A novel Slide-seq based image processing software to identify gene expression at the single cell level.

Analysis of gene expression at the single-cell level could help predict the effectiveness of therapies in the field of chronic inflammatory diseases such as arthritis. Here, we demonstrate an adopted approach for processing images from the Slide-seq method. Using a puck, which consists of about 50,000 DNA barcode beads, an RNA sequence of a cell is to be read. The pucks are repeatedly brought into contact with liquids and then recorded with a conventional epifluorescence microscope. The image analysis initially consists of stitching the partial images of a sequence recording, registering images from different sequences, and finally reading out the bases. The new method enables the use of an inexpensive epifluorescence microscope instead of a confocal microscope.

Comparing ensemble methods combined with different aggregating models using micrograph cell segmentation as an initial application example.

Strategies such as ensemble learning and averaging techniques try to reduce the variance of single deep neural networks. The focus of this study is on ensemble averaging techniques, fusing the results of differently initialized and trained networks. Thereby, using micrograph cell segmentation as an application example, various ensembles have been initialized and formed during network training, whereby the following methods have been applied: (a) random seeds, (b) L 1-norm pruning, (c) variable numbers of training examples, and (d) a combination of the latter 2 items. Furthermore, different averaging methods are in common use and were evaluated in this study. As averaging methods, the mean, the median, and the location parameter of an alpha-stable distribution, fit to the histograms of class membership probabilities (CMPs), as well as a majority vote of the members of an ensemble were considered. The performance of these methods is demonstrated and evaluated on a micrograph cell segmentation use case, employing a common state-of-the art deep convolutional neural network (DCNN) architecture exploiting the principle of the common VGG-architecture. The study demonstrates that for this data set, the choice of the ensemble averaging method only has a marginal influence on the evaluation metrics (accuracy and Dice coefficient) used to measure the segmentation performance. Nevertheless, for practical applications, a simple and fast estimate of the mean of the distribution is highly competitive with respect to the most sophisticated representation of the CMP distributions by an alpha-stable distribution, and hence seems the most proper ensemble averaging method to be used for this application.

Number of necessary training examples for Neural Networks with different number of trainable parameters.

In this work, the network complexity should be reduced with a concomitant reduction in the number of necessary training examples. The focus thus was on the dependence of proper evaluation metrics on the number of adjustable parameters of the considered deep neural network. The used data set encompassed Hematoxylin and Eosin (H&E) colored cell images provided by various clinics. We used a deep convolutional neural network to get the relation between a model's complexity, its concomitant set of parameters, and the size of the training sample necessary to achieve a certain classification accuracy. The complexity of the deep neural networks was reduced by pruning a certain amount of filters in the network. As expected, the unpruned neural network showed best performance. The network with the highest number of trainable parameter achieved, within the estimated standard error of the optimized cross-entropy loss, best results up to 30% pruning. Strongly pruned networks are highly viable and the classification accuracy declines quickly with decreasing number of training patterns. However, up to a pruning ratio of 40%, we found a comparable performance of pruned and unpruned deep convolutional neural networks (DCNN) and densely connected convolutional networks (DCCN).

Large Variability of Frequency and Type of Physical Therapy in Patients in the German Network for Systemic Sclerosis.

OBJECTIVE: To determine the type and frequency of physical therapy (PT) prescribed by physicians for patients in the registry of the German Network for Systemic Sclerosis. METHODS: The data for 4,252 patients were analyzed using descriptive statistics, chi-square tests, and odds ratios (ORs). RESULTS: Overall, 37.4% of patients (1,590 of 4,252) received PT at the end of a yearly follow-up. The most frequently used type of PT was lymphatic drainage (n = 1,061, 36.8%), followed by exercise therapy (n = 1,047, 36.3%) and heat therapy (n = 689, 23.9%). More than three-fourths of treated patients (82%) received 1 or 2 different forms of PT simultaneously. The prescription of PT was associated with the extent of skin fibrosis as measured by the modified Rodnan skin thickness score (<10 [41.8% of patients], 11-20 [55.8% of patients], and >21 [63.9% of patients]; P < 0.001). Patients with musculoskeletal involvement (e.g., arthritis, muscle weakness, joint contractures, tendon friction rubs) had a higher chance of receiving PT than patients without these symptoms, with corresponding ORs ranging from 1.96 (95% confidence interval [95% CI] 1.69-2.28) for joint contractures to 3.83 (95% CI 2.89-5.08) for arthritis. When comparing the type of PT prescription across the initial and all follow-up visits from 2003 to 2017, significant alterations with a decreasing frequency of patients receiving PT could be observed (P = 0.001). CONCLUSION: To our knowledge, this is the first study reporting the use of PT in patients with systemic sclerosis (SSc) in a large cohort. Although SSc is characterized by considerable disability and restriction of motion, <40% of patients received PT.

[Th9 cells. Functionally important or just an epiphenomenon?]. / Th9-Zellen. Funktionell bedeutsam oder nur ein Epiphänomen?

Development of the recently described Th9 cells is selectively and dynamically controlled by epigenetic modifications. The selective epigenetic inactivation of the PU.1 promoter associated with diminished Th9 cell differentiation by naive CD4 T cells allows the assumption of a special physiologic role of IL-9. Once deregulated, IL-9 seems to play an important role in the pathogenesis of several autoimmune disorders.

[Cellular therapy in autoimmune disease]. / Zelluläre Therapie von Autoimmunerkrankungen.

In addition to natural thymus-derived regulatory T-cells (Tregs), peripherally-induced Tregs are of central importance in immune homeostasis. Homotypic interactions between activated effector T-cells and resting memory T-cells induced the generation of IL-10 and IFNgamma producing Tregs in vitro. This mechanism in Treg development allows new insights into T-cell vaccination, which has been employed in pilot trials of multiple sclerosis and rheumatoid arthritis with promising results.