The rapid development of Internet of Things (IoT) systems has led to the problem of managing and analyzing the large volumes of data that they generate. Traditional approaches that involve collection of data from IoT devices into one centralized repository for further analysis are not always applicable due to the large amount of collected data, the use of communication channels with limited bandwidth, security and privacy requirements, etc. Federated learning (FL) is an emerging approach that allows one to analyze data directly on data sources and to federate the results of each analysis to yield a result as traditional centralized data processing. FL is being actively developed, and currently, there are several open-source frameworks that implement it. This article presents a comparative review and analysis of the existing open-source FL frameworks, including their applicability in IoT systems. The authors evaluated the following features of the frameworks: ease of use and deployment, development, analysis capabilities, accuracy, and performance. Three different data sets were used in the experiments—two signal data sets of different volumes and one image data set. To model low-power IoT devices, computing nodes with small resources were defined in the testbed. The research results revealed FL frameworks that could be applied in the IoT systems now, but with certain restrictions on their use.

No abstract

No abstract

No abstract

Endoscopic endonasal transsphenoidal resection of PAs invading the CS is a more efficient and safer surgical technique compared to microsurgical techniques (transsphenoidal and extra-intradural approach). The lateral extended transsphenoidal endoscopic approach enables resection of PAs with massive invasion into the CS (Grade III and Grade IV, Knosp scale) and has less postoperative complications compared to the extra-intradural approach (p<0.05).

АКТГ-аденокортикотропный гормон ВСА-внутренняя сонная артерия ЛГ-лютеинизирующий гормон МРТ-магнитно-резонансная томография ПРЛ-пролактин СТГ-соматотропный гормон ТМО-твердая мозговая оболочка ТТГ-тиреотропный гормон ФСГ-фолликулостимулирующий гормон ЦНС-центральная нервная система УЗИ-ультразвуковое исследование ЭКГ-электрокардиография

One of the most serious/potentially fatal complications of transsphenoidal surgery (TSS) is internal carotid artery (ICA) injury. Of 6230 patients who underwent TSS, ICA injury occurred in 8 (0.12%). The etiology, possible treatment options, and avoidance of ICA injury were analyzed. ICA injury occurred at two different stages: (1) during the exposure of the sella floor and dural incision over the sella and cavernous sinus and (2) during the resection of the cavernous sinus extension of the tumor. The angiographic collateral blood supply was categorized as good, sufficient, and nonsufficient to help with the decision making for repairing the injury. ICA occlusion with a balloon was performed at the injury site in two cases, microcoils in two patients, microcoils plus a single barrel extra-intracranial high-flow bypass in one case, stent grafting in one case, and no intervention in two cases. The risk of ICA injury diminishes with better preoperative preparation, intraoperative navigation, and ultrasound dopplerography. Reconstructive surgery for closing the defect and restoring the blood flow to the artery should be assessed depending on the site of the injury and the anatomical features of the ICA.

The criterion for total tumor resection was a postoperative decrease in the TSH level to 0.1 mIU/L or less. Total resection was performed in 33% of patients with tumors of only the endosellar and endo-suprasellar localization. In most cases, tumors were plurihormonal and secreted TSH and GH and/or PRL.