Background/Objectives: Diabetic retinopathy (DR) remains a leading cause of preventable blindness, with its global prevalence projected to rise sharply as diabetes incidence increases. Early detection and timely management are critical to reducing DR-related vision loss. Optical Coherence Tomography Angiography (OCTA) now enables non-invasive, layer-specific visualization of the retinal vasculature, facilitating more precise identification of early microvascular changes. Concurrently, advancements in artificial intelligence (AI), particularly deep learning (DL) architectures such as convolutional neural networks (CNNs), attention-based models, and Vision Transformers (ViTs), have revolutionized image analysis. These AI-driven tools substantially enhance the sensitivity, specificity, and interpretability of DR screening. Methods: A systematic review of PubMed, Scopus, WOS, and Embase databases, including quality assessment of published studies, investigating the result of different AI algorithms with OCTA parameters in DR patients was conducted. The variables of interest comprised training databases, type of image, imaging modality, number of images, outcomes, algorithm/model used, and performance metrics. Results: A total of 32 studies were included in this systematic review. In comparison to conventional ML techniques, our results indicated that DL algorithms significantly improve the accuracy, sensitivity, and specificity of DR screening. Multi-branch CNNs, ensemble architectures, and ViTs were among the sophisticated models with remarkable performance metrics. Several studies reported that accuracy and area under the curve (AUC) values were higher than 99%. Conclusions: This systematic review underscores the transformative potential of integrating advanced DL and machine learning (ML) algorithms with OCTA imaging for DR screening. By synthesizing evidence from 32 studies, we highlight the unique capabilities of AI-OCTA systems in improving diagnostic accuracy, enabling early detection, and streamlining clinical workflows. These advancements promise to enhance patient management by facilitating timely interventions and reducing the burden of DR-related vision loss. Furthermore, this review provides critical recommendations for clinical practice, emphasizing the need for robust validation, ethical considerations, and equitable implementation to ensure the widespread adoption of AI-OCTA technologies. Future research should focus on multicenter studies, multimodal integration, and real-world validation to maximize the clinical impact of these innovative tools.

Transition is an essential mechanism that drives the development of distinct cellular phenotypes and tumorigenesis. The expression of various types of testis cancer antigens (TCAs) in breast carcinomas suggests a potential transition to male germ cell features within the tumor. This study explores the cellular populations in breast cancer that express genes associated with male germ cell development. We re-analyzed published datasets to identify the germline-associated genes in breast tumors. We then experimentally validated the expression of the identified genes in 28 breast tissue tumor samples using a quantitative RT-PCR. Based on available datasets, we also performed single-cell RNA sequencing (scRNA-seq) to analyze the tumor heterogeneity and cellular clustering. A total of 455 overexpressed genes were identified that were related to fetal primordial germ cells (PGCs), particularly those in the male gonad. Our examinations showed a significant overexpression of five genes (CCNB1, CCNB2, PTTG1, RACGAP1, and UBE2C) in the tumor samples. The scRNA-seq analysis revealed 14 distinct cell clusters, characterized by different gene expression signatures and cell cycle phases. The breast tumor stromal cells were suggested as the main source of the germline-associated genes. This study provides insights into the molecular mechanisms and pathways involved in germ cell transition in breast carcinoma.

Background: The National Spinal Cord Injury Registry of Iran (NSCIR-IR) and the National Trauma Registry of Iran (NTRI) were established to meet the data needs for research and assessing trauma status in Iran. These registries have a group of patients shared by both registries, and it is expected that some identical data will be collected about them. A general question arises whether the spinal cord injury registry can receive part of the common data from the trauma registry and not collect them independently. Methods: We examined variables captured in both registries based on structure and concept, identified the overlapping period during which both systems recorded data in the same centers and extracted relevant data from both registries. Further, we evaluated the data for any discrepancies in amount or nature and pinpointed the underlying reasons for any inconsistencies. Results: Out of all the variables in the NSCIR-IR database, 18.6% of variables were similar to the NTRI in terms of concept and structure. Although four hospitals participated in both registries, only two (Sina and Beheshti Hospitals) had common cases. Patient names, prehospital intubation, ambulance arrival time, ICU length of stay, and admission time were consistent across both registries with no differences. Other common data variables had significant discrepancies. Conclusion: This study highlights the potential for health information exchange (HIE) between NSCIR-IR and NTRI and serves as a starting point for stakeholders and policymakers to understand the differences between the two registries and work toward the successful adoption of HIE.