Quality Of Reconstructed Images Research Articles

Parallel computational ghost imaging with modulation patterns multiplexing and permutation inspired by compound eyes

Real-time computational ghost imaging (CGI) has received significant attention in recent years to overcome the trade-off between long acquisition time and high reconstructed image quality of CGI. Inspired by compound eyes, we propose a parallel computational ghost imaging with modulation patterns multiplexing and permutation to achieve a faster and high-resolution CGI. With modulation patterns multiplexing and permutation, several small overlapping fields-of-view can be obtained; meanwhile, the difficulty in alignment of illumination light field and multiple detectors can be well resolved. The method combining compound eyes with multi-detectors to capture light intensity can resolve the issue of a gap between detector units in the array detector. Parallel computation facilitates significantly reduced acquisition time, while maintaining reconstructed quality without compromising the sampling ratio. Experiments indicate that using m × m detectors reduce modulation pattern count, projector storage, and projection time to around 1/m2 of typical CGI methods, while increasing image resolution to m2 times. This work greatly promotes the practicability of parallel computational ghost imaging and provides optional solution for real-time computational ghost imaging.

Quality improvement to holographic microscopy reconstruction based on Kramers-Kronig relations and phase background fitting.

Spectrum aliasing in off-axis digital holography may result in poor image reconstruction quality. This study proposes a method to eliminate the zero-order spectrum and enhance image quality based on Kramers-Kronig relations and phase background fitting. The Kramers-Kronig relations are employed to derive the quotient of the complex wavefront of object and the reference beam, and phase background fitting is performed in a compensatory way to yield the object complex wavefront. The effectiveness of the proposed approach is validated via simulations and experiments. The results show significantly improved off-axis digital holographic microscopy reconstruction quality, making the proposed method a promising option for holographic microscopy imaging.

Boosting Multi-modal Ocular Recognition via Spatial Feature Reconstruction and Unsupervised Image Quality Estimation

Boosting Multi-modal Ocular Recognition via Spatial Feature Reconstruction and Unsupervised Image Quality Estimation

Image quality of photon-counting detector CT virtual monoenergetic and polyenergetic reconstructions for head and neck CT angiography

We compared image quality of head and neck CT angiography (CTA) obtained with a photon-counting detector CT (PCD-CT), including virtual monoenergetic images and polyenergetic reconstructions, and conventional energy-integrating detectors CT (EID-CT) in three patients. PCD-CT monoenergetic reconstructions at 70 keV and lower provided excellent image quality, with improved signal-to-noise and contrast-to-noise compared to EID-CT and PCD-CT polyenergetic reconstructions. PCD-CT may enable radiation dose and iodinated contrast dose reduction for cerebrovascular imaging.

Optimal algorithm for color medical encryption and compression images based on DNA coding and a hyperchaotic system in the moments

Currently, visual data security plays a significant role in various fields, especially in medical imaging. Addressing the challenges associated with limited key space and vulnerability to different types of attacks within current encryption schemes, this work proposes an optimal compression-encryption scheme for large medical images that incorporates elements of Archimedes' optimization algorithm, discrete orthogonal Hahn moments, chaotic systems, and DNA coding. The primary aim of this study is to develop an optimal and exceptionally resilient compression-encryption scheme capable of countering various attack types effectively. This approach is structured into three principal phases: a compression phase harnessing the efficiencies of Hahn's discrete orthogonal moments (HMs) in signal and image representation, coupled with the Archimedes optimization algorithm (AO) to ensure optimal tuning of polynomial parameters (a, b) for superior image reconstruction quality. The encryption phase is performed on the compressed image, using hyperchaotic memristive 4-D (HCM-4D), adapted logistics map (ALM) and DNA coding. Initially, the adapted logistics map is responsible for generating random sequences linked to the compressed image. Subsequently, chaotic sequences originating from the hyperchaotic 4-D memristive system govern both random sequences and DNA processes. The optimization phase, facilitated by the AO algorithm, focuses on minimizing the value of the objective function (correlation) on the compressed and encrypted images. Ultimately, the image with the lowest correlation value is designated as the optimal compressed-encrypted representation.The simulation results clearly illustrate the resilience of the AO algorithm when juxtaposed with other optimization algorithms, especially with respect to convergence speed and computational efficiency. On the other hand, the proposed compression approach demonstrated exceptional efficiency in compressing medical images, offering us the possibility to achieve impressive compression ratio (CR) as well as exceptional quality in decompressed images, evident thanks to high PSNR values. In addition, security analyze demonstrate that the proposed compression-encryption benefits from a larger key space and superior resistance against different types of attacks. Furthermore, our approach was subjected to a comparative analysis alongside various encryption method. These comparisons demonstrate that our encryption algorithm surpasses others in terms of both security and effectiveness.

EEUR-Net: End-to-End Optimization of Under-Sampling and Reconstruction Network for 3D Magnetic Resonance Imaging

It is time-consuming to acquire complete data by fully phase encoding in two orthogonal directions along with one frequency encoding direction. Under-sampling in the 3D k-space is promising in accelerating such 3D MRI process. Although 3D under-sampling can be conducted according to predefined probability density, the density-based method is not optimal. Because of the large amount of 3D data and computational cost, it is challenging to perform data-driven and learning-based 3D under-sampling and subsequent 3D reconstruction. To tackle this challenge, this paper proposes a deep neural network called EEUR-Net, realized by optimizing specific under-sampling patterns for the fully sampled 3D k-space data. Innovatively, our under-sampling algorithm employs an end-to-end deep learning approach to optimize phase encoding patterns and uses a 3D U-Net for image reconstruction of under-sampled data. Through end-to-end training, we obtain an optimized 3D under-sampling pattern, which significantly enhances the quality of the reconstructed image under the same acceleration factor. A series of experiments on a knee MRI dataset demonstrate that, in comparison to standard random uniform, radial, Poisson and equispaced Cartesian under-sampling schemes, our end-to-end learned under-sampling pattern considerably improves the reconstruction quality of under-sampled MRI images.

Deep convolutional dictionary learning network for sparse view CT reconstruction with a group sparse prior

Purpose Numerous techniques based on deep learning have been utilized in sparse view computed tomography (CT) imaging. Nevertheless, the majority of techniques are instinctively constructed utilizing state-of-the-art opaque convolutional neural networks (CNNs) and lack interpretability. Moreover, CNNs tend to focus on local receptive fields and neglect nonlocal self-similarity prior information. Obtaining diagnostically valuable images from sparsely sampled projections is a challenging and ill-posed task.Method To address this issue, we propose a unique and understandable model named DCDL-GS for sparse view CT imaging. This model relies on a network comprised of convolutional dictionary learning and a nonlocal group sparse prior. To enhance the quality of image reconstruction, we utilize a neural network in conjunction with a statistical iterative reconstruction framework and perform a set number of iterations. Inspired by group sparsity priors, we adopt a novel group thresholding operation to improve the feature representation and constraint ability and obtain a theoretical interpretation. Furthermore, our DCDL-GS model incorporates filtered backprojection (FBP) reconstruction, fast sliding window nonlocal self-similarity operations, and a lightweight and interpretable convolutional dictionary learning network to enhance the applicability of the model.Results The efficiency of our proposed DCDL-GS model in preserving edges and recovering features is demonstrated by the visual results obtained on the LDCT-P and UIH datasets. Compared to the results of the most advanced techniques, the quantitative results are enhanced, with increases of 0.6-0.8 dB for the peak signal-to-noise ratio (PSNR), 0.005-0.01 for the structural similarity index measure (SSIM), and 1-1.3 for the regulated Fréchet inception distance (rFID) on the test dataset. The quantitative results also show the effectiveness of our proposed deep convolution iterative reconstruction module and nonlocal group sparse prior.Conclusion In this paper, we create a consolidated and enhanced mathematical model by integrating projection data and prior knowledge of images into a deep iterative model. The model is more practical and interpretable than existing approaches. The results from the experiment show that the proposed model performs well in comparison to the others.

Weakly-Supervised Contrastive Learning for Unsupervised Object Discovery.

Unsupervised object discovery (UOD) refers to the task of discriminating the whole region of objects from the background within a scene without relying on labeled datasets, which benefits the task of bounding-box-level localization and pixel-level segmentation. This task is promising due to its ability to discover objects in a generic manner. We roughly categorize existing techniques into two main directions, namely the generative solutions based on image resynthesis, and the clustering methods based on self-supervised models. We have observed that the former heavily relies on the quality of image reconstruction, while the latter shows limitations in effectively modeling semantic correlations. To directly target at object discovery, we focus on the latter approach and propose a novel solution by incorporating weakly-supervised contrastive learning (WCL) to enhance semantic information exploration. We design a semantic-guided self-supervised learning model to extract high-level semantic features from images, which is achieved by fine-tuning the feature encoder of a self-supervised model, namely DINO, via WCL. Subsequently, we introduce Principal Component Analysis (PCA) to localize object regions. The principal projection direction, corresponding to the maximal eigenvalue, serves as an indicator of the object region(s). Extensive experiments on benchmark unsupervised object discovery datasets demonstrate the effectiveness of our proposed solution. The source code and experimental results are publicly available via our project page at https://github.com/npucvr/WSCUOD.git.

Spatial and Modal Optimal Transport for Fast Cross-Modal MRI Reconstruction.

Multi-modal magnetic resonance imaging (MRI) plays a crucial role in comprehensive disease diagnosis in clinical medicine. However, acquiring certain modalities, such as T2-weighted images (T2WIs), is time-consuming and prone to be with motion artifacts. It negatively impacts subsequent multi-modal image analysis. To address this issue, we propose an end-to-end deep learning framework that utilizes T1-weighted images (T1WIs) as auxiliary modalities to expedite T2WIs' acquisitions. While image pre-processing is capable of mitigating misalignment, improper parameter selection leads to adverse pre-processing effects, requiring iterative experimentation and adjustment. To overcome this shortage, we employ Optimal Transport (OT) to synthesize T2WIs by aligning T1WIs and performing cross-modal synthesis, effectively mitigating spatial misalignment effects. Furthermore, we adopt an alternating iteration framework between the reconstruction task and the cross-modal synthesis task to optimize the final results. Then, we prove that the reconstructed T2WIs and the synthetic T2WIs become closer on the T2 image manifold with iterations increasing, and further illustrate that the improved reconstruction result enhances the synthesis process, whereas the enhanced synthesis result improves the reconstruction process. Finally, experimental results from FastMRI and internal datasets confirm the effectiveness of our method, demonstrating significant improvements in image reconstruction quality even at low sampling rates.

Image Quality and Lesion Detection of Multiplanar Reconstruction Images Using Deep Learning: Comparison with Hybrid Iterative Reconstruction.

We assessed and compared the image quality of normal and pathologic structures as well as the image noise in chest computed tomography images using "adaptive statistical iterative reconstruction-V" (ASiR-V) or deep learning reconstruction "TrueFidelity". Forty consecutive patients with suspected lung disease were evaluated. The 1.25-mm axial images and 2.0-mm coronal multiplanar images were reconstructed under the following three conditions: (i) ASiR-V, lung kernel with 60% of ASiR-V; (ii) TF-M, standard kernel, image filter (Lung) with TrueFidelity at medium strength; and (iii) TF-H, standard kernel, image filter (Lung) with TrueFidelity at high strength. Two radiologists (readers) independently evaluated the image quality of anatomic structures using a scale ranging from 1 (best) to 5 (worst). In addition, readers ranked their image preference. Objective image noise was measured using a circular region of interest in the lung parenchyma. Subjective image quality scores, total scores for normal and abnormal structures, and lesion detection were compared using Wilcoxon's signed-rank test. Objective image quality was compared using Student's paired t-test and Wilcoxon's signed-rank test. The Bonferroni correction was applied to the P value, and significance was assumed only for values of P < 0.016. Both readers rated TF-M and TF-H images significantly better than ASiR-V images in terms of visualization of the centrilobular region in axial images. The preference score of TF-M and TF-H images for reader 1 were better than that of ASiR-V images, and the preference score of TF-H images for reader 2 were significantly better than that of ASiR-V and TF-M images. TF-M images showed significantly lower objective image noise than ASiR-V or TF-H images. TrueFidelity showed better image quality, especially in the centrilobular region, than ASiR-V in subjective and objective evaluations. In addition, the image texture preference for TrueFidelity was better than that for ASiR-V.

Feasibility of a Prototype Image Reconstruction Algorithm for Motion Correction in Interventional Cone-Beam CT Scans

Assess the feasibility of a prototype image reconstruction algorithm in correcting motion artifacts in cone-beam computed tomography (CBCT) scans of interventional instruments in the lung. First, phantom experiments were performed to assess the algorithm, using the Xsight lung phantom with custom inserts containing straight or curved catheters. During scanning, the inserts moved in a continuous sinusoidal or breath-hold mimicking pattern, with varying amplitudes and frequencies. Subsequently, the algorithm was applied to CBCT data from navigation bronchoscopy procedures. The algorithm's performance was assessed quantitatively via edge-sharpness measurements and qualitatively by three specialists. In the phantom study, the algorithm improved sharpness in 13 out of 14 continuous sinusoidal motion and five out of sevenbreath-hold mimicking scans, with more significant effects at larger motion amplitudes. Analysis of 27 clinical scans showed that the motion corrected reconstructions had significantly sharper edges than standard reconstructions (2.81 (2.24-6.46) vs. 2.80 (2.16-4.75), p=0.003). These results were consistent with the qualitative assessment, which showed higher scores in the sharpness of bronchoscope-tissue interface and catheter-tissue interface in the motion-corrected reconstructions. However, the tumor demarcation ratings were inconsistent between raters, and the overall image quality of the new reconstructions was rated lower. Our findings suggest that applying the new prototype algorithm for motion correction in CBCT images is feasible. The algorithm improved the sharpness of medical instruments in CBCT scans obtained during diagnostic navigation bronchoscopy procedures, which was demonstrated both quantitatively and qualitatively.

Facial Image Compression via Neural Image Manifold Compression

Although the recent learning-based image and video coding techniques achieve rapid development, the signal fidelity-driven target in these methods leads to the divergence to a highly effective and efficient coding framework for both human and machine. In this paper, we aim to address the issue by making use of the power of generative models to bridge the gap between full fidelity (for human vision) and high discrimination (for machine vision). Therefore, relying on existing pretrained generative adversarial networks (GAN), we build a GAN inversion framework that projects the image into a low-dimensional natural image manifold. In this manifold, the feature is highly discriminative and also encodes the appearance information of the image, named as <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">latent code</i> . Taking a variational bit-rate constraint with a hyperprior model to model/suppress the entropy of image manifold code, our method is capable of fulfilling the needs of both machine and human visions at very low bit-rates. To improve the visual quality of image reconstruction, we further propose <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">multiple latent codes</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">scalable inversion</i> . The former gets several latent codes in the inversion, while the latter additionally compresses and transmits a shallow compact feature to support visual reconstruction. Experimental results demonstrate the superiority of our method in both human vision tasks, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i.e</i> . image reconstruction, and machine vision tasks, including semantic parsing and attribute prediction.

Super-resolution reconstruction algorithm for dim and blurred traffic sign images in complex environments

&lt;abstract&gt; &lt;p&gt;In poor lighting and rainy and foggy bad weather environments, road traffic signs are blurred and have low recognition, etc. A super-resolution reconstruction algorithm for complex lighting and bad weather traffic sign images was proposed. First, a novel attention residual module was designed to incorporate an aggregated feature attention mechanism on the jump connection side of the base residual module so that the deep network can obtain richer detail information; second, a cross-layer jump connection feature fusion mechanism was adopted to enhance the flow of information across layers as well as to prevent the problem of gradient disappearance of the deep network to enhance the reconstruction of the edge detail information; and lastly, a positive-inverse dual-channel sub-pixel convolutional up-sampling method was designed to reconstruct super-resolution images to obtain better pixel and spatial information expression. The evaluation model was trained on the Chinese traffic sign dataset in a natural scene, and when the scaling factor is 4, the average values of PSNR and SSIM are improved by 0.031 when compared with the latest release of the deep learning-based super-resolution reconstruction algorithm for single-frame images, MICU (Multi-level Information Compensation and U-net), the average values of PSNR and SSIM are improved by 0.031 dB and 0.083, and the actual test average reaches 20.946 dB and 0.656. The experimental results show that the reconstructed image quality of this paper's algorithm is better than the mainstream algorithms of comparison in terms of objective indexes and subjective feelings. The super-resolution reconstructed image has a higher peak signal-to-noise ratio and perceptual similarity. It can provide certain technical support for the research of safe driving assistive devices in natural scenes under multi-temporal varying illumination conditions and bad weather.&lt;/p&gt; &lt;/abstract&gt;

Application of compressive sensing techniques for advanced image processing and digital image transmission

The field of compressive sensing (CS) has emerged as a transformative approach in the acquisition and processing of high-dimensional data. This paper presents a comprehensive study on the application of compressive sensing techniques to advanced image processing and digital image transmission. By leveraging the inherent sparsity in natural images, CS allows for significant reductions in the amount of data required for accurate reconstruction, thereby overcoming the limitations imposed by the traditional Shannon-Nyquist sampling theorem. We explore the theoretical foundations of CS, including the principles of sparsity and incoherence, and provide a detailed overview of the Orthogonal Matching Pursuit (OMP) algorithm, a prominent greedy algorithm used for sparse signal recovery. Experimental results demonstrate the efficacy of CS in improving image reconstruction quality, as evidenced by enhancements in peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM). Additionally, we discuss the practical implementation of CS in single-pixel cameras and its potential impact on future imaging technologies. The findings suggest that CS offers a robust framework for efficient image acquisition and processing, making it a valuable tool for various applications in multimedia, medical imaging, and remote sensing.

Super-tokens Auto-encoders for image compression and reconstruction in IoT applications

New telecommunications networks are enabling powerful AI applications for smart cities and transport. These applications require real-time processing of large amounts of media data. Sending data to the cloud for processing is very difficult due to latency and energy constraints. Lossy compression can help, but traditional codecs may not provide enough quality or be efficient enough for resource-constrained devices. This paper proposes a new image compression and processing approach based on variational auto-encoders (VAEs). This VAE-based method aims to efficiently compress images while still allowing for high-quality reconstruction and object detection tasks. The encoder is designed to be lightweight and suitable for devices with limited computing power. The decoder is more complex and uses multi-level vector quantization to reconstruct high-resolution images. This approach allows for a simple encoder on edge devices and a powerful decoder on cloud servers. Key contributions include a low-complexity encoder, a new VAE model based on vector quantization, and a framework for using VAEs in IoT. The first experiments on reconstructed images on CelebA and ImageNet100 datasets show promising results in terms of MS-SSIM, PSNR, MSE and rFID compared to the literature and the ability of our approach to be used in IoT applications. Our approach presents results similar to complex algorithms like compression algorithms BPG in term of trade-off rate-distortion, and hierarchical auto-encoder (HQA) in terms of image reconstruction quality

Image Reconstruction for Accelerated MR Scan With Faster Fourier Convolutional Neural Networks.

High quality image reconstruction from undersampled k -space data is key to accelerating MR scanning. Current deep learning methods are limited by the small receptive fields in reconstruction networks, which restrict the exploitation of long-range information, and impede the mitigation of full-image artifacts, particularly in 3D reconstruction tasks. Additionally, the substantial computational demands of 3D reconstruction considerably hinder advancements in related fields. To tackle these challenges, we propose the following: 1) A novel convolution operator named Faster Fourier Convolution (FasterFC), aims at providing an adaptable broad receptive field for spatial domain reconstruction networks with fast computational speed. 2) A split-slice strategy that substantially reduces the computational load of 3D reconstruction, enabling high-resolution, multi-coil, 3D MR image reconstruction while fully utilizing inter-layer and intra-layer information. 3) A single-to-group algorithm that efficiently utilizes scan-specific and data-driven priors to enhance k -space interpolation effects. 4) A multi-stage, multi-coil, 3D fast MRI method, called the faster Fourier convolution based single-to-group network (FAS-Net), comprising a single-to-group k -space interpolation algorithm and a FasterFC-based image domain reconstruction module, significantly minimizes the computational demands of 3D reconstruction through split-slice strategy. Experimental evaluations conducted on the NYU fastMRI and Stanford MRI Data datasets reveal that the FasterFC significantly enhances the quality of both 2D and 3D reconstruction results. Moreover, FAS-Net, characterized as a method that can achieve high-resolution (320, 320, 256), multi-coil, (8 coils), 3D fast MRI, exhibits superior reconstruction performance compared to other state-of-the-art 2D and 3D methods.

Carbon nanotube-based multiple source C-arm CT system: feasibility study with prototype system.

To extend the field of view while reducing dimensions of the C-arm, we propose a carbon nanotube (CNT)-based C-arm computed tomography (CT) system with multiple X-ray sources. A prototype system was developed using three CNT X-ray sources, enabling a feasibility study. Geometry calibration and image reconstruction were performed to improve the quality of image acquisition. However, the geometry of the prototype system led to projection truncation for each source and an overlap region of object area covered by each source in the two-dimensional Radon space, necessitating specific corrective measures. We addressed these problems by implementing truncation correction and applying weighting techniques to the overlap region during the image reconstruction phase. Furthermore, to enable image reconstruction with a scan angle less than 360°, we designed a weighting function to solve data redundancy caused by the short scan angle. The accuracy of the geometry calibration method was evaluated via computer simulations. We also quantified the improvements in reconstructed image quality using mean-squared error and structural similarity. Moreover, detector lag correction was applied to address the afterglow observed in the experimental data obtained from the prototype system. Our evaluation of image quality involved comparing reconstructed images obtained with and without incorporating the geometry calibration results and images with and without lag correction. The outcomes of our simulation study and experimental investigation demonstrated the efficacy of our proposed geometry calibration, image reconstruction method, and lag correction in reducing image artifacts.

Reconstruction of Sparse-View X-ray Computed Tomography Based on Adaptive Total Variation Minimization.

Sparse-view reconstruction has garnered significant interest in X-ray computed tomography (CT) imaging owing to its ability to lower radiation doses and enhance detection efficiency. Among current methods for sparse-view CT reconstruction, an algorithm utilizing iterative reconstruction based on full variational regularization demonstrates good performance. The optimized direction and number of computations for the gradient operator of the regularization term play a crucial role in determining not only the reconstructed image quality but also the convergence speed of the iteration process. The conventional TV approach solely accounts for the vertical and horizontal directions of the two-dimensional plane in the gradient direction. When projection data decrease, the edges of the reconstructed image become blurred. Exploring too many gradient directions for TV terms often comes at the expense of more computational costs. To enhance the balance of computational cost and reconstruction quality, this study suggests a novel TV computation model that is founded on a four-direction gradient operator. In addition, selecting appropriate iteration parameters significantly impacts the quality of the reconstructed image. We propose a nonparametric control method utilizing the improved TV approach as a solution to the tedious manual parameter optimization issue. The relaxation parameters of projection onto convex sets (POCS) are determined according to the scanning number and numerical proportion of the projection data; according to the image error before and after iterations, the gradient descent step of the TV item is adaptively adjusted. Compared with several representative iterative reconstruction algorithms, the experimental results show that the algorithm can effectively preserve edges and suppress noise in sparse-view CT reconstruction.

Flexible and accurate total variation and cascaded denoisers-based image reconstruction algorithm for hyperspectrally compressed ultrafast photography

Hyperspectrally compressed ultrafast photography (HCUP) based on compressed sensing and time- and spectrum-to-space mappings can simultaneously realize the temporal and spectral imaging of non-repeatable or difficult-to-repeat transient events with a passive manner in single exposure. HCUP possesses an incredibly high frame rate of tens of trillions of frames per second and a sequence depth of several hundred, and therefore plays a revolutionary role in single-shot ultrafast optical imaging. However, due to ultra-high data compression ratios induced by the extremely large sequence depth, as well as limited fidelities of traditional algorithms over the image reconstruction process, HCUP suffers from a poor image reconstruction quality and fails to capture fine structures in complex transient scenes. To overcome these restrictions, we report a flexible image reconstruction algorithm based on a total variation (TV) and cascaded denoisers (CD) for HCUP, named the TV-CD algorithm. The TV-CD algorithm applies the TV denoising model cascaded with several advanced deep learning-based denoising models in the iterative plug-and-play alternating direction method of multipliers framework, which not only preserves the image smoothness with TV, but also obtains more priori with CD. Therefore, it solves the common sparsity representation problem in local similarity and motion compensation. Both the simulation and experimental results show that the proposed TV-CD algorithm can effectively improve the image reconstruction accuracy and quality of HCUP, and may further promote the practical applications of HCUP in capturing high-dimensional complex physical, chemical and biological ultrafast dynamic scenes.

Quality of T2-weighted MRI re-acquisition versus deep learning GAN image reconstruction: A multi-reader study

PurposeTo evaluate CycleGAN's ability to enhance T2-weighted image (T2WI) quality. MethodA CycleGAN algorithm was used to enhance T2WI quality. 96 patients (192 scans) were identified from patients who underwent multiple axial T2WI due to poor quality on the first attempt (RAD1) and improved quality on re-acquisition (RAD2). CycleGAN algorithm gave DL classifier scores (0–1) for quality quantification and produced enhanced versions of QI1 and QI2 from RAD1 and RAD2, respectively. A subset (n = 20 patients) was selected for a blinded, multi-reader study, where four radiologists rated T2WI on a scale of 1–4 for quality. The multi-reader study presented readers with 60 image pairs (RAD1 vs RAD2, RAD1 vs QI1, and RAD2 vs QI2), allowing for selecting sequence preferences and quantifying the quality changes. ResultsThe DL classifier correctly discerned 71.9 % of quality classes, with 90.6 % (96/106) as poor quality and 48.8 % (42/86) as diagnostic in original sequences (RAD1, RAD2). CycleGAN images (QI1, QI2) demonstrated quantitative improvements, with consistently higher DL classifier scores than original scans (p < 0.001). In the multi-reader analysis, CycleGAN demonstrated no qualitative improvements, with diminished overall quality and motion in QI2 in most patients compared to RAD2, with noise levels remaining similar (8/20). No readers preferred QI2 to RAD2 for diagnosis. ConclusionDespite quantitative enhancements with CycleGAN, there was no qualitative boost in T2WI diagnostic quality, noise, or motion. Expert radiologists didn’t favor CycleGAN images over standard scans, highlighting the divide between quantitative and qualitative metrics.