Network For Image Reconstruction Research Articles

Dual-domain faster Fourier convolution based network for MR image reconstruction

Deep learning methods for fast MRI have shown promise in reconstructing high-quality images from undersampled multi-coil k-space data, leading to reduced scan duration. However, existing methods encounter challenges related to limited receptive fields in dual-domain (k-space and image domains) reconstruction networks, rigid data consistency operations, and suboptimal refinement structures, which collectively restrict overall reconstruction performance. This study introduces a comprehensive framework that addresses these challenges and enhances MR image reconstruction quality. Firstly, we propose Faster Inverse Fourier Convolution (FasterIFC), a frequency domain convolutional operator that significantly expands the receptive field of k-space domain reconstruction networks. Expanding the information extraction range to the entire frequency spectrum according to the spectral convolution theorem in Fourier theory enables the network to easily utilize richer redundant long-range information from adjacent, symmetrical, and diagonal locations of multi-coil k-space data. Secondly, we introduce a novel softer Data Consistency (softerDC) layer, which achieves an enhanced balance between data consistency and smoothness. This layer facilitates the implementation of diverse data consistency strategies across distinct frequency positions, addressing the inflexibility observed in current methods. Finally, we present the Dual-Domain Faster Fourier Convolution Based Network (D2F2), which features a centrosymmetric dual-domain parallel structure based on FasterIFC. This architecture optimally leverages dual-domain data characteristics while substantially expanding the receptive field in both domains. Coupled with the softerDC layer, D2F2 demonstrates superior performance on the NYU fastMRI dataset at multiple acceleration factors, surpassing state-of-the-art methods in both quantitative and qualitative evaluations.

UPAMNet: A unified network with deep knowledge priors for photoacoustic microscopy

Photoacoustic microscopy (PAM) has gained increasing popularity in biomedical imaging, providing new opportunities for tissue monitoring and characterization. With the development of deep learning techniques, convolutional neural networks have been used for PAM image resolution enhancement and denoising. However, there exist several inherent challenges for this approach. This work presents a Unified PhotoAcoustic Microscopy image reconstruction Network (UPAMNet) for both PAM image super-resolution and denoising. The proposed method takes advantage of deep image priors by incorporating three effective attention-based modules and a mixed training constraint at both pixel and perception levels. The generalization ability of the model is evaluated in details and experimental results on different PAM datasets demonstrate the superior performance of the method. Experimental results show improvements of 0.59 dB and 1.37 dB, respectively, for 1/4 and 1/16 sparse image reconstruction, and 3.9 dB for image denoising in peak signal-to-noise ratio.

Iterative shrinkage thresholding-based anti-multi-noise compression perceptual image reconstruction network

Iterative shrinkage thresholding-based anti-multi-noise compression perceptual image reconstruction network

Ferumoxytol-Enhanced Cardiac Cine MRI Reconstruction Using a Variable-Splitting Spatiotemporal Network.

Balanced steady-state free precession (bSSFP) imaging is commonly used in cardiac cine MRI but prone to image artifacts. Ferumoxytol-enhanced (FE) gradient echo (GRE) has been proposed as an alternative. Utilizing the abundance of bSSFP images to develop a computationally efficient network that is applicable to FE GRE cine would benefit future network development. To develop a variable-splitting spatiotemporal network (VSNet) for image reconstruction, trained on bSSFP cine images and applicable to FE GRE cine images. Retrospective and prospective. 41 patients (26 female, 53 ± 19 y/o) for network training, 31 patients (19 female, 49 ± 17 y/o) and 5 healthy subjects (5 female, 30 ± 7 y/o) for testing. 1.5T and 3T, bSSFP and GRE. VSNet was compared to VSNet with total variation loss, compressed sensing and low rank methods for 14× accelerated data. The GRAPPA×2/×3 images served as the reference. Peak signal-to-noise-ratio (PSNR), structural similarity index (SSIM), left ventricular (LV) and right ventricular (RV) end-diastolic volume (EDV), end-systolic volume (ESV), and ejection fraction (EF) were measured. Qualitative image ranking and scoring were independently performed by three readers. Latent scores were calculated based on scores of each method relative to the reference. Linear mixed-effects regression, Tukey method, Fleiss' Kappa, Bland-Altman analysis, and Bayesian categorical cumulative probit model. A P-value <0.05 was considered statistically significant. VSNet achieved significantly higher PSNR (32.7 ± 0.2), SSIM (0.880 ± 0.004), rank (2.14 ± 0.06), and latent scores (-1.72 ± 0.22) compared to other methods (rank >2.90, latent score < -2.63). Fleiss' Kappa was 0.52 for scoring and 0.61 for ranking. VSNet showed no significantly different LV and RV ESV (P = 0.938) and EF (P = 0.143) measurements, but statistically significant different (2.62 mL) EDV measurements compared to the reference. VSNet produced the highest image quality and the most accurate functional measurements for FE GRE cine images among the tested 14× accelerated reconstruction methods. 3 TECHNICAL EFFICACY: Stage 1.

A cross-domain complex convolution neural network for undersampled magnetic resonance image reconstruction

To introduce a new cross-domain complex convolution neural network for accurate MR image reconstruction from undersampled k-space data. Most reconstruction methods utilize neural networks or cascade neural networks in either the image domain and/or the k-space domain. However, these methods encounter several challenges: 1) Applying neural networks directly in the k-space domain is suboptimal for feature extraction; 2) Classic image-domain networks have difficulty in fully extracting texture features; and 3) Existing cross-domain methods still face challenges in extracting and fusing features from both image and k-space domains simultaneously. In this work, we propose a novel deep-learning-based 2-D single-coil complex-valued MR reconstruction network termed TEID-Net. TEID-Net integrates three modules: 1) TE-Net, an image-domain-based sub-network designed to enhance contrast in input features by incorporating a Texture Enhancement Module; 2) ID-Net, an intermediate-domain sub-network tailored to operate in the image-Fourier space, with the specific goal of reducing aliasing artifacts realized by leveraging the superior incoherence property of the decoupled one-dimensional signals; and 3) TEID-Net, a cross-domain reconstruction network in which ID-Nets and TE-Nets are combined and cascaded to boost the quality of image reconstruction further. Extensive experiments have been conducted on the fastMRI and Calgary-Campinas datasets. Results demonstrate the effectiveness of the proposed TEID-Net in mitigating undersampling-induced artifacts and producing high-quality image reconstructions, outperforming several state-of-the-art methods while utilizing fewer network parameters. The cross-domain TEID-Net excels in restoring tissue structures and intricate texture details. The results illustrate that TEID-Net is particularly well-suited for regular Cartesian undersampling scenarios.

SWISTA-Nets: Subband-adaptive wavelet iterative shrinkage thresholding networks for image reconstruction

Robust and interpretable image reconstruction is central to imageology applications in clinical practice. Prevalent deep networks, with strong learning ability to extract implicit information from data manifold, are still lack of prior knowledge introduced from mathematics or physics, leading to instability, poor structure interpretability and high computation cost. As to this issue, we propose two prior knowledge-driven networks to combine the good interpretability of mathematical methods and the powerful learnability of deep learning methods. Incorporating different kinds of prior knowledge, we propose subband-adaptive wavelet iterative shrinkage thresholding networks (SWISTA-Nets), where almost every network module is in one-to-one correspondence with each step involved in the iterative algorithm. By end-to-end training of proposed SWISTA-Nets, implicit information can be extracted from training data and guide the tuning process of key parameters that possess mathematical definition. The inverse problems associated with two medical imaging modalities, i.e., electromagnetic tomography and X-ray computational tomography are applied to validate the proposed networks. Both visual and quantitative results indicate that the SWISTA-Nets outperform mathematical methods and state-of-the-art prior knowledge-driven networks, especially with fewer training parameters, interpretable network structures and well robustness. We assume that our analysis will support further investigation of prior knowledge-driven networks in the field of ill-posed image reconstruction.

Application of a deep-learning neural network for image reconstruction from a single-pixel infrared camera

Application of a deep-learning neural network for image reconstruction from a single-pixel infrared camera

Multi-Scale Image- and Feature-Level Alignment for Cross-Resolution Person Re-Identification

Cross-Resolution Person Re-Identification (re-ID) aims to match images with disparate resolutions arising from variations in camera hardware and shooting distances. Most conventional works utilize Super-Resolution (SR) models to recover Low Resolution (LR) images to High Resolution (HR) images. However, because the SR models cannot completely compensate for the missing information in the LR images, there is still a large gap between the HR image recovered from the LR images and the real HR images. To tackle this challenge, we propose a novel Multi-Scale Image- and Feature-Level Alignment (MSIFLA) framework to align the images on multiple resolution scales at both the image and feature level. Specifically, (i) we design a Cascaded Multi-Scale Resolution Reconstruction (CMSR2) module, which is composed of three cascaded Image Reconstruction (IR) networks, and can continuously reconstruct multiple variables of different resolution scales from low to high for each image, regardless of image resolution. The reconstructed images with specific resolution scales are of similar distribution; therefore, the images are aligned on multiple resolution scales at the image level. (ii) We propose a Multi-Resolution Representation Learning (MR2L) module which consists of three-person re-ID networks to encourage the IR models to preserve the ID-discriminative information during training separately. Each re-ID network focuses on mining discriminative information from a specific scale without the disturbance from various resolutions. By matching the extracted features on three resolution scales, the images with different resolutions are also aligned at the feature-level. We conduct extensive experiments on multiple public cross-resolution person re-ID datasets to demonstrate the superiority of the proposed method. In addition, the generalization of MSIFLA in handling cross-resolution retrieval tasks is verified on the UAV vehicle dataset.

Industrial Product Surface Anomaly Detection with Realistic Synthetic Anomalies Based on Defect Map Prediction.

The occurrence of anomalies on the surface of industrial products can lead to issues such as decreased product quality, reduced production efficiency, and safety hazards. Early detection and resolution of these problems are crucial for ensuring the quality and efficiency of production. The key challenge in applying deep learning to surface defect detection of industrial products is the scarcity of defect samples, which will make supervised learning methods unsuitable for surface defect detection problems. Therefore, it is a reasonable solution to use anomaly detection methods to deal with surface defect detection. Among image-based anomaly detection, reconstruction-based methods are the most commonly used. However, reconstruction-based approaches lack the involvement of defect samples in the training process, posing the risk of a perfect reconstruction of defects by the reconstruction network. In this paper, we propose a reconstruction-based defect detection algorithm that addresses these challenges by utilizing more realistic synthetic anomalies for training. Our model focuses on creating authentic synthetic defects and introduces an auto-encoder image reconstruction network with deep feature consistency constraints, as well as a defect separation network with a large receptive field. We conducted experiments on the challenging MVTec anomaly detection dataset and our trained model achieved an AUROC score of 99.70% and an average precision (AP) score of 99.87%. Our method surpasses recently proposed defect detection algorithms, thereby enhancing the accuracy of surface defect detection in industrial products.

A Faithful Deep Sensitivity Estimation for Accelerated Magnetic Resonance Imaging.

Magnetic resonance imaging (MRI) is an essential diagnostic tool that suffers from prolonged scan time. To alleviate this limitation, advanced fast MRI technology attracts extensive research interests. Recent deep learning has shown its great potential in improving image quality and reconstruction speed. Faithful coil sensitivity estimation is vital for MRI reconstruction. However, most deep learning methods still rely on pre-estimated sensitivity maps and ignore their inaccuracy, resulting in the significant quality degradation of reconstructed images. In this work, we propose a Joint Deep Sensitivity estimation and Image reconstruction network, called JDSI. During the image artifacts removal, it gradually provides more faithful sensitivity maps with high-frequency information, leading to improved image reconstructions. To understand the behavior of the network, the mutual promotion of sensitivity estimation and image reconstruction is revealed through the visualization of network intermediate results. Results on in vivo datasets and radiologist reader study demonstrate that, for both calibration-based and calibrationless reconstruction, the proposed JDSI achieves the state-of-the-art performance visually and quantitatively, especially when the acceleration factor is high. Additionally, JDSI owns nice robustness to patients and autocalibration signals.

HARA-GAN: Hybrid Attention and Relative Average Discriminator Based Generative Adversarial Network for MR Image Reconstruction

HARA-GAN: Hybrid Attention and Relative Average Discriminator Based Generative Adversarial Network for MR Image Reconstruction

Adaptive Local Neighborhood-based Neural Networks for MR Image Reconstruction from Undersampled Data

Adaptive Local Neighborhood-based Neural Networks for MR Image Reconstruction from Undersampled Data

SOUL-Net: A Sparse and Low-Rank Unrolling Network for Spectral CT Image Reconstruction.

Spectral computed tomography (CT) is an emerging technology, that generates a multienergy attenuation map for the interior of an object and extends the traditional image volume into a 4-D form. Compared with traditional CT based on energy-integrating detectors, spectral CT can make full use of spectral information, resulting in high resolution and providing accurate material quantification. Numerous model-based iterative reconstruction methods have been proposed for spectral CT reconstruction. However, these methods usually suffer from difficulties such as laborious parameter selection and expensive computational costs. In addition, due to the image similarity of different energy bins, spectral CT usually implies a strong low-rank prior, which has been widely adopted in current iterative reconstruction models. Singular value thresholding (SVT) is an effective algorithm to solve the low-rank constrained model. However, the SVT method requires a manual selection of thresholds, which may lead to suboptimal results. To relieve these problems, in this article, we propose a sparse and low-rank unrolling network (SOUL-Net) for spectral CT image reconstruction, that learns the parameters and thresholds in a data-driven manner. Furthermore, a Taylor expansion-based neural network backpropagation method is introduced to improve the numerical stability. The qualitative and quantitative results demonstrate that the proposed method outperforms several representative state-of-the-art algorithms in terms of detail preservation and artifact reduction.

Semantics-Guided Hierarchical Feature Encoding Generative Adversarial Network for Visual Image Reconstruction From Brain Activity.

The utilization of deep learning techniques for decoding visual perception images from brain activity recorded by functional magnetic resonance imaging (fMRI) has garnered considerable attention in recent research. However, reconstructed images from previous studies still suffer from low quality or unreliability. Moreover, the complexity inherent to fMRI data, characterized by high dimensionality and low signal-to-noise ratio, poses significant challenges in extracting meaningful visual information for perceptual reconstruction. In this regard, we proposes a novel neural decoding model, named the hierarchical semantic generative adversarial network (HS-GAN), inspired by the hierarchical encoding of the visual cortex and the homology theory of convolutional neural networks (CNNs), which is capable of reconstructing perceptual images from fMRI data by leveraging the hierarchical and semantic representations. The experimental results demonstrate that HS-GAN achieved the best performance on Horikawa2017 dataset (histogram similarity: 0.447, SSIM-Acc: 78.9%, Peceptual-Acc: 95.38%, AlexNet(2): 96.24% and AlexNet(5): 94.82%) over existing advanced methods, indicating improved naturalness and fidelity of the reconstructed image. The versatility of the HS-GAN was also highlighted, as it demonstrated promising generalization capabilities in reconstructing handwritten digits, achieving the highest SSIM (0.783±0.038), thus extending its application beyond training solely on natural images.

Unsupervised fabric defect detection based on multiscale image reconstruction and structural similarity assessment

AbstractFabric defect detection is a crucial aspect of the textile industry. Currently, deep learning methods have demonstrated exceptional performance in fabric defect detection tasks. However, their performance is greatly affected by the number of defect samples, which is a challenge to obtain during actual production. To address this issue, this article proposes an unsupervised anomaly detection method for fabric defects using image reconstruction networks. This method only requires defect‐free samples for training. During the training phase, the model compresses defect‐free samples to obtain a low‐dimensional manifold and reconstruct them. During the inference phase, the method assesses whether a sample is defective by calculating the reconstruction error between the input and output images, and locates the defect region by computing the difference in various patches. Furthermore, since fabric contains rich texture features, with high correlation between neighbouring pixels, a structure similarity index measure combined with mean absolute error is introduced to evaluate the reconstruction error, which enhances the model's representation ability for defect‐free samples. Additionally, considering the diverse texture backgrounds in fabric, a multiscale reconstruction module is designed to optimise the reconstruction effect. Experimental results demonstrate that compared with other related approaches, the proposed method achieves high accuracy (image‐based area under the curve (AUC) up to 98.2% and pixel‐based AUC up to 97.3%) on multiple datasets and has good generalisation ability for different fabric textures.

DOTnet 2.0: Deep learning network for diffuse optical tomography image reconstruction

Breast cancer is the most common cancer worldwide. The standard imaging modality for breast cancer screening is X-ray mammography, which suffers from low sensitivities in women with dense breasts and can potentially cause cancers despite a low radiation dosage. Diffuse Optical Tomography (DOT) is a noninvasive imaging technique that can potentially be employed to improve breast cancer early detection. However, conventional model-based algorithms for reconstructing DOT images usually produce low-quality images with limited resolution and low reconstruction accuracy. We propose to integrate deep neural networks (DNNs) with the conventional DOT reconstruction methods. This hybrid framework significantly enhances image quality. The DNNs have been trained and tested with sample data derived from clinically relevant breast models. The sample dataset contains blood vessel structures from breast structures and artificially created vessels using the Lindenmayer-system algorithm. By comparing the hybrid reconstruction with the ground truth image, we demonstrated a multi scale - structural similarity index measure (MS-SSIM) score of 0.80–0.90. Whereas using conventional reconstruction, MS-SSIM provided a much inferior score of 0.36–0.59. In terms of DOT image quality, both qualitative and quantitative assessments of the reconstructed images signify that the hybrid approach is superior to conventional methods. This improvement suggests that DOT can potentially become a viable alternative to breast cancer screening, providing a step towards the next-generation device for optical mammography.

A Deep Convolutional Gated Recurrent Unit for CT Image Reconstruction.

Computed tomography (CT) is one of the most important medical imaging technologies in use today. Most commercial CT products use a technique known as the filtered backprojection (FBP) that is fast and can produce decent image quality when an X-ray dose is high. However, the FBP is not good enough on low-dose X-ray CT imaging because the CT image reconstruction problem becomes more stochastic. A more effective reconstruction technique proposed recently and implemented in a limited number of CT commercial products is an iterative reconstruction (IR). The IR technique is based on a Bayesian formulation of the CT image reconstruction problem with an explicit model of the CT scanning, including its stochastic nature, and a prior model that incorporates our knowledge about what a good CT image should look like. However, constructing such prior knowledge is more complicated than it seems. In this article, we propose a novel neural network for CT image reconstruction. The network is based on the IR formulation and constructed with a recurrent neural network (RNN). Specifically, we transform the gated recurrent unit (GRU) into a neural network performing CT image reconstruction. We call it "GRU reconstruction." This neural network conducts concurrent dual-domain learning. Many deep learning (DL)-based methods in medical imaging are single-domain learning, but dual-domain learning performs better because it learns from both the sinogram and the image domain. In addition, we propose backpropagation through stage (BPTS) as a new RNN backpropagation algorithm. It is similar to the backpropagation through time (BPTT) of an RNN; however, it is tailored for iterative optimization. Results from extensive experiments indicate that our proposed method outperforms conventional model-based methods, single-domain DL methods, and state-of-the-art DL techniques in terms of the root mean squared error (RMSE), the peak signal-to-noise ratio (PSNR), and the structure similarity (SSIM) and in terms of visual appearance.

Ultrafast Cardiac Imaging Using Deep Learning for Speckle-Tracking Echocardiography.

High-quality ultrafast ultrasound imaging is based on coherent compounding from multiple transmissions of plane waves (PW) or diverging waves (DW). However, compounding results in reduced frame rate, as well as destructive interferences from high-velocity tissue motion if motion compensation (MoCo) is not considered. While many studies have recently shown the interest of deep learning for the reconstruction of high-quality static images from PW or DW, its ability to achieve such performance while maintaining the capability of tracking cardiac motion has yet to be assessed. In this article, we addressed such issue by deploying a complex-weighted convolutional neural network (CNN) for image reconstruction and a state-of-the-art speckle-tracking method. The evaluation of this approach was first performed by designing an adapted simulation framework, which provides specific reference data, i.e., high-quality, motion artifact-free cardiac images. The obtained results showed that, while using only three DWs as input, the CNN-based approach yielded an image quality and a motion accuracy equivalent to those obtained by compounding 31 DWs free of motion artifacts. The performance was then further evaluated on nonsimulated, experimental in vitro data, using a spinning disk phantom. This experiment demonstrated that our approach yielded high-quality image reconstruction and motion estimation, under a large range of velocities and outperforms a state-of-the-art MoCo-based approach at high velocities. Our method was finally assessed on in vivo datasets and showed consistent improvement in image quality and motion estimation compared to standard compounding. This demonstrates the feasibility and effectiveness of deep learning reconstruction for ultrafast speckle-tracking echocardiography.

Multi-Channel Representation Learning Enhanced Unfolding Multi-Scale Compressed Sensing Network for High Quality Image Reconstruction.

Deep Unfolding Networks (DUNs) serve as a predominant approach for Compressed Sensing (CS) reconstruction algorithms by harnessing optimization. However, a notable constraint within the DUN framework is the restriction to single-channel inputs and outputs at each stage during gradient descent computations. This constraint compels the feature maps of the proximal mapping module to undergo multi-channel to single-channel dimensionality reduction, resulting in limited feature characterization capabilities. Furthermore, most prevalent reconstruction networks rely on single-scale structures, neglecting the extraction of features from different scales, thereby impeding the overall reconstruction network's performance. To address these limitations, this paper introduces a novel CS reconstruction network termed the Multi-channel and Multi-scale Unfolding Network (MMU-Net). MMU-Net embraces a multi-channel approach, featuring the incorporation of Adap-SKConv with an attention mechanism to facilitate the exchange of information between gradient terms and enhance the feature map's characterization capacity. Moreover, a Multi-scale Block is introduced to extract multi-scale features, bolstering the network's ability to characterize and reconstruct the images. Our study extensively evaluates MMU-Net's performance across multiple benchmark datasets, including Urban100, Set11, BSD68, and the UC Merced Land Use Dataset, encompassing both natural and remote sensing images. The results of our study underscore the superior performance of MMU-Net in comparison to existing state-of-the-art CS methods.

Adaptive deep learning network for image reconstruction of compressed sensing

Adaptive deep learning network for image reconstruction of compressed sensing