In order to automate microscopic examinations of female urogenital samples, the “learning” of the “Vision Cyto STD” system was performed using the technology of image recognition based on convolutional neural networks and deep learning. More than a thousand digital slides with urogenital material with different microscopic composition were evaluated during the learning process. As the dataset was replenished with new clinical examples, the accuracy of object recognition increased. The use of artificial neural networks (ANN) for imaging and analysis of urogenital samples ensures high quality of examination performance due to the clarity of identification, accuracy of analysis and correctness of entering the examination results. Using of ANN speeds up the process of giving the results, allows to minimize the influence of the subjective factor, and also provides an opportunity to redistribute the workload of laboratory workers, without expanding the laboratory staff when the number of examinations to be performed increases. A brief overview of the automated Vision Cyto STDs system is presented.
The development of digital microscopy and computer data analysis has contributed to the introduction into clinical practice of methods for evaluating laboratory samples with automated image analysis. A comparative analysis of the time required to evaluate 100 samples of various types of laboratory tests by manual and automated methods using Vision® analysis systems has been carried out. The results obtained indicate that automated approaches in microscopic studies using Vision® analysis systems reduce the time for laboratory tests by up to 4 times compared with traditional manual methods. Vision® systems also improve the accuracy of the analysis by automatically collecting and pre-classifying cells, which eliminates the influence of human factors during the evaluation of the sample. Thus, the use of automatic Vision® systems makes it possible to increase the efficiency of laboratory work.
Abstract. According to elibrary3 reports, scientific and practical medical journal Laboratory and Clinical Medicine. Pharmacy (LCMP)4 which has been published 3 years takes well-deserved place along with well-known, authoritative and long-published scientific medical mass media. Increasing in twice the authors number (20 vs 39) and in 1.5 times new once (20 vs 29), upward trend of h-index (Hirsch index) (4.2 vs 4.9) and Gini index (0.55 vs 0.8), a noticeable drop of HHI (the Herfindahl–Hirschman index) for authors' organizations (1837 vs 1378), increase in 6-times the number of views per year (100 vs 625) and almost in 4 times the downloads of articles per year (38 vs 146), the two-year IF (Impact Factor), taking into account citation of all sources in Russian Science Citation Index (RSCI) – 0.692, as well as the possibility of publication in three branches of science, characterize the journal as promising and competitive in its industry, with a wide-spread geography of authors and medical organizations. In order to increase the citation of the LCMP, the main concept of the journal is to improve a manuscript. The results of the three-years LCMP work showed that the preparation of manuscripts according to the Author Guidelines should belong to editorial and publishing team. In order to avoid the loss of publication activity the editorial team of LCMP has all the necessary competencies for supporting and providing an author's manuscript.
The analysis of sperm morphology (n = 100) was performed using Vision Sperm automatic sperm analysis system. Evaluation of detection accuracy of sperm morphology was carried out using the following operational criteria that system calculated automatically: diagnostic sensitivity (DSe), diagnostic specificity (DSp) and diagnostic efficiency (DE). The system automatically scanned the slides, identified and performed preliminary sorting (pre-classification) of spermatozoa into four categories of morphological defects: ‘Head’, ‘Neck’, ‘Tail’ and ‘ERC’. Medical validation and generation of report on results of the analysis were carried out simultaneously with scanning of new sperm samples. The average examination time of one glass slide was 3 min 43 sec. The high efficiency of sperm recognition by the Vision Sperm system has been established. Application of Vision Sperm analysis system ensured automation and standardization of assessment a sperm morphology and improved a performance in clinical laboratory.
The possibility of remote consultations of specialists in microscopy through the exchange of digital preparations is highly important in clinical laboratory diagnostics. This review describes the Pathoview online service, which allows storing, viewing and exchanging clinical cases in the form of digital slides in common formats: SVS, TIFF, NDPI, MRXS, DCM. The service requires no additional software installation on your computer or mobile device. In Pathoview, the digital slide is available for viewing in any browser immediately after being uploaded to the service. The link-based sharing function significantly speeds up and simplifies the process of collaborative viewing and remote consultation of specialists.
In the lockdown settings due to COVID-19 pandemic the numerous of schools faced a number of difficulties in organizing the learning process. The requirements of programs aimed to offline training in microscopic methods were overcome with the online service Vision Expertise. The Vision Expertise cloud solution offers extensive functionality for training and exchange of experience in the field of digital clinical microscopy.
Clinical laboratory diagnostics of male infertility is an integral part of the diagnostic process in the field of reproductive medicine. Studies conducted during the pandemia of novel coronavirus infection (COVID-19) indicate that RNA of SARS-CoV-2 can be detected in the testes, and that the possibility of disrupting spermatogenesis and the viral impact on male reproductive health has been predicted.