- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
A Coarse-to-Fine Fully Convolutional Neural Network for Fundus Vessel Segmentation
摘要： Fundus vessel analysis is a significant tool for evaluating the development of retinal diseases such as diabetic retinopathy and hypertension in clinical practice. Hence, automatic fundus vessel segmentation is essential and valuable for medical diagnosis in ophthalmopathy and will allow identification and extraction of relevant symmetric and asymmetric patterns. Further, due to the uniqueness of fundus vessel, it can be applied in the field of biometric identification. In this paper, we remold fundus vessel segmentation as a task of pixel-wise classification task, and propose a novel coarse-to-fine fully convolutional neural network (CF-FCN) to extract vessels from fundus images. Our CF-FCN is aimed at making full use of the original data information and making up for the coarse output of the neural network by harnessing the space relationship between pixels in fundus images. Accompanying with necessary pre-processing and post-processing operations, the efficacy and efficiency of our CF-FCN is corroborated through our experiments on DRIVE, STARE, HRF and CHASE DB1 datasets. It achieves sensitivity of 0.7941, specificity of 0.9870, accuracy of 0.9634 and Area Under Receiver Operating Characteristic Curve (AUC) of 0.9787 on DRIVE datasets, which surpasses the state-of-the-art approaches.
关键词： fundus vessel segmentation,conditional random field,dilated convolution,medical diagnosis,fully convolutional neural network
更新于2025-09-19 17:15:36
-
Editorial: Plasmonic Technologies for Bioanalytical Applications
摘要： Bioanalytical technologies that provide quantitative information about bioanalytes of interest in biological systems are becoming widespread in biomedical applications, environment monitoring, and food quality and safety. Among recent developments, plasmonic-based technologies made significant strides toward real life applications. They are based on surface plasmons, which are collective oscillations of conductive electrons on noble metal film or nanoparticle surfaces induced by electromagnetic radiation at the metal-dielectric interface. Plasmonic nanostructures have the ability to control and manipulate visible light at the nanometer scale and have been used to create plasmonic filters, wave-guides, nanoscopic light sources, and other devices with unique or improved properties. In addition, plasmonics has helped further our understanding of the interaction of molecules with nanostructures and has been used in biosensing applications. Their low ohmic and optical losses, chemical activity, tunable optical properties, specific response to incident light, and the ability to enhance signals such as fluorescence and Raman scattering, have been exploited in biomedical applications. Specific plasmonic-based technologies include nanoscale optical absorption spectroscopy, surface plasmon resonance (SPR), localized surface plasmon resonance (LSPR), surface-enhanced Raman scattering spectroscopy (SERS), tip-enhanced Raman spectroscopy (TERS), surface-enhanced infrared absorption spectroscopy (SEIRAS), single molecule plasmonics (SMP), and chiral plasmonics (CP). This special issue is needed for chemists, biologists, and materials scientists who work in the area of plasmonics applications in bioanalytical sensing.
关键词： plasmonic materials,plasmonics,bioanalytical,medical diagnosis,extracellular vesicles
更新于2025-09-16 10:30:52
-
Spectral Imaging Technology - A Review on Skin and Endoscopy Applications
摘要： Spectral imaging technology is an emerging modality that combines the advantages of both imaging and spectroscopy (high spatial and spectral resolution) in one device. The technology has potential in numerous medical imaging and diagnostic applications. In this review, we describe the techniques used to acquire spectral images and the methods used for analyzing spectral images. We then provide detailed review about the progress of the spectral imaging technology in skin and endoscopy applications. This review also covers the recent patents on spectral imaging devices, methods, and data analysis algorithms.
关键词： optical scattering,spectroscopy,Endoscopy,spectral imaging,tissue reflectance,skin diagnosis,medical diagnosis,optical absorption
更新于2025-09-10 09:29:36
-
Raman Spectroscopy and Applications || Raman Mapping: Emerging Applications
摘要： Raman mapping is a noninvasive, label‐free technique with high chemical specificity and high potential to become a leading method in biological and biomedical applications. As opposed to Raman spectroscopy, which provides discrete chemical information at distinct positions within the sample, Raman mapping provides chemical information coupled with spatial information. The laser spot scans the investigated sample area with a preset step size and acquires Raman spectra pixel by pixel. The Raman spectra are then discriminated from each other by chemometric analysis, and the end result is a false color map, an image of the sample that contains highly precise structural and chemical information. Raman imaging has been successfully used for label‐free investigations at cellular and subcellular level. Cell compartments, cell responses to drugs and different stages of the cell cycle from the stem cell to the completely differentiated cell were successfully distinguished. This technique is also able to differentiate between healthy and cancer cells, indicating great potential for replacing conventional cancer detection tools with Raman detection in the future.
关键词： plants,algae,cells,medical diagnosis,tissues,Raman imaging,Raman mapping,Raman spectroscopy
更新于2025-09-04 15:30:14