicating mechanisms such as altered TMA-lyase activity or expression.

scholarly journals Two-step machine learning method for the rapid analysis of microvascular flow in intravital video microscopy

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Ossama Mahmoud ◽  
Mahmoud El-Sakka ◽  
Barry G. H. Janssen
Keyword(s):  
Machine Learning ◽  
Blood Flow ◽  
Human Error ◽  
Image Data ◽  
Video Microscopy ◽  
Microvascular Blood Flow ◽  
Image Processing Algorithm ◽  
Step Algorithm ◽  
3D Cnn

AbstractMicrovascular blood flow is crucial for tissue and organ function and is often severely affected by diseases. Therefore, investigating the microvasculature under different pathological circumstances is essential to understand the role of the microcirculation in health and sickness. Microvascular blood flow is generally investigated with Intravital Video Microscopy (IVM), and the captured images are stored on a computer for later off-line analysis. The analysis of these images is a manual and challenging process, evaluating experiments very time consuming and susceptible to human error. Since more advanced digital cameras are used in IVM, the experimental data volume will also increase significantly. This study presents a new two-step image processing algorithm that uses a trained Convolutional Neural Network (CNN) to functionally analyze IVM microscopic images without the need for manual analysis. While the first step uses a modified vessel segmentation algorithm to extract the location of vessel-like structures, the second step uses a 3D-CNN to assess whether the vessel-like structures have blood flowing in it or not. We demonstrate that our two-step algorithm can efficiently analyze IVM image data with high accuracy (83%). To our knowledge, this is the first application of machine learning for the functional analysis of microvascular blood flow in vivo.

scholarly journals High-Throughput Chlorophyll and Carotenoid Profiling Reveals Positive Associations with Sugar and Apocarotenoid Volatile Content in Fruits of Tomato Varieties in Modern and Wild Accessions

Metabolites ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 398
Author(s):  
Yusuke Aono ◽  
Yonathan Asikin ◽  
Ning Wang ◽  
Denise Tieman ◽  
Harry Klee ◽  
...  
Keyword(s):  
High Throughput ◽  
Fruit Color ◽  
Wild Relatives ◽  
Aroma Compounds ◽  
Soluble Solids ◽  
Sugar Production ◽  
Volatile Content ◽  
Factors Influencing ◽  
High Throughput Method ◽  
Wild Accessions

Flavor and nutritional quality has been negatively impacted during the course of domestication and improvement of the cultivated tomato (Solanum lycopersicum). Recent emphasis on consumers has emphasized breeding strategies that focus on flavor-associated chemicals, including sugars, acids, and aroma compounds. Carotenoids indirectly affect flavor as precursors of aroma compounds, while chlorophylls contribute to sugar production through photosynthesis. However, the relationships between these pigments and flavor content are still unclear. In this study, we developed a simple and high-throughput method to quantify chlorophylls and carotenoids. This method was applied to over one hundred tomato varieties, including S. lycopersicum and its wild relatives (S. l. var. cerasiforme and S. pimpinellifolium), for quantification of these pigments in fruits. The results obtained by integrating data of the pigments, soluble solids, sugars, and aroma compounds indicate that (i) chlorophyll-abundant varieties have relatively higher sugar accumulations and (ii) prolycopene is associated with an abundance of linear carotenoid-derived aroma compounds in one of the orange-fruited varieties, “Dixie Golden Giant”. Our results suggest the importance of these pigments not only as components of fruit color but also as factors influencing flavor traits, such as sugars and aroma.

scholarly journals Fast and Efficient 5′P Degradome Library Preparation for Analysis of Co-Translational Decay in Arabidopsis

Plants ◽  
2021 ◽  
Vol 10 (3) ◽  
pp. 466
Author(s):  
Marie-Christine Carpentier ◽  
Cécile Bousquet-Antonelli ◽  
Rémy Merret
Keyword(s):  
Gene Expression ◽  
Quality Control ◽  
Transcriptional Regulation ◽  
High Throughput ◽  
Library Preparation ◽  
Working Day ◽  
Set Up ◽  
Post Transcriptional Regulation ◽  
Commercial Kit

The recent development of high-throughput technologies based on RNA sequencing has allowed a better description of the role of post-transcriptional regulation in gene expression. In particular, the development of degradome approaches based on the capture of 5′monophosphate decay intermediates allows the discovery of a new decay pathway called co-translational mRNA decay. Thanks to these approaches, ribosome dynamics could now be revealed by analysis of 5′P reads accumulation. However, library preparation could be difficult to set-up for non-specialists. Here, we present a fast and efficient 5′P degradome library preparation for Arabidopsis samples. Our protocol was designed without commercial kit and gel purification and can be easily done in one working day. We demonstrated the robustness and the reproducibility of our protocol. Finally, we present the bioinformatic reads-outs necessary to assess library quality control.

Sign in / Sign up

Export Citation Format

Share Document