Auto-classification for confocal back-scattering micro-spectrum at single-cell scale using principal component analysis

Wang, Cheng; Wen, Ming‐Shien; Li-hong, Bai; Zhang, Tong

doi:10.1016/j.ijleo.2015.10.066

Cited by 8 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dimensionality reduction has been proven to be a powerful tool for high-dimensional data analysis because it can eliminate the redundances among data samples and simultaneously extract useful features. In this paper, two dimensionality reduction methods, namely, principal component analysis (PCA) and partial least squares (PLS), were used to reduce the dimensions of the HMI datasets to improve the accuracy of the model and speed up the algorithms [ 16 , 17 ]. PCA is a widely used linear unsupervised method, which can convert a set of observations of possibly correlated variables into as few uncorrelated variables, named principal components, as possible to retain the characteristics of the original data to the maximum extent; however, PCA cannot predict the dependent variables well.…”

Section: Methodsmentioning

confidence: 99%

Staging of Skin Cancer Based on Hyperspectral Microscopic Imaging and Machine Learning

Liu

et al. 2022

Biosensors

View full text Add to dashboard Cite

Skin cancer, a common type of cancer, is generally divided into basal cell carcinoma (BCC), squamous cell carcinoma (SCC) and malignant melanoma (MM). The incidence of skin cancer has continued to increase worldwide in recent years. Early detection can greatly reduce its morbidity and mortality. Hyperspectral microscopic imaging (HMI) technology can be used as a powerful tool for skin cancer diagnosis by reflecting the changes in the physical structure and microenvironment of the sample through the differences in the HMI data cube. Based on spectral data, this work studied the staging identification of SCC and the influence of the selected region of interest (ROI) on the staging results. In the SCC staging identification process, the optimal result corresponded to the standard normal variate transformation (SNV) for spectra preprocessing, the partial least squares (PLS) for dimensionality reduction, the hold-out method for dataset partition and the random forest (RF) model for staging identification, with the highest staging accuracy of 0.952 ± 0.014, and a kappa value of 0.928 ± 0.022. By comparing the staging results based on spectral characteristics from the nuclear compartments and peripheral regions, the spectral data of the nuclear compartments were found to contribute more to the accurate staging of SCC.

show abstract

Section: Methodsmentioning

confidence: 99%

Staging of Skin Cancer Based on Hyperspectral Microscopic Imaging and Machine Learning

Liu

et al. 2022

Biosensors

View full text Add to dashboard Cite

show abstract

“…The PCA method is used to reduce the dimensionality. The main characteristics of the data are extracted by data decorrelation [19]. Then the main information is included in the first few principal components (PCs).…”

Section: Analysis and Identification Methodsmentioning

confidence: 99%

Rapid Classification of Single Bacterium Based on Backscattering Microscopic Spectrum—A Pilot Study

Wang

Liu

et al. 2020

Front. Phys.

Self Cite

View full text Add to dashboard Cite

Rapid detection of foodborne pathogens is one of the most effective ways to solve food safety problems. To achieve rapid and noninvasive detection and classification of foodborne pathogens, we modified a fiber confocal backscattering micro-spectral system to suit an extremely small biological sample, that is, a bacterium. This system offers single-bacterium level, label-free, convenient, and environmentally friendly characterization. Three categories of common foodborne pathogens (Salmonella typhimurium, Escherichia coli, and Staphylococcus aureus) were measured. The scattering spectrum ranging from 450 to 900 nm was selected, and by the model of principal component analysis (PCA) and error back propagation algorithm of back propagation neural network (BPNN), the backscattering microscopic spectra of three categories of pathogens were dimensionally reduced, identified, and classified. The results showed that the identification accuracy of three categories of pathogens was above 90%, under neutral, acidic, and alkaline culturing conditions, respectively. The preliminary results demonstrated the feasibility of using confocal backscattering microscopic spectra combined with PCA and BPNN algorithm to identify and classify single bacterium in a rapid, noninvasive, and label-free manner.

show abstract

“…It has been used in detecting pattern for features extraction and reduction of data size leading to increase the algorithm speed, also less storage space is needed and can reduce the calculation process and is sensitive to the scaling main variables. In the field of biomedical research PCA has a potential ability with the aim of using analysis of principal component of PCA to identify micro-spectrum of normal cells automatically and cancer cells obtained from confocal imaging [18].…”

Section: Classification Of Principal Component Analysis and K-nearestmentioning

confidence: 99%

Investigation of Different Algorithms for Surface Defects of Steel Sheet for Quality

Pishyar¹,

Emadi²

2016

IJCA

View full text Add to dashboard Cite

In the process of inspection and quality control of steel sheets which is considered as an important issue in the metal industry surface defects of metals is one of the reasons that reduces the quality of products, also the detection of different defects in raw metals with the naked eye is very difficult and given that in recent years, automatic surface inspection system has made remarkable progress and is deemed as the research's mainstream and while the accuracy of visual inspection of people is different there is a need to a rapid, accurate, and non-destructive way to identify and classify surface defects based on the texture and form of this product and guarantee metal quality in the production process ; also, increase the production rate and helps separating defective metal from normal metal in a very short period of time. The main purpose of examining surface automatically is to investigate defective parts by comparing the user requirements and the generated images to minimize the wastes led to the product rejection to be delivered steel with better quality to the customer. Accordingly, the expression of different methods and examine them.

show abstract

Auto-classification for confocal back-scattering micro-spectrum at single-cell scale using principal component analysis

Cited by 8 publications

References 16 publications

Staging of Skin Cancer Based on Hyperspectral Microscopic Imaging and Machine Learning

Staging of Skin Cancer Based on Hyperspectral Microscopic Imaging and Machine Learning

Rapid Classification of Single Bacterium Based on Backscattering Microscopic Spectrum—A Pilot Study

Investigation of Different Algorithms for Surface Defects of Steel Sheet for Quality

Contact Info

Product

Resources

About