This paper presents a comprehensive review of the principle and application of deep learning in retinal image analysis. Many eye diseases often lead to blindness in the absence of proper clinical diagnosis and medical treatment. For example, diabetic retinopathy (DR) is one such disease in which the retinal blood vessels of human eyes are damaged. The ophthalmologists diagnose DR based on their professional knowledge, that is labor intensive. With the advances in image processing and artificial intelligence, computer vision-based techniques have been applied rapidly and widely in the field of medical images analysis and are becoming a better way to advance ophthalmology in practice. Such approaches utilize accurate visual analysis to identify the abnormality of blood vessels with improved performance over manual procedures. More recently, machine learning, in particular, deep learning, has been successfully implemented in this area. In this paper, we focus on recent advances in deep learning methods for retinal image analysis. We review the related publications since 1982, which include more than 80 papers for retinal vessels detections in the research scope spanning from segmentation to classification. Although deep learning has been successfully implemented in other areas, we found only 17 papers so far focus on retinal blood vessel segmentation. This paper characterizes each deep learning based segmentation method as described in the literature. Analyzing along with the limitations and advantages of each method. In the end, we offer some recommendations for future improvement for retinal image analysis. INDEX TERMS Retinal colour fundus images, convolutional neural networks, retinal vessels segmentation.

No abstract

No abstract

No abstract

No abstract

As surface-enhanced Raman scattering (SERS) has been used to diagnose several respiratory viruses (e.g., influenza A virus subtypes such as H1N1 and the new coronavirus SARS-CoV-2), SERS is gaining popularity as a method for diagnosing viruses at the point-of-care. Although the prior and quick diagnosis of respiratory viruses is critical in the outbreak of infectious disease, ELISA, PCR, and RT-PCR have been used to detect respiratory viruses for pandemic control that are limited for point-of-care testing. SERS provides quantitative data with high specificity and sensitivity in a real-time, label-free, and multiplex manner recognizing molecular fingerprints. Recently, the design of Raman spectroscopy system was simplified from a complicated design to a small and easily accessible form that enables point-of-care testing. We review the optical design (e.g., laser wavelength/power and detectors) of commercialized and customized handheld Raman instruments. As respiratory viruses have prominent risk on the pandemic, we review the applications of handheld Raman devices for detecting respiratory viruses. By instrumentation and commercialization advancements, the advent of the portable SERS device creates a fast, accurate, practical, and cost-effective analytical method for virus detection, and would continue to attract more attention in point-of-care testing.

No abstract

No abstract