CARS Imaging Advances Early Diagnosis of Cardiac Manifestation of Fabry Disease.

Vibrational spectroscopy can detect characteristic biomolecular signatures and thus has the potential to support diagnostics. Fabry disease (FD) is a lipid disorder disease that leads to accumulations of globotriaosylceramide in different organs, including the heart, which is particularly critical for the patient's prognosis. Effective treatment options are available if initiated at early disease stages, but many patients are late- or under-diagnosed. Since Coherent anti-Stokes Raman (CARS) imaging has a high sensitivity for lipid/protein shifts, we applied CARS as a diagnostic tool to assess cardiac FD manifestation in an FD mouse model. CARS measurements combined with multivariate data analysis, including image preprocessing followed by image clustering and data-driven modeling, allowed for differentiation between FD and control groups. Indeed, CARS identified shifts of lipid/protein content between the two groups in cardiac tissue visually and by subsequent automated bioinformatic discrimination with a mean sensitivity of 90-96%. Of note, this genotype differentiation was successful at a very early time point during disease development when only kidneys are visibly affected by globotriaosylceramide depositions. Altogether, the sensitivity of CARS combined with multivariate analysis allows reliable diagnostic support of early FD organ manifestation and may thus improve diagnosis, prognosis, and possibly therapeutic monitoring of FD.

Vibrational Spectroscopic Investigation of Blood Plasma and Serum by Drop Coating Deposition for Clinical Application.

In recent decades, vibrational spectroscopic methods such as Raman and FT-IR spectroscopy are widely applied to investigate plasma and serum samples. These methods are combined with drop coating deposition techniques to pre-concentrate the biomolecules in the dried droplet to improve the detected vibrational signal. However, most often encountered challenge is the inhomogeneous redistribution of biomolecules due to the coffee-ring effect. In this study, the variation in biomolecule distribution within the dried-sample droplet has been investigated using Raman and FT-IR spectroscopy and fluorescence lifetime imaging method. The plasma-sample from healthy donors were investigated to show the spectral differences between the inner and outer-ring region of the dried-sample droplet. Further, the preferred location of deposition of the most abundant protein albumin in the blood during the drying process of the plasma has been illustrated by using deuterated albumin. Subsequently, two patients with different cardiac-related diseases were investigated exemplarily to illustrate the variation in the pattern of plasma and serum biomolecule distribution during the drying process and its impact on patient-stratification. The study shows that a uniform sampling position of the droplet, both at the inner and the outer ring, is necessary for thorough clinical characterization of the patient's plasma and serum sample using vibrational spectroscopy.

Discrimination between pathogenic and non-pathogenic E. coli strains by means of Raman microspectroscopy.

Bacteria can be harmless commensals, beneficial probiotics, or harmful pathogens. Therefore, mankind is challenged to detect and identify bacteria in order to prevent or treat bacterial infections. Examples are identification of species for treatment of infection in clinics and E. coli cell counting for water quality monitoring. Finally, in some instances, the pathogenicity of a species is of interest. The main strategies to investigate pathogenicity are detection of target genes which encode virulence factors. Another strategy could be based on phenotypic identification. Raman spectroscopy is a promising phenotypic method, which offers high sensitivities and specificities for the identification of bacteria species. In this study, we evaluated whether Raman microspectroscopy could be used to determine the pathogenicity of E. coli strains. We used Raman spectra of seven non-pathogenic and seven pathogenic E. coli strains to train a PCA-SVM model. Then, the obtained model was tested by identifying the pathogenicity of three additional E. coli strains. The pathogenicity of these three strains could be correctly identified with a mean sensitivity of 77%, which is suitable for a fast screening of pathogenicity of single bacterial cells. Graphical abstract.

WE-ASCA: The Weighted-Effect ASCA for Analyzing Unbalanced Multifactorial Designs-A Raman Spectra-Based Example.

Analyses of multifactorial experimental designs are used as an explorative technique describing hypothesized multifactorial effects based on their variation. The procedure of analyzing multifactorial designs is well established for univariate data, and it is known as analysis of variance (ANOVA) tests, whereas only a few methods have been developed for multivariate data. In this work, we present the weighted-effect ASCA, named WE-ASCA, as an enhanced version of ANOVA-simultaneous component analysis (ASCA) to deal with multivariate data in unbalanced multifactorial designs. The core of our work is to use general linear models (GLMs) in decomposing the response matrix into a design matrix and a parameter matrix, while the main improvement in WE-ASCA is to implement the weighted-effect (WE) coding in the design matrix. This WE-coding introduces a unique solution to solve GLMs and satisfies a constrain in which the sum of all level effects of a categorical variable equal to zero. To assess the WE-ASCA performance, two applications were demonstrated using a biomedical Raman spectral data set consisting of mice colorectal tissue. The results revealed that WE-ASCA is ideally suitable for analyzing unbalanced designs. Furthermore, if WE-ASCA is applied as a preprocessing tool, the classification performance and its reproducibility can significantly improve.

Sample-Size Planning for Multivariate Data: A Raman-Spectroscopy-Based Example.

The goal of sample-size planning (SSP) is to determine the number of measurements needed for statistical analysis. This SSP is necessary to achieve robust and significant results with a minimal number of measurements that need to be collected. SSP is a common procedure for univariate measurements, whereas for multivariate measurements, like spectra or time traces, no general sample-size-planning method exists. Sample-size planning becomes more important for biospectroscopic data because the data generation is time-consuming and costly. Additionally, ethical reasons do not allow the use of unnecessary samples and the measurement of unnecessary spectra. In this paper, a general sample-size-planning algorithm is presented that is based on learning curves. The learning curve quantifies the improvement of a classifier for an increasing training-set size. These curves are fitted by the inverse-power law, and the parameters of this fit can be utilized to predict the necessary training-set size. Sample-size planning is demonstrated for a biospectroscopic task of differentiating six different bacterial species, including Escherichia coli, Klebsiella terrigena, Pseudomonas stutzeri, Listeria innocua, Staphylococcus warneri, and Staphylococcus cohnii, on the basis of their Raman spectra. Thereby, we estimate the required number of Raman spectra and biological replicates to train a classification model, which consists of principal-component analysis (PCA) combined with linear-discriminant analysis (LDA). The presented algorithm revealed that 142 Raman spectra per species and seven biological replicates are needed for the above-mentioned biospectroscopic-classification task. Even though it was not demonstrated, the learning-curve-based sample-size-planning algorithm can be applied to any multivariate data and in particular to biospectroscopic-classification tasks.

Deep learning-based classification of blue light cystoscopy imaging during transurethral resection of bladder tumors.

Bladder cancer is one of the top 10 frequently occurring cancers and leads to most cancer deaths worldwide. Recently, blue light (BL) cystoscopy-based photodynamic diagnosis was introduced as a unique technology to enhance the detection of bladder cancer, particularly for the detection of flat and small lesions. Here, we aim to demonstrate a BL image-based artificial intelligence (AI) diagnostic platform using 216 BL images, that were acquired in four different urological departments and pathologically identified with respect to cancer malignancy, invasiveness, and grading. Thereafter, four pre-trained convolution neural networks were utilized to predict image malignancy, invasiveness, and grading. The results indicated that the classification sensitivity and specificity of malignant lesions are 95.77% and 87.84%, while the mean sensitivity and mean specificity of tumor invasiveness are 88% and 96.56%, respectively. This small multicenter clinical study clearly shows the potential of AI based classification of BL images allowing for better treatment decisions and potentially higher detection rates.