LDA vs. QDA for FT-MIR prostate cancer tissue classification

Siqueira, Laurinda Fernanda Saldanha; Júnior, Raimundo F. Araújo; Araújo, Aurigena Antunes de; Morais, Camilo L. M.; Lima, Kássio M. G.

doi:10.1016/j.chemolab.2017.01.021

Cited by 63 publications

(32 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Usually, the first LDA factor is used to visualise the main biochemical alterations within the sample on a 1-D scores plot. The optimum number of variables for SPA-LDA and GA-LDA was determined by the minimum cost function G calculated for a given validation dataset as:where N V is the number of validation samples and g n is defined as:in which r 2 ( x n , m I ( n ) ) is the squared Mahalanobis distance between object x n (of class index I ( n )) and the centre of its true class ( m I ( n ) ), and r 2 ( x n , m I ( m ) ) is the squared Mahalanobis distance between object x n and the centre of the closest wrong class ( m I ( m ) ) [36]. …”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Synchrotron- and focal plane array-based Fourier-transform infrared spectroscopy differentiates the basalis and functionalis epithelial endometrial regions and identifies putative stem cell regions of human endometrial glands

et al. 2018

View full text Add to dashboard Cite

The cyclical process of regeneration of the endometrium suggests that it may contain a cell population that can provide daughter cells with high proliferative potential. These cell lineages are clinically significant as they may represent clonogenic cells that may also be involved in tumourigenesis as well as endometriotic lesion development. To determine whether the putative stem cell location within human uterine tissue can be derived using vibrational spectroscopy techniques, normal endometrial tissue was interrogated by two spectroscopic techniques. Paraffin-embedded uterine tissues containing endometrial glands were sectioned to 10-μm-thick parallel tissue sections and were floated onto BaF2 slides for synchrotron radiation-based Fourier-transform infrared (SR-FTIR) microspectroscopy and globar focal plane array-based FTIR spectroscopy. Different spectral characteristics were identified depending on the location of the glands examined. The resulting infrared spectra were subjected to multivariate analysis to determine associated biophysical differences along the length of longitudinal and crosscut gland sections. Comparison of the epithelial cellular layer of transverse gland sections revealed alterations indicating the presence of putative transient-amplifying-like cells in the basalis and mitotic cells in the functionalis. SR-FTIR microspectroscopy of the base of the endometrial glands identified the location where putative stem cells may reside at the same time pointing towards νsPO2− in DNA and RNA, nucleic acids and amide I and II vibrations as major discriminating factors. This study supports the view that vibration spectroscopy technologies are a powerful adjunct to our understanding of the stem cell biology of endometrial tissue. Graphical abstractᅟ Electronic supplementary materialThe online version of this article (10.1007/s00216-018-1111-x) contains supplementary material, which is available to authorized users.

show abstract

Section: Methodsmentioning

confidence: 99%

“…The quality metrics used in this study for evaluating the classification results can be calculated following the equations [36]:where FN is defined as false negative, FP as false positive, TP as true positive and TN as true negative.…”

Section: Methodsmentioning

confidence: 99%

Synchrotron- and focal plane array-based Fourier-transform infrared spectroscopy differentiates the basalis and functionalis epithelial endometrial regions and identifies putative stem cell regions of human endometrial glands

et al. 2018

View full text Add to dashboard Cite

show abstract

“…The most used ones are the accuracy (total number of samples correct classified considering true and false negatives), sensitivity (proportion of positivies correctly identified) and specificity (proportion of negatives correctly identified) [1]. Additional figures of merit can also be estimated to confirm the predictive performance of a classification model, such as precision (classifier ability to avoid wrong predictions), F-score (overall performance of the model considering imbalanced data), G-score (overall performance of the model not accounting for class sizes), area under the curve (AUC) of receiver operating characteristic curves, positive and negative prediction values, positive and negative likelihood ratios, and Youden's index [1][2][3][4][5]. The latter three are more commonly used for biomedical applications, where the ratio of true and false positives and negatives are an important factor towards making clinical decisions.…”

Section: Introductionmentioning

confidence: 99%

Uncertainty estimation and misclassification probability for classification models based on discriminant analysis and support vector machines

Morais

Lima

Martin

2019

Analytica Chimica Acta

Self Cite

View full text Add to dashboard Cite

show abstract

“…In classification applications, samples are assigned to groups based on their IR spectrochemical signature. This includes, for example, differentiation of brain tumour types (3), identification of neurodegenerative diseases (4), cervical cancer screening (5), endometrial and ovarian cancer identification (6), identification of prostate cancer tissue samples (7), differentiation of endometrial tissue regions (8), toxicology screening (9,10), and microbiologic studies involving fungi and virus identification (11)(12)(13). However, before model construction, a fundamental step is to split the spectral dataset into at least two subsets: training and test.…”

Section: Introductionmentioning

confidence: 99%

A computational protocol for sample selection in biological-derived infrared spectroscopy datasets using Morais-Lima-Martin (MLM) algorithm

Morais¹,

Lima²,

Martin³

2018

Protocol Exchange

View full text Add to dashboard Cite

Infrared (IR) spectroscopy is a powerful analytical technique that can be applied to investigate a wide range of biological materials (e.g., biofluids, cells, tissues), where a specific biochemical signature is obtained representing the 'fingerprint' signal of the sample being analysed. This chemical information can be used as an input data for classification models in order to distinguish or predict samples groups based on computational algorithms. One fundamental step towards building such computational models is sample selection, where a fraction of the samples measured during an experiment are used for building the classifier, whereas the remaining ones are used for evaluating the model classification performance. This protocol shows how sample selection can be performed in a computational environment (MATLAB) by using a combination of Euclidian-distance calculation and random selection, named Morais-Lima-Martin (MLM) algorithm, as a previous step before building classification models in biological-derived IR datasets.

show abstract

LDA vs. QDA for FT-MIR prostate cancer tissue classification

Cited by 63 publications

References 43 publications

Synchrotron- and focal plane array-based Fourier-transform infrared spectroscopy differentiates the basalis and functionalis epithelial endometrial regions and identifies putative stem cell regions of human endometrial glands

Synchrotron- and focal plane array-based Fourier-transform infrared spectroscopy differentiates the basalis and functionalis epithelial endometrial regions and identifies putative stem cell regions of human endometrial glands

Uncertainty estimation and misclassification probability for classification models based on discriminant analysis and support vector machines

A computational protocol for sample selection in biological-derived infrared spectroscopy datasets using Morais-Lima-Martin (MLM) algorithm

Contact Info

Product

Resources

About