A Review on Data Fusion of Multidimensional Medical and Biomedical Data.

Data fusion aims to provide a more accurate description of a sample than any one source of data alone. At the same time, data fusion minimizes the uncertainty of the results by combining data from multiple sources. Both aim to improve the characterization of samples and might improve clinical diagnosis and prognosis. In this paper, we present an overview of the advances achieved over the last decades in data fusion approaches in the context of the medical and biomedical fields. We collected approaches for interpreting multiple sources of data in different combinations: image to image, image to biomarker, spectra to image, spectra to spectra, spectra to biomarker, and others. We found that the most prevalent combination is the image-to-image fusion and that most data fusion approaches were applied together with deep learning or machine learning methods.

Nondestructive molecular imaging by Raman spectroscopy vs. marker detection by MALDI IMS for an early diagnosis of HCC.

Hepatocellular carcinoma (HCC) is a leading cause of cancer-related deaths worldwide with a steadily increasing mortality rate. Fast diagnosis at early stages of HCC is of key importance for the improvement of patient survival rates. In this regard, we combined two imaging techniques with high potential for HCC diagnosis in order to improve the prediction of liver cancer. In detail, Raman spectroscopic imaging and matrix-assisted laser desorption ionization imaging mass spectrometry (MALDI IMS) were applied for the diagnosis of 36 HCC tissue samples. The data were analyzed using multivariate methods, and the results revealed that Raman spectroscopy alone showed a good capability for HCC tumor identification (sensitivity of 88% and specificity of 80%), which could not be improved by combining the Raman data with MALDI IMS. In addition, it could be shown that the two methods in combination can differentiate between well-, moderately- and poorly-differentiated HCC using a linear classification model. MALDI IMS not only classified the HCC grades with a sensitivity of 100% and a specificity of 80%, but also showed significant differences in the expression of glycerophospholipids and fatty acyls during HCC differentiation. Furthermore, important differences in the protein, lipid and collagen compositions of differentiated HCC were detected using the model coefficients of a Raman based classification model. Both Raman and MALDI IMS, as well as their combination showed high potential for resolving concrete questions in liver cancer diagnosis.

Towards Raman spectroscopy of urine as screening tool.

For the screening purposes urine is an especially attractive biofluid, since it offers easy and noninvasive sample collection and provides a snapshot of the whole metabolic status of the organism, which may change under different pathological conditions. Raman spectroscopy (RS) has the potential to monitor these changes and utilize them for disease diagnostics. The current study utilizes mouse models aiming to compare the feasibility of the urine based RS combined with chemometrics for diagnosing kidney diseases directly influencing urine composition and respiratory tract diseases having no direct connection to urine formation. The diagnostic models for included diseases were built using principal component analysis with linear discriminant analysis and validated with a leave-one-mouse-out cross-validation approach. Considering kidney disorders, the accuracy of 100% was obtained in discrimination between sick and healthy mice, as well as between two different kidney diseases. For asthma and invasive pulmonary aspergillosis achieved accuracies were noticeably lower, being, respectively, 77.27% and 78.57%. In conclusion, our results suggest that RS of urine samples not only provides a solution for a rapid, sensitive and noninvasive diagnosis of kidney disorders, but also holds some promises for the screening of nonurinary tract diseases.

Surface enhanced Raman spectroscopy-detection of the uptake of mannose-modified nanoparticles by macrophages in vitro: A model for detection of vulnerable atherosclerotic plaques.

Atherosclerosis is a process of thickening and stiffening of the arterial walls through the accumulation of lipids and fibrotic material, as a consequence of aging and unhealthy life style. However, not all arterial plaques lead to complications, which can lead to life-threatening events such as stroke and myocardial infarction. Diagnosis of the disease in early stages and identification of unstable atherosclerotic plaques are still challenging. It has been shown that the development of atherosclerotic plaques is an inflammatory process, where the accumulation of macrophages in the arterial walls is immanent in the early as well as late stages of the disease. We present a novel surface enhanced Raman spectroscopy (SERS)-based strategy for the detection of early stage atherosclerosis, based on the uptake of tagged gold nanoparticles by macrophages and subsequent detection by means of SERS. The results presented here provide a basis for future in vivo studies in animal models.The workflow of tracing the SERS-active nanoparticle uptake by macrophages employing confocal Raman imaging.