Combining Extracellular miRNA Determination with Microfluidic 3D Cell Cultures for the Assessment of Nephrotoxicity: a Proof of Concept Study.

Drug-induced kidney injury is often observed in the clinics and can lead to long-term organ failure. In this work, we evaluated a novel in vitro system that aims at detecting whether compounds can cause renal proximal tubule damage in man. For this, we implemented organotypic cultures of human conditionally immortalized proximal tubule epithelial cells overexpressing the organic anion transporter 1 (ciPTEC-OAT1) in a three-channel OrganoPlate under microfluidic conditions. Cells were exposed to four known nephrotoxicants (cisplatin, tenofovir, cyclosporine A, and tobramycin). The effect on cell viability and NAG release into the medium was determined. A novel panel of four miRNAs (mir-21, mir-29a, mir-34a, and mir-192) was selected as potential biomarkers of proximal tubule damage. After nephrotoxicant treatment, miRNA levels in culture medium were earlier indicators than cell viability (WST-8 assay) and outperformed NAG for proximal tubule damage. In particular, mir-29a, mir-34a, and mir-192 were highly reproducible between experiments and across compounds, whereas mir-21 showed more variability. Moreover, similar data were obtained in two different laboratories, underlining the reproducibility and technical transferability of the results, a key requirement for the implementation of novel biomarkers. In conclusion, the selected miRNAs behaved like sensitive biomarkers of damage to tubular epithelial cells caused by several nephrotoxicity mechanisms. This biomarker panel, in combination with the 3D cultures of ciPTEC-OAT1 in the OrganoPlate, represents a novel tool for in vitro nephrotoxicity detection. These results pave the way for the application of miRNAs in longitudinal, time-course in vitro toxicity studies.

A machine-learning framework for automatic reference-free quality assessment in MRI.

Magnetic resonance (MR) imaging offers a wide variety of imaging techniques. A large amount of data is created per examination which needs to be checked for sufficient quality in order to derive a meaningful diagnosis. This is a manual process and therefore time- and cost-intensive. Any imaging artifacts originating from scanner hardware, signal processing or induced by the patient may reduce the image quality and complicate the diagnosis or any image post-processing. Therefore, the assessment or the ensurance of sufficient image quality in an automated manner is of high interest. Usually no reference image is available or difficult to define. Therefore, classical reference-based approaches are not applicable. Model observers mimicking the human observers (HO) can assist in this task. Thus, we propose a new machine-learning-based reference-free MR image quality assessment framework which is trained on HO-derived labels to assess MR image quality immediately after each acquisition. We include the concept of active learning and present an efficient blinded reading platform to reduce the effort in the HO labeling procedure. Derived image features and the applied classifiers (support-vector-machine, deep neural network) are investigated for a cohort of 250 patients. The MR image quality assessment framework can achieve a high test accuracy of 93.7% for estimating quality classes on a 5-point Likert-scale. The proposed MR image quality assessment framework is able to provide an accurate and efficient quality estimation which can be used as a prospective quality assurance including automatic acquisition adaptation or guided MR scanner operation, and/or as a retrospective quality assessment including support of diagnostic decisions or quality control in cohort studies.