Image super‐resolution via dynamic network

Convolutional neural networks depend on deep network architectures to extract accurate information for image super‐resolution.However,obtained information of these con-volutional neural networks cannot completely express predicted high‐quality images for complex scenes.A dynamic network for image super‐resolution(DSRNet)is presented,which contains a residual enhancement block,wide enhancement block,feature refine-ment block and construction block.The residual enhancement block is composed of a residual enhanced architecture to facilitate hierarchical features for image super‐resolution.To enhance robustness of obtained super‐resolution model for complex scenes,a wide enhancement block achieves a dynamic architecture to learn more robust information to enhance applicability of an obtained super‐resolution model for varying scenes.To prevent interference of components in a wide enhancement block,a refine-ment block utilises a stacked architecture to accurately learn obtained features.Also,a residual learning operation is embedded in the refinement block to prevent long‐term dependency problem.Finally,a construction block is responsible for reconstructing high‐quality images.Designed heterogeneous architecture can not only facilitate richer structural information,but also be lightweight,which is suitable for mobile digital devices.Experimental results show that our method is more competitive in terms of performance,recovering time of image super‐resolution and complexity.The code of DSRNet can be obtained at https://github.com/hellloxiaotian/DSRNet.

RGB-guided hyperspectral image super-resolution with deep progressive learning

Due to hardware limitations,existing hyperspectral(HS)camera often suffer from low spatial/temporal resolution.Recently,it has been prevalent to super-resolve a low reso-lution(LR)HS image into a high resolution(HR)HS image with a HR RGB(or mul-tispectral)image guidance.Previous approaches for this guided super-resolution task often model the intrinsic characteristic of the desired HR HS image using hand-crafted priors.Recently,researchers pay more attention to deep learning methods with direct supervised or unsupervised learning,which exploit deep prior only from training dataset or testing data.In this article,an efficient convolutional neural network-based method is presented to progressively super-resolve HS image with RGB image guidance.Specif-ically,a progressive HS image super-resolution network is proposed,which progressively super-resolve the LR HS image with pixel shuffled HR RGB image guidance.Then,the super-resolution network is progressively trained with supervised pre-training and un-supervised adaption,where supervised pre-training learns the general prior on training data and unsupervised adaptation generalises the general prior to specific prior for variant testing scenes.The proposed method can effectively exploit prior from training dataset and testing HS and RGB images with spectral-spatial constraint.It has a good general-isation capability,especially for blind HS image super-resolution.Comprehensive experimental results show that the proposed deep progressive learning method out-performs the existing state-of-the-art methods for HS image super-resolution in non-blind and blind cases.

Resolution-enhanced single-pixel imaging using the Hadamard transform matrix

We propose a single-pixel imaging(SPI)method to achieve a higher-resolution image via the Hadamard transform matrix.Unlike traditional SPI schemes,this new method recovers images by correlating single-pixel signals with synchronized transformed patterns of Hadamard bases that are actually projected onto the digital micromirror device.Each transform pattern is obtained through the inverse Fourier transform of the pattern acquired by Gaussian filtering of each Hadamard basis in the frequency domain.The proposed scheme is based on a typical SPI experimental setup and does not add any hardware complexity,enabling the transformation of Hadamard matrices and image reconstruction through data processing alone.Therefore,this approach could be considered as an alternative option for achieving fast SPI in a diffraction-limited imaging system,without the need for additional hardware.

Correg-Yolov3:a Method for Dense Buildings Detection in High-resolution Remote Sensing Images

The exploration of building detection plays an important role in urban planning,smart city and military.Aiming at the problem of high overlapping ratio of detection frames for dense building detection in high resolution remote sensing images,we present an effective YOLOv3 framework,corner regression-based YOLOv3(Correg-YOLOv3),to localize dense building accurately.This improved YOLOv3 algorithm establishes a vertex regression mechanism and an additional loss item about building vertex offsets relative to the center point of bounding box.By extending output dimensions,the trained model is able to output the rectangular bounding boxes and the building vertices meanwhile.Finally,we evaluate the performance of the Correg-YOLOv3 on our self-produced data set and provide a comparative analysis qualitatively and quantitatively.The experimental results achieve high performance in precision(96.45%),recall rate(95.75%),F1 score(96.10%)and average precision(98.05%),which were 2.73%,5.4%,4.1%and 4.73%higher than that of YOLOv3.Therefore,our proposed algorithm effectively tackles the problem of dense building detection in high resolution images.

Numerical Simulation of Super-Resolution Structured Illumination Microscopy (SIM) Using Heintzmann-Cremer Algorithm with Non-Continuous Spatial Frequency Support

We report a comprehensive numerical study of super resolution (SR) structured illumination microscopy (SIM) utilizing the classic Heintzmann-Cremer SIM process and algorithm. In particular, we investigated the impact of the diffraction limit of the underlying imaging system on the optimal SIM grating frequency that can be used to obtain the highest SR enhancement with non-continuous spatial frequency support. Besides confirming the previous theoretical and experimental work that SR-SIM can achieve an enhancement close to 3 times the diffraction limit with grating pattern illuminations, we also observe and report a series of more subtle effects of SR-SIM with non-continuous spatial frequency support. Our simulations show that when the SIM grating frequency exceeds twice that of the diffraction limit, the higher SIM grating frequency can help achieve a higher SR enhancement for the underlying imaging systems whose diffraction limit is low, though this enhancement is obtained at the cost of losing resolution at some lower resolution targets. Our simulations also show that, for underlying imaging systems with high diffraction limits, however, SR-SIM grating frequencies above twice the diffraction limits tend to bring no significant extra enhancement. Furthermore, we observed that there exists a limit grating frequency above which the SR enhancement effect is lost, and the reconstructed images essentially have the same resolution as the one obtained directly from the underlying imaging system without using the SIM process.

Enhancement of spatial resolution of ghost imaging via localizing and thresholding

In ghost imaging, an illumination light is split into test and reference beams which pass through two different optical systems respectively and an image is constructed with the second-order correlation between the two light beams. Since both light beams are diffracted when passing through the optical systems, the spatial resolution of ghost imaging is in general lower than that of a corresponding conventional imaging system. When Gaussian-shaped light spots are used to illuminate an object, randomly scanning across the object plane, in the ghost imaging scheme, we show th√at by localizing central positions of the spots of the reference light beam, the resolution can be increased by a factor of 2^(1/2) same as that of the corresponding conventional imaging system. We also find that the resolution can be further enhanced by setting an appropriate threshold to the bucket measurement of ghost imaging.

Stomach wall structure and vessels imaging by acoustic resolution photoacoustic microscopy

AIM To image stomach wall blood vessels and tissue, layerby-layer.METHODS We built up the acoustic resolution photoacoustic microscopy(AR-PAM) system for imaging layered tissues, such as the stomach wall. A tunable dye laser system was coupled to a fiber bundle. The fibers of the bundle were placed in nine directions with an incident angle of 45° around a high-frequency ultrasound transducer attached to the acoustic lens. This structure formed a dark field on the tissue surface under the acoustic lens and the nine light beams from the fibers to be combined near the focal point of the acoustic lens. The sample piece was cut from a part of the porcine stomach into a petri dish. In order to realize photoacoustic depth imaging of tumor, we designed a tumor model based on indocyanine green(ICG) dye. The ICG solution(concentration of 129 μM/m L)was mixed into molten gel, and then a gel mixture of ICG(concentration of 12.9 μM/mL) was injected into the stomach submucosa. The injection quantity was controlled by 0.1 mL to make a small tumor model. RESULTS An acoustic resolution photoacoustic microscopy based on fiber illumination was established and an axial resolution of 25 μm and a lateral resolution of 50 μm in its focal zone range of 500 μm has been accomplished. We tuned the laser wavelength to 600 nm. The photoacoustic probe was driven to do B-scan imaging in tissue thickness of 200 μm. The photoacoustic micro-image of mucosa and submucosa of the tissue have been obtained and compared with a pathological photograph of the tissue stained by hematoxylin-eosin staining. We have observed more detailed internal structure of the tissue. We also utilized this photoacoustic microscopy to image blood vessels inside the submucosa. High contrast imaging of the submucosa tumor model was obtained using ICG dye. CONCLUSION This AR-PAM is able to image layer-by-layer construction and some blood vessels under mucosa in the stomach wall without any contrast agents.

Three-dimensional time-of-flight magnetic resonance angiography combined with high resolution T2-weighted imaging in preoperative evaluation of microvascular decompression

BACKGROUND Neurovascular compression(NVC) is the main cause of primary trigeminal neuralgia(TN) and hemifacial spasm(HFS). Microvascular decompression(MVD) is an effective surgical method for the treatment of TN and HFS caused by NVC. The judgement of NVC is a critical step in the preoperative evaluation of MVD, which is related to the effect of MVD treatment. Magnetic resonance imaging(MRI) technology has been used to detect NVC prior to MVD for several years. Among many MRI sequences, three-dimensional time-of-flight magnetic resonance angiography(3D TOF MRA) is the most widely used. However, 3D TOF MRA has some shortcomings in detecting NVC. Therefore, 3D TOF MRA combined with high resolution T2-weighted imaging(HR T2WI) is considered to be a more effective method to detect NVC.AIM To determine the value of 3D TOF MRA combined with HR T2WI in the judgment of NVC, and thus to assess its value in the preoperative evaluation of MVD.METHODS Related studies published from inception to September 2022 based on PubMed, Embase, Web of Science, and the Cochrane Library were retrieved. Studies that investigated 3D TOF MRA combined with HR T2WI to judge NVC in patients with TN or HFS were included according to the inclusion criteria. Studies without complete data or not relevant to the research topics were excluded. The Quality Assessment of Diagnostic Accuracy Studies checklist was used to assess the quality of included studies. The publication bias of the included literature was examined by Deeks’ test. An exact binomial rendition of the bivariate mixed-effects regression model was used to synthesize data. Data analysis was performed using the MIDAS module of statistical software Stata 16.0. Two independent investigators extracted patient and study characteristics, and discrepancies were resolved by consensus. Individual and pooled sensitivities and specificities were calculated. The I_(2) statistic and Q test were used to test heterogeneity. The study was registered on the website of PROSERO(registration No. CRD42022357158).RESULTS Our search identified 595 articles, of which 12(including 855 patients) fulfilled the inclusion criteria. Bivariate analysis showed that the pooled sensitivity and specificity of 3D TOF MRA combined with HR T2WI for detecting NVC were 0.96 [95% confidence interval(CI): 0.92-0.98] and 0.92(95%CI: 0.74-0.98), respectively. The pooled positive likelihood ratio was 12.4(95%CI: 3.2-47.8), pooled negative likelihood ratio was 0.04(95%CI: 0.02-0.09), and pooled diagnostic odds ratio was 283(95%CI: 50-1620). The area under the receiver operating characteristic curve was 0.98(95%CI: 0.97-0.99). The studies showed no substantial heterogeneity(I2 = 0, Q = 0.001 P = 0.50).CONCLUSION Our results suggest that 3D TOF MRA combined with HR T2WI has excellent sensitivity and specificity for judging NVC in patients with TN or HFS. This method can be used as an effective tool for preoperative evaluation of MVD.

High-resolution bone microstructure imaging based on ultrasonic frequency-domain full-waveform inversion

The main challenge in bone ultrasound imaging is the large acoustic impedance contrast and sound velocity differences between the bone and surrounding soft tissue. It is difficult for conventional pulse-echo modalities to give accurate ultrasound images for irregular bone boundaries and microstructures using uniform sound velocity assumption rather than getting a prior knowledge of sound speed. To overcome these limitations, this paper proposed a frequency-domain fullwaveform inversion(FDFWI) algorithm for bone quantitative imaging utilizing ultrasonic computed tomography(USCT).The forward model was calculated in the frequency domain by solving the full-wave equation. The inverse problem was solved iteratively from low to high discrete frequency components via minimizing a cost function between the modeled and measured data. A quasi-Newton method called the limited-memory Broyden–Fletcher–Goldfarb–Shanno algorithm(L-BFGS) was utilized in the optimization process. Then, bone images were obtained based on the estimation of the velocity and density. The performance of the proposed method was verified by numerical examples, from tubular bone phantom to single distal fibula model, and finally with a distal tibia-fibula pair model. Compared with the high-resolution peripheral quantitative computed tomography(HR-p QCT), the proposed FDFWI can also clearly and accurately presented the wavelength scaled pores and trabeculae in bone images. The results proved that the FDFWI is capable of reconstructing high-resolution ultrasound bone images with sub-millimeter resolution. The parametric bone images may have the potential for the diagnosis of bone disease.

Spatial resolution and image processing for pinhole camera-based X-ray fluorescence imaging: a simulation study

Spatial resolution and image-processing methods for full-field X-ray fluorescence(FF-XRF)imaging using X-ray pinhole cameras were studied using Geant4simulations with different geometries and algorithms for image reconstruction.The main objectives were:(1)calculating the quantum efficiency curves of specific cameras,(2)studying the relationships between the spatial resolution and the pinhole diameter,magnification,and camera binning value,and(3)comparing image-processing methods for pinhole camera systems.Several results were obtained using a point and plane source as the X-ray fluorescence emitter and an array of 100×100 silicon pixel detectors as the X-ray camera.The quantum efficiency of a back-illuminated deep depletion(BI-DD)structure was above 30%for the XRF energies in the 0.8–9 keV range,with the maximum of 93.7%at 4 keV.The best spatial resolution of the pinhole camera was 24.7μm and 31.3 lp/mm when measured using the profile function of the point source,with the diameter of 20μm,magnification of 3.16,and camera bin of 1.A blind deconvolution algorithm with Gaussian filtering performed better than the Wiener filter and Richardson iterative methods on FF-XRF images,with the signal-to-noise ratio of 7.81 dB and improved signalto-noise ratio of 7.24 dB at the diameter of 120μm,magnification of 1.0,and camera bin of 1.

A fast decoupled ISAR high-resolution imaging method using structural sparse information under low SNR

Inverse synthetic aperture radar (ISAR) image can be represented and reconstructed by sparse recovery (SR) approaches. However, the existing SR algorithms, which are used for ISAR imaging, have suffered from high computational cost and poor imaging quality under a low signal to noise ratio (SNR) condition. This paper proposes a fast decoupled ISAR imaging method by exploiting the inherent structural sparse information of the targets. Firstly, the ISAR imaging problem is decoupled into two sub-problems. One is range direction imaging and the other is azimuth direction focusing. Secondly, an efficient two-stage SR method is proposed to obtain higher resolution range profiles by using jointly sparse information. Finally, the residual linear Bregman iteration via fast Fourier transforms (RLBI-FFT) is proposed to perform the azimuth focusing on low SNR efficiently. Theoretical analysis and simulation results show that the proposed method has better performence to efficiently implement higher-resolution ISAR imaging under the low SNR condition.

Influence of the interaction volume on the kinetic energy resolution of a velocity map imaging spectrometer

We investigate the influence of the interaction volume on the energy resolution of a velocity map imaging spectrometer. The simulation results show that the axial interaction size has a significant influence on the resolution. This influence is increased for a higher kinetic energy. We further show that the radial interaction size has a minor influence on the energy resolution for the electron or ion with medium energy, but it is crucial for the resolution of the electron or ion With low kinetic energy. By tracing the flight trajectories we show how the electron or ion energy resolution is influenced by the interaction size.

Multiframe Blind Super Resolution Imaging Based on Blind Deconvolution

As an ill-posed problem, multiframe blind super resolution imaging recovers a high resolution image from a group of low resolution images with some degradations when the information of blur kernel is limited. Note that the quality of the recovered image is influenced more by the accuracy of blur estimation than an advanced regularization. We study the traditional model of the multiframe super resolution and modify it for blind deblurring. Based on the analysis, we proposed two algorithms. The first one is based on the total variation blind deconvolution algorithm and formulated as a functional for optimization with the regularization of blur. Based on the alternating minimization and the gradient descent algorithm, the high resolution image and the unknown blur kernel are estimated iteratively. By using the median shift and add operator, the second algorithm is more robust to the outlier influence. The MSAA initialization simplifies the interpolation process to reconstruct the blurred high resolution image for blind deblurring and improves the accuracy of blind super resolution imaging. The experimental results demonstrate the superiority and accuracy of our novel algorithms.

MTF Measurement of EBCCD Imaging System by Using Super Resolution Technique

Existing methods of measurement MTF for discrete imaging system are analysed. A slit target is frequently used to measure the MTF for an imaging system. Usually there are four methods to measure the MTF for a discrete imaging system by using a slit. These methods have something imperfect respectively. But for the discrete imaging systems of under sampling it is difficult to reproduce this type of target properly since frequencies above Nyquist are folded into those below Nyquist, resulting in aliasing effect. To tackle the aliasing problem, a super resolution technique is introduced into our measurement, which gives MTF values both above and below Nyquist more accurately.

HIGH RESOLUTION REAL-TIME MEDICAL IMAGING BASED ON PARALLEL BEAMFORMING TECHNIQUE

Improvement of frame-rate is very important for high quality ultrasound imaging of fast-moving structures.It is also one of the key technologies of Three-Dimension(3-D) real-time medical imaging.In this paper,we have demonstrated a beamforming method which gives imaging frame-rate increment without sacrificing the quality of medical images.By using wider and fewer transmit beams in combination with four narrower parallel receive beams,potentially increasing the imaging frame-rate by a factor four.Through employing full transmit aperture,controlling the mainlobe width,and suppressing sidelobes of angular responses,the inherent gain loss of normal parallel beamfomer can be compensated in the maximal degree.The noise and interference signals also can be suppressed effectively.Finally,we show comparable lateral resolution and contrast of ultrasound images to normal single widow weighting beamformer on simulated phantoms of point targets,cyst and fetus of 12th week.As the computational cost is linear with the number of array elements and the same with Delay And Sum(DAS) beamformers,this method has great ad-vantages of possibility for high frame-rate real-time applications.

High-resolution forward-looking imaging algorithm for missile-borne detectors

Aiming at a novel missile-borne detector in the optional burst height proximity fuze, a self-adaptive high-resolution forward-looking imaging algorithm (SAHRFL-IA) is presented. The echo data are captured by the missile-borne detector in the target regions;thereby the azimuth angulation accuracy at the same distance dimension is improved dynamically. Thus, azimuth information of the targets in the detection area may be obtained accurately. The proposed imaging algorithm breaks through the conventional misconception of merely using azimuth discrimination curves under ideal conditions during monopulse angulation. The real-time echo data from the target region are used to perform error correction for this discrimination curve, and finally the accuracy of the azimuth angulation may reach the optimum at the same distance dimension. A series of experiments demonstrate the validity, reliability and high performance of the proposed imaging algorithm. Azimuth angulation accuracy may reach ten times that of the detection beam width. Meanwhile, the running time of this algorithm satisfies the requirements of missile-borne platforms.

A super-high angular resolution principle for coded-mask X-ray imaging beyond the diffraction limit of a single pinhole

High angular resolution X-ray imaging is always useful in astrophysics and solar physics. In principle, it can be performed by using coded-mask imaging with a very long mask-detector distance. Previously, the diffraction-interference effect was thought to degrade coded-mask imaging performance dramatically at the low energy end with its very long mask-detector distance. The diffraction-interference effect is described with numerical calculations, and the diffraction-interference cross correlation reconstruction method （DICC） is developed in order to overcome the imaging performance degradation. Based on the DICC, a super-high angular resolution principle （SHARP） for coded-mask X-ray imaging is proposed. The feasibility of coded mask imaging beyond the diffraction limit of a single pinhole is demonstrated with simulations. With the specification that the mask element size is 50 × 50 μm^2 and the mask-detector distance is 50 m, the achieved angular resolution is 0.32arcsec above about 10keV and 0.36arcsec at 1.24keV （λ = 1 nm）, where diffraction cannot be neglected. The on-axis source location accuracy is better than 0.02 arcsec. Potential applications for solar observations and wide-field X-ray monitors are also briefly discussed.

Super-resolution filtered ghost imaging with compressed sensing

A filtered ghost imaging(GI)protocol is proposed that enables the Rayleigh diffraction limit to be exceeded in an intensity correlation system;a super-resolution reconstructed image is achieved by low-pass filtering of the measured intensities.In a lensless GI experiment performed with spatial bandpass filtering,the spatial resolution can exceed the Rayleigh diffraction bound by more than a factor of 10.The resolution depends on the bandwidth of the filter,and the relationship between the two is investigated and discussed.In combination with compressed sensing programming,not only high resolution can be maintained but also image quality can be improved,while a much lower sampling number is sufficient.

Super-Resolution Imaging of Mammograms Based on the Super-Resolution Convolutional Neural Network

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.

Photoacoustic mesoscopy:pushing toward the depth limit in the high-resolution optical imaging for biomedical applications and clinical potentials

Photoacoustic mesoscopy(PAMe) offers high-sensitivity in vivo imaging based on the rich optical contrast in biological tissues,with sub-100-micron resolutions at a few millimeters depth. By benefiting from low ultrasonic scattering,this emerging technology has pushed the penetration depth beyond the optical diffuse limit unprecedented for high-resolution optical methods.Here,we review ed the state-of-art implementations of PAMe and their achievements in biological and primary clinical applications. With the high-frequency focused ultrasonic detector,the high-resolution optical visualization can be achieved by utilizing various PAMe systems. These capabilities of PAMe have made it well applicable for understanding the biological mechanisms,exploring the pathological features and analyzing the characteristics of human skin. Future improvements and prospects of PAMe are also mentioned,suggesting its great potential tow ards the corresponding emerging biomedical and clinical applications.