Search

Abstract 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.

The antibiotic resistance of bacterial pathogens has become one of the most serious global health issues due to misusing and overusing of antibiotics. Recently, different technologies were developed to determine bacteria susceptibility towards antibiotics; however, each of these technologies has its advantages and limitations in clinical applications. In this contribution, we aim to assess and automate the detection of bacterial susceptibilities towards three antibiotics; i.e. ciprofloxacin, cefotaxime and piperacillin using a combination of image processing and machine learning algorithms. Therein, microscopic images were collected from different E. coli strains, then the convolutional neural network U-Net was implemented to segment the areas showing bacteria. Subsequently, the encoder part of the trained U-Net was utilized as a feature extractor, and the U-Net bottleneck features were utilized to predict the antibiotic susceptibility of E. coli strains using a one-class support vector machine (OCSVM). This one-class model was always trained on images of untreated controls of each bacterial strain while the image labels of treated bacteria were predicted as control or non-control images. If an image of treated bacteria is predicted as control, we assume that these bacteria resist this antibiotic. In contrast, the sensitive bacteria show different morphology of the control bacteria; therefore, images collected from these treated bacteria are expected to be classified as non-control. Our results showed 83% area under the receiver operating characteristic (ROC) curve when OCSVM models were built using the U-Net bottleneck features of control bacteria images only. Additionally, the mean sensitivities of these one-class models are 91.67% and 86.61% for cefotaxime and piperacillin; respectively. The mean sensitivity for the prediction of ciprofloxacin is only 59.72% as the bacteria morphology was not fully detected by the proposed method.

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.

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.

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.