Label-free multi-class classification of phytoplankton based on quantitative phase time-stretch imaging (Conference Presentation)

2018 ◽  
Author(s):  
Queenie Tsz Kwan K. Lai ◽  
Kelvin C. M. Lee ◽  
Kenneth K. Y. Wong ◽  
Kevin K. Tsia
Keyword(s):  
Label Free ◽  
Quantitative Phase ◽  
Phase Time ◽  
Multi Class Classification

scholarly journals Deep learning classification of lipid droplets in quantitative phase images

2020 ◽  
Author(s):  
L. Sheneman ◽  
G. Stephanopoulos ◽  
A. E. Vasdekis
Keyword(s):  
Machine Learning ◽  
Lipid Droplets ◽  
Phase Imaging ◽  
Label Free ◽  
Quantitative Phase Imaging ◽  
Learning Methods ◽  
Quantitative Phase ◽  
Machine Learning Methods ◽  
Phase Images

AbstractWe report the application of supervised machine learning to the automated classification of lipid droplets in label-free, quantitative-phase images. By comparing various machine learning methods commonly used in biomedical imaging and remote sensing, we found convolutional neural networks to outperform others, both quantitatively and qualitatively. We describe our imaging approach, all machine learning methods that we implemented, and their performance in computational requirements, training resource needs, and accuracy. Overall, our results indicate that quantitative-phase imaging coupled to machine learning enables accurate lipid droplet classification in single living cells. As such, the present paradigm presents an excellent alternative of the more common fluorescent and Raman imaging modalities by enabling label-free, ultra-low phototoxicity and deeper insight into the thermodynamics of metabolism of single cells.Author SummaryRecently, quantitative-phase imaging (QPI) has demonstrated the ability to elucidate novel parameters of cellular physiology and metabolism without the need for fluorescent staining. Here, we apply label-free, low photo-toxicity QPI to yeast cells in order to identify lipid droplets (LDs), an important organelle with key implications in human health and biofuel development. Because QPI yields low specificity, we explore the use of modern machine learning methods to rapidly identify intracellular LDs with high discriminatory power and accuracy. In recent years, machine learning has demonstrated exceptional abilities to recognize and segment objects in biomedical imaging, remote sensing, and other areas. Trained machine learning classifiers can be combined with QPI within high-throughput analysis pipelines, allowing for efficient and accurate identification and quantification of cellular components. Non-invasive, accurate and high-throughput classification of these organelles will accelerate research and improve our understanding of cellular functions with beneficial applications in biofuels, biomedicine, and more.

scholarly journals Deep learning classification of lipid droplets in quantitative phase images

PLoS ONE ◽  
2021 ◽  
Vol 16 (4) ◽  
pp. e0249196
Author(s):  
Luke Sheneman ◽  
Gregory Stephanopoulos ◽  
Andreas E. Vasdekis
Keyword(s):  
Machine Learning ◽  
Lipid Droplets ◽  
Supervised Machine Learning ◽  
Label Free ◽  
Learning Methods ◽  
Method Performance ◽  
Quantitative Phase ◽  
Machine Learning Methods ◽  
Phase Images

We report the application of supervised machine learning to the automated classification of lipid droplets in label-free, quantitative-phase images. By comparing various machine learning methods commonly used in biomedical imaging and remote sensing, we found convolutional neural networks to outperform others, both quantitatively and qualitatively. We describe our imaging approach, all implemented machine learning methods, and their performance with respect to computational efficiency, required training resources, and relative method performance measured across multiple metrics. Overall, our results indicate that quantitative-phase imaging coupled to machine learning enables accurate lipid droplet classification in single living cells. As such, the present paradigm presents an excellent alternative of the more common fluorescent and Raman imaging modalities by enabling label-free, ultra-low phototoxicity, and deeper insight into the thermodynamics of metabolism of single cells.

A Study on Multi Class Classification from Breast Cancer Images using Ensemble Network and Transfer Learning

2020 ◽  
Vol 14 ◽  
Author(s):  
Lahari Tipirneni ◽  
Rizwan Patan
Keyword(s):  
Breast Cancer ◽  
Neural Network ◽  
Convolutional Neural Network ◽  
Binary Classification ◽  
Disease Diagnosis ◽  
Feature Descriptors ◽  
Histopathological Images ◽  
Viable Approach ◽  
Multi Class Classification

Abstract:: Millions of deaths all over the world are caused by breast cancer every year. It has become the most common type of cancer in women. Early detection will help in better prognosis and increases the chance of survival. Automating the classification using Computer-Aided Diagnosis (CAD) systems can make the diagnosis less prone to errors. Multi class classification and Binary classification of breast cancer is a challenging problem. Convolutional neural network architectures extract specific feature descriptors from images, which cannot represent different types of breast cancer. This leads to false positives in classification, which is undesirable in disease diagnosis. The current paper presents an ensemble Convolutional neural network for multi class classification and Binary classification of breast cancer. The feature descriptors from each network are combined to produce the final classification. In this paper, histopathological images are taken from publicly available BreakHis dataset and classified between 8 classes. The proposed ensemble model can perform better when compared to the methods proposed in the literature. The results showed that the proposed model could be a viable approach for breast cancer classification.

Label-free metabolic clustering through unsupervised pixel classification of multiparametric fluorescent images

2020 ◽  
Author(s):  
Giada Bianchetti ◽  
Fabio Ciccarone ◽  
Maria Rosa Ciriolo ◽  
Marco De Spirito ◽  
Giovambattista Pani ◽  
...  
Keyword(s):  
Label Free ◽  
Pixel Classification

scholarly journals Characterization of Liposomes Using Quantitative Phase Microscopy (QPM)

Pharmaceutics ◽  
2021 ◽  
Vol 13 (5) ◽  
pp. 590
Author(s):  
Jennifer Cauzzo ◽  
Nikhil Jayakumar ◽  
Balpreet Singh Ahluwalia ◽  
Azeem Ahmad ◽  
Nataša Škalko-Basnet
Keyword(s):  
Rapid Development ◽  
Fluorescent Labeling ◽  
Label Free ◽  
Batch Mode ◽  
Full Field ◽  
Quantitative Phase ◽  
Phase Microscopy ◽  
Quantitative Phase Microscopy ◽  
Tracking Ability

The rapid development of nanomedicine and drug delivery systems calls for new and effective characterization techniques that can accurately characterize both the properties and the behavior of nanosystems. Standard methods such as dynamic light scattering (DLS) and fluorescent-based assays present challenges in terms of system’s instability, machine sensitivity, and loss of tracking ability, among others. In this study, we explore some of the downsides of batch-mode analyses and fluorescent labeling, while introducing quantitative phase microscopy (QPM) as a label-free complimentary characterization technique. Liposomes were used as a model nanocarrier for their therapeutic relevance and structural versatility. A successful immobilization of liposomes in a non-dried setup allowed for static imaging conditions in an off-axis phase microscope. Image reconstruction was then performed with a phase-shifting algorithm providing high spatial resolution. Our results show the potential of QPM to localize subdiffraction-limited liposomes, estimate their size, and track their integrity over time. Moreover, QPM full-field-of-view images enable the estimation of a single-particle-based size distribution, providing an alternative to the batch mode approach. QPM thus overcomes some of the drawbacks of the conventional methods, serving as a relevant complimentary technique in the characterization of nanosystems.

Label-free non-invasive classification of rice seeds using optical coherence tomography assisted with deep neural network

2021 ◽  
Vol 137 ◽  
pp. 106861
Author(s):  
Deepa Joshi ◽  
Ankit Butola ◽  
Sheetal Raosaheb Kanade ◽  
Dilip K. Prasad ◽  
S.V. Amitha Mithra ◽  
...  
Keyword(s):  
Neural Network ◽  
Optical Coherence Tomography ◽  
Deep Neural Network ◽  
Optical Coherence ◽  
Label Free ◽  
Non Invasive ◽  
Rice Seeds
Sign in / Sign up

Export Citation Format

Share Document