Seeking a Sufficient Data Volume for Railway Infrastructure Component Detection with Computer Vision Models.

Railway infrastructure monitoring is crucial for transportation reliability and travelers' safety. However, it requires plenty of human resources that generate high costs and is limited to the efficiency of the human eye. Integrating machine learning into the railway monitoring process can overcome these problems. Since advanced algorithms perform equally to humans in many tasks, they can provide a faster, cost-effective, and reproducible evaluation of the infrastructure. The main issue with this approach is that training machine learning models involves acquiring a large amount of labeled data, which is unavailable for rail infrastructure. We trained YOLOv5 and MobileNet architectures to meet this challenge in low-data-volume scenarios. We established that 120 observations are enough to train an accurate model for the object-detection task for railway infrastructure. Moreover, we proposed a novel method for extracting background images from railway images. To test our method, we compared the performance of YOLOv5 and MobileNet on small datasets with and without background extraction. The results of the experiments show that background extraction reduces the sufficient data volume to 90 observations.

The comparative analysis of selected interleukins and proinflammatory factors in CSF among de novo diagnosed patients with RRMS.

OBJECTIVES: Cytokines play a key role in neuroinflammation, which is present in every subset of multiple sclerosis (MS). The aim of the study was to assess levels of selected interleukins and proinflammatory factors in cerebrospinal fluid (CSF) among patients diagnosed with relapsing-remitting multiple sclerosis (RRMS). METHODS: One hundred eighteen patients diagnosed de novo with RRMS were enrolled in the study. We analysed the relationships between selected cytokines' levels depending on the age at diagnosis, time from the first symptoms to diagnosis and presence of MRI lesions. RESULTS: Among the study group the levels of IL-5 and IL-13 increased with the age at the diagnosis of MS. The concentration of IL-10 was lower in group of patients over the age of 35. The levels of IFN-γ, TNF-α, IL-5, IL-10 and IL-15 increased with the longer time from the first symptoms to diagnosis. Positive correlations were found between the levels of IL-2 and IL-12, IL-17, IL-4, IL-1RA as well as IL-1 and IL-4, IL-17. The concentration of IL-5 correlated positively with IL-4, IL-9 and IL-13. The level of IL-10 increased with IL-6 and IL-9 concentrations. A negative correlation was found for IL-10 and IL-4. In turn, between IL-13 and both IL-5 and IL-9, the relationship was positive. The level of IL-2 was significantly higher among patients without gadolinium-enhanced (Gd(+)) MRI lesions. CONCLUSIONS: The results of the study provide new insight into the role of selected molecules in the development of inflammation in MS. It might be crucial in planning the most adequate immunomodulatory therapy.

Multiple sclerosis immunomodulatory therapies tested for effectiveness in COVID-19.

INTRODUCTION: The global pandemic of COVID-19 began in Wuhan, China in December 2019. Research into effective therapies has been conducted worldwide. Currently, there is no antiviral treatment and many patients develop a severe course of the disease, including severe respiratory failure. Due to similar pathomechanisms of inflammation in multiple sclerosis (MS) and COVID-19, immunomodulatory drugs that are registered for the treatment of MS are under study in the SARS-CoV-2 infection in clinical trials. MATERIALS AND METHODS: Using clinicaltrials.gov, we found information related to ongoing clinical studies on potential drugs for COVID-19 which are also used in MS therapy. The outcomes of several trials were published on pubmed.ncbi.nlm.nih.gov. RESULTS: There were 18 clinical trials evaluating the effectiveness and safety of interferon-ß, fingolimod, or leflunomide in COVID-19. Some trial outcomes available at pubmed.ncbi.nlm.nih.gov suggested an association of these drug treatments with improvements in signs and symptoms, and the disease course. CONCLUSION: The administration of immunomodulatory drugs in COVID-19 may result in potential beneficial effects probably associated with their anti-inflammatory and antiviral properties. Further research is warranted to confirm the long-term effects of immunomodulatory therapies in patients with COVID-19.

Plant stem cells as innovation in cosmetics.

The stem cells thanks to their ability of unlimited division number or transformation into different cell types creating organs, are responsible for regeneration processes. Depending on the organism in which the stem cells exists, they divide to the plant or animal ones. The later group includes the stem cells existing in both embryo's and adult human's organs. It includes, among others, epidermal stem cells, located in the hair follicle relieves and also in its basal layers, and responsible for permanent regeneration of the epidermis. Temporary science looks for method suitable for stimulation of the epidermis stem cells, amongst the other by delivery of e.g., growth factors for proliferation that decrease with the age. One of the methods is the use of the plant cell culture technology, including a number of methods that should ensure growth of plant cells, issues or organs in the environment with the microorganism-free medium. It uses abilities of the different plant cells to dedifferentiation into stem cells and coming back to the pluripotent status. The extracts obtained this way from the plant stem cells are currently used for production of both common or professional care cosmetics. This work describes exactly impact of the plant stem cell extract, coming from one type of the common apple tree (Uttwiler Spätlauber) to human skin as one of the first plant sorts, which are used in cosmetology and esthetic dermatology.