<div style="text-align:justify;"> Due to the wave characteristics of light, diffraction occurs when the light passes through the optical system, so that the resolution of the ordinary far-field optical...<div style="text-align:justify;"> Due to the wave characteristics of light, diffraction occurs when the light passes through the optical system, so that the resolution of the ordinary far-field optical system is limited by the size of the Airy disk diameter. There are various factors that cause image quality degradation during system detection and imaging, such as optical system aberrations, atmospheric inter-ference, defocusing, system noise and so on. Super-resolution optical imaging technology is the most innovative breakthrough in the optical imaging and detection field in this century. It goes beyond the resolution limit of ordinary optical systems or detectors, and can get more details and information of the structure, providing unprecedented tools for various fields. Compared with ordinary optical systems, super-resolution systems have very high requirements on the signals to be detected, which cannot be met by ordinary detection techniques. Vacuum photoelectric detection and imaging technology is equipped with the characteristics of high sensitivity and fast response. It is widely used in super-resolution systems and has played a great role in super-resolution systems. In this paper, the principles and structure of the image-converter streak camera super-resolution system, scanning electron microscopy super-resolution system and laser scanning confocal super-resolution system will be sorted out separately, and the essential role of the vacuum photoelectric detection technology in the ultra-microscopic sys-tem will be analyzed. </div>展开更多
传统的超分辨成像系统易受外界环境影响,抗噪效果差,输出的超分辨图像清晰度较低,基于此设计基于空域变换的超分辨成像系统,系统先将激光集中在孔径光栏上射出,通过聚光镜汇聚激光,根据分光镜和辅助镜将激光聚焦在显微镜焦平面上,依照...传统的超分辨成像系统易受外界环境影响,抗噪效果差,输出的超分辨图像清晰度较低,基于此设计基于空域变换的超分辨成像系统,系统先将激光集中在孔径光栏上射出,通过聚光镜汇聚激光,根据分光镜和辅助镜将激光聚焦在显微镜焦平面上,依照物镜将激光束转变成平型光,使平行光能够均匀照射测量样品上,采用显微镜和辅助物镜处理从样品表面反射的带有样品信息的激光,最后通过分光镜反射带有信息的激光,反射光束在CCD上显示成像,核心处理器是FPGAWie的图像采集模块,采集CCD传输的视频图像后,通过通用并行接口将采集的视频图像数据传输到图像处理模块,该模块通过空域变换方法处理图像,获取超分辨图像,最终传输到计算机上进行显示。经过实验分析发现,该系统图像稳定性和图像清晰度平均值分别是98.538%和99.19%,干扰信噪比为16 d B时,该系统成像时间最短为6.57 ms,说明该系统成像清晰度高、抗干扰性能优。展开更多
Purpose: To apply and evaluate a super-resolution scheme based on the super-resolution convolutional neural network (SRCNN) for enhancing image resolution in digital mammograms. Materials and Methods: A total of 711 m...Purpose: To apply and evaluate a super-resolution scheme based on the super-resolution convolutional neural network (SRCNN) for enhancing image resolution in digital mammograms. Materials and Methods: A total of 711 mediolateral oblique (MLO) images including breast lesions were sampled from the Curated Breast Imaging Subset of the Digital Database for Screening Mammography (CBIS-DDSM). We first trained the super-resolution convolutional neural network (SRCNN), which is a deep-learning based super-resolution method. Using this trained SRCNN, high-resolution images were reconstructed from low-resolution images. We compared the image quality of the super-resolution method and that obtained using the linear interpolation methods (nearest neighbor and bilinear interpolations). To investigate the relationship between the image quality of the SRCNN-processed images and the clinical features of the mammographic lesions, we compared the image quality yielded by implementing the SRCNN, in terms of the breast density, the Breast Imaging-Reporting and Data System (BI-RADS) assessment, and the verified pathology information. For quantitative evaluation, peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) were measured to assess the image restoration quality and the perceived image quality. Results: The super-resolution image quality yielded by the SRCNN was significantly higher than that obtained using linear interpolation methods (p p Conclusion: SRCNN can significantly outperform conventional interpolation methods for enhancing image resolution in digital mammography. SRCNN can significantly improve the image quality of magnified mammograms, especially in dense breasts, high-risk BI-RADS assessment groups, and pathology-verified malignant cases.展开更多
文摘<div style="text-align:justify;"> Due to the wave characteristics of light, diffraction occurs when the light passes through the optical system, so that the resolution of the ordinary far-field optical system is limited by the size of the Airy disk diameter. There are various factors that cause image quality degradation during system detection and imaging, such as optical system aberrations, atmospheric inter-ference, defocusing, system noise and so on. Super-resolution optical imaging technology is the most innovative breakthrough in the optical imaging and detection field in this century. It goes beyond the resolution limit of ordinary optical systems or detectors, and can get more details and information of the structure, providing unprecedented tools for various fields. Compared with ordinary optical systems, super-resolution systems have very high requirements on the signals to be detected, which cannot be met by ordinary detection techniques. Vacuum photoelectric detection and imaging technology is equipped with the characteristics of high sensitivity and fast response. It is widely used in super-resolution systems and has played a great role in super-resolution systems. In this paper, the principles and structure of the image-converter streak camera super-resolution system, scanning electron microscopy super-resolution system and laser scanning confocal super-resolution system will be sorted out separately, and the essential role of the vacuum photoelectric detection technology in the ultra-microscopic sys-tem will be analyzed. </div>
文摘传统的超分辨成像系统易受外界环境影响,抗噪效果差,输出的超分辨图像清晰度较低,基于此设计基于空域变换的超分辨成像系统,系统先将激光集中在孔径光栏上射出,通过聚光镜汇聚激光,根据分光镜和辅助镜将激光聚焦在显微镜焦平面上,依照物镜将激光束转变成平型光,使平行光能够均匀照射测量样品上,采用显微镜和辅助物镜处理从样品表面反射的带有样品信息的激光,最后通过分光镜反射带有信息的激光,反射光束在CCD上显示成像,核心处理器是FPGAWie的图像采集模块,采集CCD传输的视频图像后,通过通用并行接口将采集的视频图像数据传输到图像处理模块,该模块通过空域变换方法处理图像,获取超分辨图像,最终传输到计算机上进行显示。经过实验分析发现,该系统图像稳定性和图像清晰度平均值分别是98.538%和99.19%,干扰信噪比为16 d B时,该系统成像时间最短为6.57 ms,说明该系统成像清晰度高、抗干扰性能优。
文摘Purpose: To apply and evaluate a super-resolution scheme based on the super-resolution convolutional neural network (SRCNN) for enhancing image resolution in digital mammograms. Materials and Methods: A total of 711 mediolateral oblique (MLO) images including breast lesions were sampled from the Curated Breast Imaging Subset of the Digital Database for Screening Mammography (CBIS-DDSM). We first trained the super-resolution convolutional neural network (SRCNN), which is a deep-learning based super-resolution method. Using this trained SRCNN, high-resolution images were reconstructed from low-resolution images. We compared the image quality of the super-resolution method and that obtained using the linear interpolation methods (nearest neighbor and bilinear interpolations). To investigate the relationship between the image quality of the SRCNN-processed images and the clinical features of the mammographic lesions, we compared the image quality yielded by implementing the SRCNN, in terms of the breast density, the Breast Imaging-Reporting and Data System (BI-RADS) assessment, and the verified pathology information. For quantitative evaluation, peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) were measured to assess the image restoration quality and the perceived image quality. Results: The super-resolution image quality yielded by the SRCNN was significantly higher than that obtained using linear interpolation methods (p p Conclusion: SRCNN can significantly outperform conventional interpolation methods for enhancing image resolution in digital mammography. SRCNN can significantly improve the image quality of magnified mammograms, especially in dense breasts, high-risk BI-RADS assessment groups, and pathology-verified malignant cases.
