RESUMEN
Background: This pilot study aimed to evaluate the Retinal Function Imager (RFI) for visualizing retinal vasculature and assessment of blood flow characteristics in patients with retinal vasculitis. The RFI is a non-invasive imaging device measuring the blood flow velocity (BFV) in secondary and tertiary retinal vessels using hemoglobin as an intrinsic motion-contrast agent. Methods: To test the feasibility of the RFI for patients with retinal vasculitis, capillary perfusion maps (nCPMs) were generated from 15 eyes of eight patients (five females; mean age: 49 ± 12 years) with a mean uveitis duration of 74 ± 85 months. Five of these patients had birdshot chorioretinopathy, and three had primarily non-occlusive venous retinal vasculitis of unknown origin. To reflect that the BFV may be more reduced in patients with prolonged disease, patients were classified into a short-term (uveitis duration: 8-15 months) and a long-term uveitis group (uveitis duration: 60-264 months). Data were compared with healthy controls (16 eyes of 11 patients; mean age 45 ± 12 years; 8 females). Results: The mean BFV in the controls was 3.79 ± 0.50 mm/s in the retinal arteries and 2.35 ± 0.44 mm/s in the retinal veins, which was significantly higher compared to the retinal vasculitis group. Patients revealed an arterial BFV of 2.75 ± 0.74 mm/s (p < 0.001) and a venous BFV of 1.75 ± 0.51 mm/s (p = 0.016). In the short-term group, a trend towards a decreased venular and arteriolar BFV was seen, while a significant reduction was observed in the long-term group. The patients' microvasculature anatomy revealed by the nCPMs appeared unevenly distributed and a lower number of blood vessels were seen, along with a lower degree of complexity of their branching patterns, when compared with controls. Conclusions: This study demonstrated a reduction in venular and arteriolar BFVs in patients with retinal vasculitis. BFV alterations were already observed in early disease stages and became more pronounced in progressed disease. Additionally, we showed that retinal microvasculature changes may be observed by nCPMs. Retinal imaging with the RFI may serve as a diagnostic and quantifying tool in retinal vasculitis.
RESUMEN
Artificial intelligence has transformed medical diagnostic capabilities, particularly through medical image analysis. AI algorithms perform well in detecting abnormalities with a strong performance, enabling computer-aided diagnosis by analyzing the extensive amounts of patient data. The data serve as a foundation upon which algorithms learn and make predictions. Thus, the importance of data cannot be underestimated, and clinically corresponding datasets are required. Many researchers face a lack of medical data due to limited access, privacy concerns, or the absence of available annotations. One of the most widely used diagnostic tools in ophthalmology is Optical Coherence Tomography (OCT). Addressing the data availability issue is crucial for enhancing AI applications in the field of OCT diagnostics. This review aims to provide a comprehensive analysis of all publicly accessible retinal OCT datasets. Our main objective is to compile a list of OCT datasets and their properties, which can serve as an accessible reference, facilitating data curation for medical image analysis tasks. For this review, we searched through the Zenodo repository, Mendeley Data repository, MEDLINE database, and Google Dataset search engine. We systematically evaluated all the identified datasets and found 23 open-access datasets containing OCT images, which significantly vary in terms of size, scope, and ground-truth labels. Our findings indicate the need for improvement in data-sharing practices and standardized documentation. Enhancing the availability and quality of OCT datasets will support the development of AI algorithms and ultimately improve diagnostic capabilities in ophthalmology. By providing a comprehensive list of accessible OCT datasets, this review aims to facilitate better utilization and development of AI in medical image analysis.
RESUMEN
This comprehensive review explores the role of Functional Near-Infrared Spectroscopy (fNIRS) in advancing our understanding of the visual system. Beginning with an introduction to fNIRS, we delve into its historical development, highlighting how this technology has evolved over time. The core of the review critically examines the advantages and disadvantages of fNIRS, offering a balanced view of its capabilities and limitations in research and clinical settings. We extend our discussion to the diverse applications of fNIRS beyond its traditional use, emphasizing its versatility across various fields. In the context of the visual system, this review provides an in-depth analysis of how fNIRS contributes to our understanding of eye function, including eye diseases. We discuss the intricacies of the visual cortex, how it responds to visual stimuli and the implications of these findings in both health and disease. A unique aspect of this review is the exploration of the intersection between fNIRS, virtual reality (VR), augmented reality (AR) and artificial intelligence (AI). We discuss how these cutting-edge technologies are synergizing with fNIRS to open new frontiers in visual system research. The review concludes with a forward-looking perspective, envisioning the future of fNIRS in a rapidly evolving technological landscape and its potential to revolutionize our approach to studying and understanding the visual system.