Support Vector Machine on fluorescence landscapes for breast cancer diagnostics

Detection of Escherichia coli Using Bacteriophage T7 and Analysis of Excitation‑Emission Matrix Fluorescence Spectroscopy

Conventional detection methods require the isolation and enrichment of bacteria, followed by molecular, biochemical, or culture-based analysis. To address some of the limitations of conventional methods, this study develops a machine learning (ML) approach to analyze the excitation-emission matrix (EEM) fluorescence data generated based on bacteriophage T7 and Escherichia coli interactions for in-situ detection of live bacteria in the presence of fresh produce homogenate. We trained classification models using various ML algorithms based on the 3-D EEM data generated with bacteria and their interactions with a T7 phage. These ML algorithms, including linear Support Vector Classifier (SVC) and Random Forest (RF), demonstrate high accuracy (>0.85) for detecting E. coli at 102 CFU/ml concentration within 6 h. Additionally, these ML models can differentiate among different E. coli concentration levels. For example, the Gaussian Process model achieved an accuracy of 92% in detecting different concentration levels of live E. coli. Application of these ML methods to detect E. coli in spinach homogenate yielded an accuracy of 89% using the linear-SVC model. Furthermore, feature selection techniques were employed to reduce the dimensionality of the data, revealing that only six features were necessary for achieving classification accuracy (>0.85) of spinach homogenate samples containing 102 CFU/ml of E. coli. These findings highlight the potential of this novel bacterial detection methodology, offering rapid, specific, and efficient solutions for applications in food safety and environmental monitoring.

Fluorescence Spectroscopy With Temperature Functional Tests in the Assessment of Markers of Intracellular Energy Metabolism: Spatial Heterogeneity and Reproducibility of Measurements

The fluorescence intensities of the cellular respiratory cofactors NADH (reduced nicotinamide adenine dinucleotide) and FAD++ (oxidized flavin adenine dinucleotide) reflect energy metabolism in skin and other tissues and can be quantified in vivo by fluorescence spectroscopy (FS). However, the variability of physiological parameters largely determines the reproducibility of measurement results and the reliability of the diagnostic test. In this prospective study, we evaluated the interday reproducibility of NADH and FAD++ fluorescence intensity measurements in the skin of 51 healthy volunteers assessed by the FS at baseline, after local cooling (10°C) and heating of the skin (35°C). Results showed that the fluorescence amplitude of NADH (AFNADH) in forearm skin was the most reproducible of the FS parameters studied. Assessment of AFNADH in the dorsal forearm in combination with a thermal functional test is the most promising method for clinical use for assessing energy metabolism in the skin.

Indocyanine green fluorescence image processing techniques for breast cancer macroscopic demarcation

Re-operation due to disease being inadvertently close to the resection margin is a major challenge in breast conserving surgery (BCS). Indocyanine green (ICG) fluorescence imaging could be used to visualize the tumor boundaries and help surgeons resect disease more efficiently. In this work, ICG fluorescence and color images were acquired with a custom-built camera system from 40 patients treated with BCS. Images were acquired from the tumor in-situ, surgical cavity post-excision, freshly excised tumor and histopathology tumour grossing. Fluorescence image intensity and texture were used as individual or combined predictors in both logistic regression (LR) and support vector machine models to predict the tumor extent. ICG fluorescence spectra in formalin-fixed histopathology grossing tumor were acquired and analyzed. Our results showed that ICG remains in the tissue after formalin fixation. Therefore, tissue imaging could be validated in freshly excised and in formalin-fixed grossing tumor. The trained LR model with combined fluorescence intensity (pixel values) and texture (slope of power spectral density curve) identified the tumor's extent in the grossing images with pixel-level resolution and sensitivity, specificity of 0.75 ± 0.3, 0.89 ± 0.2.This model was applied on tumor in-situ and surgical cavity (post-excision) images to predict tumor presence.

Excitation–emission matrix fluorescence spectroscopy for cell viability testing in UV-treated cell culture

Monitoring of cells viability is essential in a number of biomedical applications, including cell-based sensors, cell-based microsystems, and cell-based assays. The use of spectroscopic techniques for such purposes is especially advantageous since they are non-invasive, label-free, and non-destructive. However, such an approach must include chemometric analysis of the data to assess the information on cells viability. In the presented article we demonstrate, that excitation–emission matrix (EEM) fluorescence spectroscopy can be applied for reliable determination of cells viability due to the high correlation of EEM fluorescence data with the MTT test data. A375 cells (malignant melanoma) were exposed to UV radiation as a physical stress factor, resulting in a decrease of viability up to ca. 20%, confirmed by the standard MTT test. They were also characterized by means of EEM fluorescence spectroscopy coupled with unfolded partial least squares (UPLS) regression. Statistical evaluation revealed high accordance of the two methods of viability testing in terms of accuracy, precision, and correlation. The presented results are very promising for the development of spectroscopic soft sensors that can be applied for drug screening, biocompatibility testing, tissue engineering, and pharmacodynamic studies.

Excitation-emission matrix fluorescence spectroscopy can be applied for label-free and non-destructive determination of cells viability, which is promising methodology for drug screening, biocompatibility testing, or pharmacodynamic studies.

Macroscopic and microscopic fluorescence spectroscopy of colorectal benign and malignant lesions - diagnostically important features

Fluorescence spectroscopy is a sensitive, fast and non-invasive tool for a diagnostics of cancerous gastrointestinal lesions. It could be applied for in situ detection of tumours during primary endoscopic observations or as add-on measurement modality during microscopic observations of tissue histology slides for their initial or retrospective diagnosis. Therefore, we are looking for diagnostically important features of normal and cancerous tissue areas in a broad spectral range for gastrointestinal tissues ex vivo using two steady-state macroscopic fluorescent spectroscopic modalities and by confocal fluorescent microscopic detection. Results obtained from autofluorescence spectroscopy of benign and malignant lower part gastrointestinal tract (GIT) lesions from freshly excised tissues during surgical removal of the lesions in 18 patients (22 lesions), were compared with the spectral measurements obtained during confocal fluorescent microscopy observations of unstained tissue slides using 405 nm excitation. Excitation-emission matrices (EEMs) were used for ex vivo measurements with applied excitation in 280-440 nm spectral region and emission observed between 300 and 700 nm. Synchronous fluorescence spectroscopy (SFS) approach was also applied to improve the spectral resolution of the observed complex emission spectra. Specific fluorescent features observed, related to presence of structural proteins, co-enzymes and endogenous porphyrins in the tissues investigated, allow discriminating normal mucosa from benign polyps and malignant carcinoma lesions with diagnostic accuracy up to 94.4%.

Diagnostic Accuracy of Different Machine Learning Algorithms for Breast Cancer Risk Calculation: a Meta-Analysis

Objective: The aim of this study was to determine the diagnostic accuracy of different machine learning algorithms for breast cancer risk calculation. Methods: A meta-analysis was conducted of published research articles on diagnostic test accuracy of different machine learning algorithms for breast cancer risk calculation published between January 2000 and May 2018 in the online article databases of PubMed, ProQuest and EBSCO. Paired forest plots were employed for the analysis. Numerical values for sensitivity and specificity were obtained from false negative (FN), false positive (FP), true negative (TN) and true positive (TP) rates, presented alongside graphical representations with boxes marking the values and horizontal lines showing the confidence intervals (CIs). Summary receiver operating characteristic (SROC) curves were applied to assess the performance of diagnostic tests. Data were processed using Review Manager 5.3 (RevMan 5.3). Results: A total of 1,879 articles were reviewed, of which 11 were selected for systematic review and meta-analysis. Fve algorithms for machine learning able to predict breast cancer risk were identified: Super Vector Machine (SVM); Artificial Neural Networks (ANN); Decision Tree (DT); Naive Bayes (NB); and K-Nearest Neighbor (KNN). With the SVM, the Area Under Curve (AUC) from the SROC was > 90%, therefore classified into the excellent category. Conclusion: The meta-analysis confirmed that the SVM algorithm is able to calculate breast cancer risk with better accuracy value than other machine learning algorithms.

Analysis of dilute aqueous multifluorophoric mixtures using excitation-emission matrix fluorescence (EEMF) and total synchronous fluorescence (TSF) spectroscopy: a comparative evaluation

Excitation-emission matrix fluorescence (EEMF) and total synchronous fluorescence (TSF) spectroscopy are two conceptually different fluorescence techniques that have been used to map the fluorescence responses of the fluorophores present in a multifluorophoric mixture. EEMF was introduced four decades back and most of the fluorimeters have the suitable computer program which allows the acquisition EEMF spectra. Recently introduced TSF spectroscopy has been shown to possess good application potential in analytical fluorimetry and has started attracting the attention of analytical chemists. TSF data structure, however, is intrinsically different from EEMF data structure and a better understanding of TSF data structure is crucial to utilising its application potential. In the present work, a comprehensive comparative study between EEMF and TSF spectroscopic data set was performed by taking aqueous mixtures containing low concentrations of benzo[a]pyrene, chrysene, and pyrene as test case. The EEMF and TSF data structures were clearly explained by taking pyrene as an example. The effects of Rayleigh and Raman scattering on the quality of EEMF and TSF data sets were studied. EEMF and TSF data sets of dilute aqueous mixtures of benzo[a]pyrene, chrysene, and pyrene were subjected to three chemometric techniques PARAFAC, N-PLS, and MCR-ALS analysis. TSF data set in particular was found to be highly attuned to MCR-ALS analysis. Obtained results of chemometric analyses on EEMF and TSF data sets show that TSF data of dilute aqueous mixtures provides more accurate spectral and concentration information than EEMF data sets. Therefore, TSF spectroscopy could be considered as an alternate to the EEMF for the analyses of dilute multifluorophoric mixtures.

Application of parallel factor analysis to total synchronous fluorescence spectrum of dilute multifluorophoric solutions: addressing the issue of lack of trilinearity in total synchronous fluorescence data set

In recent years, total synchronous fluorescence (TSF) spectroscopy has become popular for the analysis of multifluorophoric systems. Application of PARAFAC, a popular deconvolution tool, requires trilinear structure in the three-way data array. The present work shows that TSF based three-way array data set of dimension sample × wavelength × Δλ does not have trilinear structure and hence it should not be subjected to PARAFAC analysis. This work also proposes that a TSF data set can be converted to an excitation-emission matrix fluorescence (EEMF) like data set which has trilinear structure, so that PARAFAC analysis can be performed on it. This also enables the retrieval of PARAFAC-separated component TSF spectra.