Medical image captioning via generative pretrained transformers.

The proposed model for automatic clinical image caption generation combines the analysis of radiological scans with structured patient information from the textual records. It uses two language models, the Show-Attend-Tell and the GPT-3, to generate comprehensive and descriptive radiology records. The generated textual summary contains essential information about pathologies found, their location, along with the 2D heatmaps that localize each pathology on the scans.

[Low-pressure pneumoperitoneum with abdominal elevation in laparoscopic radical prosta-tectomy in elderly patients with a localized form of prostate cancer.].

Prostate cancer is an actual problem among males of older age groups, while the concomi-tant premorbid background of this category of patients often leads to the development of postopera-tive complications using the standard surgical method. The article presents the results of using low-pressure pneumoperitoneum with anterior abdominal wall lifting for laparoscopic radical prostatec-tomy in elderly patients with a localized form of prostate cancer. Convincingly shown that the use of low-pressure techniques pneumoperitoneum with lifting anterior abdominal wall ensures satis-factory operating field, obtains stable indicators of operational monitoring and allow to reduce the duration of the operation, as well as reduce the duration of hospitalization and incidence of postoperative complications.

Isolation and phylogenetic analysis of SARS-CoV-2 variants collected in Russia during the COVID-19 outbreak.

Objectives: The outbreak of coronavirus disease 2019 (COVID-19) started in December 2019 in China and then spread worldwide over the following months, involving 188 countries. The objective of this study was to determine the molecular epidemiology of the COVID-19 outbreak in Russia.

Methods: In this study, two severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) strains were isolated and genetically characterized.

NEXAFS study of electronic and atomic structure of active layer in Al/indium tin oxide/TiO stack during resistive switching.

We have studied the stability of the resistive switching process in the Al/(InO)(SnO)/TiO assembly grown by atomic layer deposition. Besides electrical characterization the effect of electric field on the atomic electronic structure of the TiO layer was studied using near edge X-ray absorption fine structure (NEXAFS) spectroscopy. The region of the current instability in the I-V characteristics was revealed.