Survey of Medical Applications of Federated Learning.

OBJECTIVES: Medical artificial intelligence (AI) has recently attracted considerable attention. However, training medical AI models is challenging due to privacy-protection regulations. Among the proposed solutions, federated learning (FL) stands out. FL involves transmitting only model parameters without sharing the original data, making it particularly suitable for the medical field, where data privacy is paramount. This study reviews the application of FL in the medical domain. METHODS: We conducted a literature search using the keywords "federated learning" in combination with "medical," "healthcare," or "clinical" on Google Scholar and PubMed. After reviewing titles and abstracts, 58 papers were selected for analysis. These FL studies were categorized based on the types of data used, the target disease, the use of open datasets, the local model of FL, and the neural network model. We also examined issues related to heterogeneity and security. RESULTS: In the investigated FL studies, the most commonly used data type was image data, and the most studied target diseases were cancer and COVID-19. The majority of studies utilized open datasets. Furthermore, 72% of the FL articles addressed heterogeneity issues, while 50% discussed security concerns. CONCLUSIONS: FL in the medical domain appears to be in its early stages, with most research using open data and focusing on specific data types and diseases for performance verification purposes. Nonetheless, medical FL research is anticipated to be increasingly applied and to become a vital component of multi-institutional research.

Injectable alginate-based in situ self-healable transparent hydrogel as a vitreous substitute with a tamponading function.

Retinal detachment and other vision-threatening disorders often necessitate vitreous body removal and tamponade injection for retina stabilization. Current clinical tamponades such as silicone oil and expansile gases have drawbacks, including patient discomfort and the need for secondary surgery. We introduce a transparent alginate-phenylboronic acid/polyvinyl alcohol composite hydrogel (TALPPH) as a novel vitreous substitute with tamponading capabilities. In vitro physicochemical, rheological, and optical characterization of in situ self-healable TALPPH was performed, and long-term biocompatibility was assessed in a rabbit model of vitrectomy retinal detachment. In vivo evaluations confirmed TALPPH's ability to inhibit retinal detachment recurrence and preserve rabbit vision without adverse effects. TALPPH's close resemblance to the natural vitreous body suggests potential as a vitreous tamponade substitute for future ophthalmological applications.

AI-Based Drug Discovery of TKIs Targeting L858R/T790M/C797S-Mutant EGFR in Non-small Cell Lung Cancer.

Lung cancer has a high mortality rate, and non-small cell lung cancer (NSCLC) is the most common type of lung cancer. Patients have been observed to acquire resistance against various anticancer agents used for NSCLC due to L858R (or Exon del19)/T790M/C797S-EGFR mutations. Therefore, next-generation drugs are being developed to overcome this problem of acquired resistance. The goal of this study was to use artificial intelligence (AI) to discover drug candidates that can overcome acquired resistance and reduce the limitations of the current drug discovery process, such as high costs and long durations of drug design and production. To generate ligands using AI, we collected data related to tyrosine kinase inhibitors (TKIs) from accessible libraries and used LSTM (Long short term memory) based transfer learning (TL) model. Through the simplified molecular-input line-entry system (SMILES) datasets of the generated ligands, we obtained drug-like ligands via parameter-filtering, cyclic skeleton (CSK) analysis, and virtual screening utilizing deep-learning method. Based on the results of this study, we are developing prospective EGFR TKIs for NSCLC that have overcome the limitations of existing third-generation drugs.

The culture of primary duck endothelial cells for the study of avian influenza.

BACKGROUND: Endothelial cells play a major role in highly pathogenic avian influenza (HPAI) virus pathogenesis in gallinaceous poultry species (e.g. chicken, turkey and quail). Upon infection of gallinaceous poultry with HPAI viruses, endothelial cells throughout the body become rapidly infected, leading to systemic dissemination of the virus, disseminated intravascular coagulation, oedema and haemorrhaging. In contrast, the pathogenesis of HPAI viruses in most wild bird species (e.g. duck, goose and gull species) is not associated with endothelial tropism. Indeed, viral antigen is not found in the endothelial cells of most wild bird species following infection with HPAI viruses. This differential endothelial cell tropism in avian species is poorly understood, mainly due to the absence of appropriate cell culture systems. RESULTS: Here, we describe the isolation and purification of primary duck endothelial cells from the aorta or bone marrow of Pekin duck embryos. Cells were differentiated in the presence of vascular endothelial growth factor and, if needed, enriched via fluorescent-activated cell sorting based on the uptake of acetylated low-density lipoprotein. The expression of von Willebrand factor, a key marker of endothelial cells, was confirmed by polymerase chain reaction. Monocultures of duck endothelial cells, either derived from the aorta or the bone marrow, were susceptible to infection with an H5N1 HPAI virus but to a much lesser extent than chicken endothelial cells. CONCLUSIONS: The methods described herein to isolate and purify duck endothelial cells from the aorta or bone marrow could also be applied to obtain microvascular endothelial cells from other tissues and organs, such as the lung or the intestine, and represent a valuable tool to study the pathogenesis of avian viruses.