Mean Peak Signal-to-noise Ratio Research Articles

Optimizing Image Watermarking with Dual-Tree Complex Wavelet Transform and Particle Swarm Intelligence for Secure and High-Quality Protection

Watermarking is a technique used to address issues related to the widespread use of the internet, such as copyright protection, tamper localization, and authentication. However, most watermarking approaches negatively affect the quality of the original image. In this research, we propose an optimized image watermarking approach that utilizes the dual-tree complex wavelet transform and particle swarm optimization algorithm. Our approach focuses on maintaining the highest possible quality of the watermarked image by minimizing any noticeable changes. During the embedding phase, we break down the original image using a technique called dual-tree complex wavelet transform (DTCWT) and then use particle swarm optimization (PSO) to choose specific coefficients. We embed the bits of a binary logo into the least significant bits of these selected coefficients, creating the watermarked image. To extract the watermark, we reverse the embedding process by first decomposing both versions of the input image using DTCWT and extracting the same coefficients to retrieve those corresponding bits (watermark). In our experiments, we used a common dataset from watermarking research to demonstrate the functionality against various watermarked copies and peak signal-to-noise ratio (PSNR) and normalized cross-correlation (NCC) metrics. The PSNR is a measure of how well the watermarked image maintains its original quality, and the NCC reflects how accurately the watermark can be extracted. Our method gives mean PSNR and NCC of 80.50% and 92.51%, respectively.

Validation of deep-learning accelerated quantitative susceptibility mapping for deep brain nuclei

PurposeTo test the feasibility and consistency of a deep-learning (DL) accelerated QSM method for deep brain nuclei evaluation.MethodsParticipants were scanned with both parallel imaging (PI)-QSM and DL-QSM methods. The PI- and DL-QSM scans had identical imaging parameters other than acceleration factors (AF). The DL-QSM employed Poisson disk style under-sampling scheme and a previously developed cascaded CNN based reconstruction model, with acquisition time of 4:35, 3:15, and 2:11 for AF of 3, 4, and 5, respectively. For PI-QSM acquisition, the AF was 2 and the acquisition time was 6:46. The overall image similarity was assessed between PI- and DL-QSM images using the structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR). QSM values from 7 deep brain nuclei were extracted and agreements between images with different Afs were assessed. Finally, the correlations between age and QSM values in the selected deep brain nuclei were evaluated.Results59 participants were recruited. Compared to PI-QSM images, the mean SSIM of DL images were 0.87, 0.86, and 0.85 for AF of 3, 4, and 5. The mean PSNR were 44.56, 44.53, and 44.23. Susceptibility values from DL-QSM were highly consistent with routine PI-QSM images, with differences of less than 5% at the group level. Furthermore, the associations between age and QSM values could be consistently revealed.ConclusionDL-QSM could be used for measuring susceptibility values of deep brain nucleus. An AF up to 5 did not significantly impact the correlation between age and susceptibility in deep brain nuclei.

Two self-supervised image denoiser designs with discrete wavelet transform and non-local means-based algorithms

Image denoising is crucial in applications like medical imaging and photography, where restoring high-quality images from noisy data is essential. Traditional techniques often struggle with complex noise patterns, while deep learning-based methods typically rely on clean-noisy image pairs for training, limiting their practicality. Additionally, deep learning approaches face challenges such as the lack of ground truth clean images, sensitivity to specific noise types, and the introduction of artifacts during processing. In this work, we propose two novel self-supervised denoising approaches: a Discrete Wavelet Transform (DWT)-based model and a Non-Local Means (NLM)-based model. The DWT-based approach employs wavelet decomposition to separate image details across multiple frequency scales, selectively suppressing high-frequency noise via soft thresholding while preserving low-frequency components. The resulting wavelet coefficients are used to create pseudo-clean targets for training a U-Net architecture, ensuring effective denoising while maintaining structural integrity. The NLM-based approach leverages redundancy in image patches by applying the NLM algorithm to generate pseudo-clean targets through patch similarity-based averaging. These targets train a U-Net model with a custom loss function that balances Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR), and Structural Similarity Index (SSIM), optimizing perceptual quality. Both models are trained on 5,000 noisy images from the ImageNet validation set without relying on clean references. Validated on synthetic Gaussian and Poisson noise at varying magnitudes, the DWT-based model achieved Mean PSNR and SSIM values of 31.07 and 0.9279, respectively, while the NLM-based model attained 30.17 and 0.9303. These results demonstrate the robustness and effectiveness of the proposed methods, making them suitable for real-world applications such as medical diagnostics and low-light photography.

Using a patient-specific diffusion model to generate CBCT-based synthetic CTs for CBCT-guided adaptive radiotherapy.

Cone beam computed tomography (CBCT) can be used to evaluate the inter-fraction anatomical changes during the entire course for image-guided radiotherapy (IGRT). However, CBCT artifacts from various sources restrict the full application of CBCT-guided adaptive radiation therapy (ART). Inter-fraction anatomical changes during ART, including variations in tumor size and normal tissue anatomy, can affect radiation therapy (RT) efficacy. Acquiring high-quality CBCT images that accurately capture patient- and fraction-specific (PFS) anatomical changes is crucial for successful IGRT. To enhance CBCT image quality, we proposed PFS lung diffusion models (PFS-LDMs). The proposed PFS models use a pre-trained general lung diffusion model (GLDM) as a baseline, which is trained on historical deformed CBCT (dCBCT)-planning CT (pCT) paired data. For a given patient, a new PFS model is fine-tuned on a CBCT-deformed pCT (dpCT) pair after each fraction to learn the PFS knowledge for generating personalized synthetic CT (sCT) with quality comparable to pCT or dpCT. The learned PFS knowledge is the specific mapping relationships, including personal inter-fraction anatomical changes between personalized CBCT-dpCT pairs. The PFS-LDMs were evaluated on an institutional lung cancer dataset, quantified by mean absolute error (MAE), peak signal-to-noise ratio (PSNR), normalized cross-correlation (NCC), and structural similarity index measure (SSIM) metrics. We also compared our PFS-LDMs with a mainstream GAN-based model, demonstrating that our PFS fine-tuning strategy could be applied to existing generative models. Our models showed remarkable improvements across all four evaluation metrics. The proposed PFS-LDMs outperformed the GLDM, demonstrating the effectiveness of our proposed fine-tuning strategy. The PFS model fine-tuned with CBCT images from four prior fractions, reduced the MAE from 103.95 to 15.96 Hounsfield units (HU), and increased the mean PSNR, NCC, and SSIM from 25.36dB to 33.57dB, 0.77 to 0.98, and 0.75 to 0.97, respectively. Applying our PFS fine-tuning strategy to a Cycle GAN model also showed improvements, with all four fine-tuned PFS Cycle GAN (PFS-CG) models outperforming the general Cycle GAN model. Overall, our proposed PFS fine-tuning strategy improved CBCT image quality compared to both the pre-correction and non-fine-tuned general models, with our proposed PFS-LDMs yielding better performance than the GAN-based model across all metrics. Our proposed PFS-LDMs significantly improve CBCT image quality with increased HU accuracy and fewer artifacts, thus better capturing inter-fraction anatomical changes. This lays the groundwork for enabling CBCT-based ART, which could enhance clinical efficiency and achieve personalized high-precision treatment by accounting for inter-fraction anatomical changes.

Improved protection for colour images via invertible colour‐to‐grey, image distortion, and visible‐imperceptible watermarking

AbstractInvertible colour‐to‐grey algorithms protect the colour of an image against illegal usage and distribution. These schemes hide the colour information into a grayscale version of the image, making colour recovery without proper authorization challenging. A previous study proposed the incorporation of content security by distorting the protected image to hinder illegal structure restoration. This work addresses the limitations of this method, significantly improving both processing time and the quality of the recovered colour image. Specifically, processing times are reduced from 45 h to 9 s, and the mean PSNR value is increased by up to 2.23 dB. Furthermore, this proposal achieves competitive results compared to existing approaches that do not implement content security, obtaining mean peak signal‐to‐noise ratio (PSNR) and structural similarity index measure (SSIM) values above 42.32 dB and 0.992, respectively. Finally, quantitative results are supported by visual comparisons.

Engineered 3D Vortex Array with Customized Energy and Topological Charges for Multi‐View Display

AbstractArrays of multiple vortex beams enhance parallel processing capabilities from particle manipulation to information communication. However, the spatial position, topological charge, and energy parameters of the vortex beams within the array have yet to be precisely controlled, posing significant challenges to the realization of multi‐view 3D Orbital Angular Momentum (OAM) display using vortex arrays as information carriers. To address this issue, a method for generating vortex arrays based on a phase‐only hologram, customizing the array by using the energy and OAM spectrum of each vortex beam as the loss function is developed. Experimental results indicate that a 2D array generates 100 vortex beams in the spatial frequency domain, while a 3D array in the Fresnel zone produces 252 vortex beams across 7 planes, each with 36 unprecedentedly controllable energy and topological charge vortex beams. Subsequently, images of 4 views using the 3D vortex arrays and decoded through coordinate transformation to achieve a multi‐view 3D OAM display are encoded. The results demonstrate imaging quality with Mean Peak Signal‐to‐Noise Ratio (MPSNR) of 12.7, 13.0, 13.4, and 12.2 dB in 4 views, respectively, offering promising opportunities for applications in 3D optical manipulation, high‐capacity communication, and 3D OAM holography.

Motion Correction for Brain MRI Using Deep Learning and a Novel Hybrid Loss Function

Purpose: Motion-induced magnetic resonance imaging (MRI) artifacts can deteriorate image quality and reduce diagnostic accuracy, but motion by human subjects is inevitable and can even be caused by involuntary physiological movements. Deep-learning-based motion correction methods might provide a solution. However, most studies have been based on directly applying existing models, and the trained models are rarely accessible. Therefore, we aim to develop and evaluate a deep-learning-based method (Motion Correction-Net, or MC-Net) for suppressing motion artifacts in brain MRI scans. Methods: A total of 57 subjects, providing 20,889 slices in four datasets, were used. Furthermore, 3T 3D sagittal magnetization-prepared rapid gradient-echo (MP-RAGE) and 2D axial fluid-attenuated inversion-recovery (FLAIR) sequences were acquired. The MC-Net was derived from a UNet combined with a two-stage multi-loss function. T1-weighted axial brain images contaminated with synthetic motions were used to train the network to remove motion artifacts. Evaluation used simulated T1- and T2-weighted axial, coronal, and sagittal images unseen during training, as well as T1-weighted images with motion artifacts from real scans. The performance indices included the peak-signal-to-noise ratio (PSNR), the structural similarity index measure (SSIM), and visual reading scores from three blinded clinical readers. A one-sided Wilcoxon signed-rank test was used to compare reader scores, with p < 0.05 considered significant. Intraclass correlation coefficients (ICCs) were calculated for inter-rater evaluations. Results: The MC-Net outperformed other methods in terms of PSNR and SSIM for the T1 axial test set. The MC-Net significantly improved the quality of all T1-weighted images for all directions (i.e., the mean SSIM of axial, sagittal, and coronal slices improved from 0.77, 0.64, and 0.71 to 0.92, 0.75, and 0.84; the mean PSNR improved from 26.35, 24.03, and 24.55 to 29.72, 24.40, and 25.37, respectively) and for simulated as well as real motion artifacts, both using quantitative measures and visual scores. However, MC-Net performed poorly for images with untrained T2-weighted contrast because the T2 contrast was unseen during training and is different from T1 contrast. Conclusion: The proposed two-stage multi-loss MC-Net can effectively suppress motion artifacts in brain MRI without compromising image quality. Given the efficiency of MC-Net (with a single-image processing time of ~40 ms), it can potentially be used in clinical settings.

Technical note: Minimizing CIED artifacts on a 0.35 T MRI-Linac using deep learning.

Artifacts from implantable cardioverter defibrillators (ICDs) are a challenge to magnetic resonance imaging (MRI)-guided radiotherapy (MRgRT). This study tested an unsupervised generative adversarial network to mitigate ICD artifacts in balanced steady-state free precession (bSSFP) cine MRIs and improve image quality and tracking performance for MRgRT. Fourteen healthy volunteers (Group A) were scanned on a 0.35 T MRI-Linac with and without an MR conditional ICD taped to their left pectoral to simulate an implanted ICD. bSSFP MRI data from 12 of the volunteers were used to train a CycleGAN model to reduce ICD artifacts. The data from the remaining two volunteers were used for testing. In addition, the dataset was reorganized three times using a Leave-One-Out scheme. Tracking metrics [Dice similarity coefficient (DSC), target registration error (TRE), and 95 percentile Hausdorff distance (95% HD)] were evaluated for whole-heart contours. Image quality metrics [normalized root mean square error (nRMSE), peak signal-to-noise ratio (PSNR), and multiscale structural similarity (MS-SSIM) scores] were evaluated. The technique was also tested qualitatively on three additional ICD datasets (Group B) including a patient with an implanted ICD. For the whole-heart contour with CycleGAN reconstruction: 1) Mean DSC rose from 0.910 to 0.935; 2) Mean TRE dropped from 4.488 to 2.877mm; and 3) Mean 95% HD dropped from 10.236 to 7.700mm. For the whole-body slice with CycleGAN reconstruction: 1) Mean nRMSE dropped from 0.644 to 0.420; 2) Mean MS-SSIM rose from 0.779 to 0.819; and 3) Mean PSNR rose from 18.744 to 22.368. The three Group B datasets evaluated qualitatively displayed a reduction in ICD artifacts in the heart. CycleGAN-generated reconstructions significantly improved both tracking and image quality metrics when used to mitigate artifacts from ICDs.

Super-Resolution Reconstruction of CT Images Based on Multi-scale Information Fused Generative Adversarial Networks.

The popularization and widespread use of computed tomography (CT) in the field of medicine evocated public attention to the potential radiation exposure endured by patients. Reducing the radiation dose may lead to scattering noise and low resolution, which can adversely affect the radiologists' judgment. Hence, this paper introduces a new network called PANet-UP-ESRGAN (PAUP-ESRGAN), specifically designed to obtain low-dose CT (LDCT) images with high peak signal-to-noise ratio (PSNR) and high resolution (HR). The model was trained on synthetic medical image data based on a Generative Adversarial Network (GAN). A degradation modeling process was introduced to accurately represent realistic degradation complexities. To reconstruct image edge textures, a pyramidal attention model call PANet was added before the middle of the multiple residual dense blocks (MRDB) in the generator to focus on high-frequency image information. The U-Net discriminator with spectral normalization was also designed to improve its efficiency and stabilize the training dynamics. The proposed PAUP-ESRGAN model was evaluated on the abdomen and lung image datasets, which demonstrated a significant improvement in terms of robustness of model and LDCT image detail reconstruction, compared to the latest real-esrgan network. Results showed that the mean PSNR increated by 19.1%, 25.05%, and 21.25%, the mean SSIM increated by 0.4%, 0.4%, and 0.4%, and the mean NRMSE decreated by 0.25%, 0.25%, and 0.35% at 2[Formula: see text], 4[Formula: see text], and 8[Formula: see text] super-resolution scales, respectively. Experimental results demonstrate that our method outperforms the state-of-the-art super-resolution methods on restoring CT images with respect to peak signal-to-noise ratio (PSNR), structural similarity (SSIM) and normalized root-mean-square error (NRMSE) indices.

EDSR: Empowering super-resolution algorithms with high-quality DIV2K images

Remarkable strides have been made in Enhanced-resolution image reconstruction in recent times. In this research, we propose EDSR, a novel algorithm leveraging high-quality DIV2K images to enhance super-resolution algorithms’ performance. Our approach addresses challenges associated with capturing and reconstructing fine details and textures in low-resolution images. The training process utilizes a deep neural network fed with the extensive DIV2K dataset, comprising meticulously selected high-resolution images for super-resolution tasks. The network learns from these high-quality images to improve super-resolved outputs’ accuracy and fidelity. Extensive experimentation evaluates the effectiveness of the EDSR algorithm in achieving superior results. Experimental outcomes exhibit the remarkable progress made by EDSR compared to other leading super-resolution algorithms. The mean PSNR values obtained using EDSR on various test datasets indicate substantial improvement in image quality. The SSIM scores show enhanced preservation of fine details and textures. In the Nature category, the EDSR algorithm exhibits impressive performance, achieving a mean Peak Signal-to-Noise Ratio (PSNR) of 35.92 dB and a Structural Similarity Index (SSIM) of 0.9321. When analyzing Portrait images, the algorithm consistently maintains high quality, delivering a mean PSNR of 34.17 dB and an SSIM of 0.9125. For Cityscape images, EDSR showcases excellent capabilities with a mean PSNR of 36.05 dB and an SSIM of 0.9382, highlighting its exceptional handling in this category. Lastly, in the Still Life category, the algorithm demonstrates competence, achieving a mean PSNR of 33.79 dB and an SSIM of 0.9024. In conclusion, the proposed EDSR algorithm empowers super-resolution algorithms by leveraging high-quality DIV2K images. The empirical findings validate that EDSR is highly efficient in enhancing image quality and preserving fine details.

Handling Missing MRI Data in Brain Tumors Classification Tasks: Usage of Synthetic Images vs. Duplicate Images and Empty Images.

Deep-learning is widely used for lesion classification. However, in the clinic patient data often has missing images. To evaluate the use of generated, duplicate and empty(black) images for replacing missing MRI data in AI brain tumor classification tasks. Retrospective. 224 patients (local-dataset; low-grade-glioma (LGG) = 37, high-grade-glioma (HGG) = 187) and 335 patients (public-dataset (BraTS); LGG = 76, HGG = 259). The local-dataset was divided into training (64), validation (16), and internal-test-data (20), while the public-dataset was an independent test-set. T1WI, T1WI+C, T2WI, and FLAIR images (1.5T/3.0T-MR), obtained from different suppliers. Three image-to-image translation generative-adversarial-network (Pix2Pix-GAN) models were trained on the local-dataset, to generate T1WI, T2WI, and FLAIR images. The rating-and-preference-judgment assessment was performed by three human-readers (radiologist (MD) and two MRI-technicians). Resnet152 was used for classification, and inference was performed on both datasets, with baseline input, and with missing data replaced by 1) generated images; 2) duplication of existing images; and 3) black images. The similarity between the generated and the original images was evaluated using the peak-signal-to-noise-ratio (PSNR) and the structural-similarity-index-measure (SSIM). Classification results were evaluated using accuracy, F1-score and the Kolmogorov-Smirnov test and distance. For baseline-state, the classification model reached to accuracy = 0.93,0.82 on the local and public-datasets. For the missing-data methods, high similarity was obtained between the generated and the original images with mean PSNR = 35.65,32.94 and SSIM = 0.87,0.91 on the local and public-datasets; 39% of the generated-images were labeled as real images by the human-readers. The classification model using generated-images to replace missing images produced the highest results with mean accuracy = 0.91,0.82 compared to 0.85,0.79 for duplicated and 0.77,0.68 for use of black images; DATA CONCLUSION: The feasibility for inference classification model on an MRI dataset with missing images using the Pix2pix-GAN generated images, was shown. The stability and generalization ability of the model was demonstrated by producing consistent results on two independent datasets. 3 TECHNICAL EFFICACY: Stage 5.

Deep-Learning-Aided Evaluation of Spondylolysis Imaged with Ultrashort Echo Time Magnetic Resonance Imaging.

Isthmic spondylolysis results in fracture of pars interarticularis of the lumbar spine, found in as many as half of adolescent athletes with persistent low back pain. While computed tomography (CT) is the gold standard for the diagnosis of spondylolysis, the use of ionizing radiation near reproductive organs in young subjects is undesirable. While magnetic resonance imaging (MRI) is preferable, it has lowered sensitivity for detecting the condition. Recently, it has been shown that ultrashort echo time (UTE) MRI can provide markedly improved bone contrast compared to conventional MRI. To take UTE MRI further, we developed supervised deep learning tools to generate (1) CT-like images and (2) saliency maps of fracture probability from UTE MRI, using ex vivo preparation of cadaveric spines. We further compared quantitative metrics of the contrast-to-noise ratio (CNR), mean squared error (MSE), peak signal-to-noise ratio (PSNR), and structural similarity index (SSIM) between UTE MRI (inverted to make the appearance similar to CT) and CT and between CT-like images and CT. Qualitative results demonstrated the feasibility of successfully generating CT-like images from UTE MRI to provide easier interpretability for bone fractures thanks to improved image contrast and CNR. Quantitatively, the mean CNR of bone against defect-filled tissue was 35, 97, and 146 for UTE MRI, CT-like, and CT images, respectively, being significantly higher for CT-like than UTE MRI images. For the image similarity metrics using the CT image as the reference, CT-like images provided a significantly lower mean MSE (0.038 vs. 0.0528), higher mean PSNR (28.6 vs. 16.5), and higher SSIM (0.73 vs. 0.68) compared to UTE MRI images. Additionally, the saliency maps enabled quick detection of the location with probable pars fracture by providing visual cues to the reader. This proof-of-concept study is limited to the data from ex vivo samples, and additional work in human subjects with spondylolysis would be necessary to refine the models for clinical use. Nonetheless, this study shows that the utilization of UTE MRI and deep learning tools could be highly useful for the evaluation of isthmic spondylolysis.

Shortening image registration time using a deep neural network for patient positional verification in radiotherapy.

We sought to accelerate 2D/3D image registration computation time using image synthesis with a deep neural network (DNN) to generate digitally reconstructed radiographic (DRR) images from X-ray flat panel detector (FPD) images. And we explored the feasibility of using our DNN in the patient setup verification application. Images of the prostate and of the head and neck (H&N) regions were acquired by two oblique X-ray fluoroscopic units and the treatment planning CT. DNN was designed to generate DRR images from the FPD image data. We evaluated the quality of the synthesized DRR images to compare the ground-truth DRR images using the peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM). Image registration accuracy and computation time were evaluated by comparing the 2D-3D image registration algorithm using DRR and FPD image data with DRR and synthesized DRR images. Mean PSNR values were 23.4 ± 3.7 dB and 24.1 ± 3.9 dB for the pelvic and H&N regions, respectively. Mean SSIM values for both cases were also similar (= 0.90). Image registration accuracy was degraded by a mean of 0.43mm and 0.30°, it was clinically acceptable. Computation time was accelerated by a factor of 0.69. Our DNN successfully generated DRR images from FPD image data, and improved 2D-3D image registration computation time up to 37% in average.

Synthesis of diffusion-weighted MRI scalar maps from FLAIR volumes using generative adversarial networks.

Acquisition and pre-processing pipelines for diffusion-weighted imaging (DWI) volumes are resource- and time-consuming. Generating synthetic DWI scalar maps from commonly acquired brain MRI sequences such as fluid-attenuated inversion recovery (FLAIR) could be useful for supplementing datasets. In this work we design and compare GAN-based image translation models for generating DWI scalar maps from FLAIR MRI for the first time. We evaluate a pix2pix model, two modified CycleGANs using paired and unpaired data, and a convolutional autoencoder in synthesizing DWI fractional anisotropy (FA) and mean diffusivity (MD) from whole FLAIR volumes. In total, 420 FLAIR and DWI volumes (11,957 images) from multi-center dementia and vascular disease cohorts were used for training/testing. Generated images were evaluated using two groups of metrics: (1) human perception metrics including peak signal-to-noise ratio (PSNR) and structural similarity (SSIM), (2) structural metrics including a newly proposed histogram similarity (Hist-KL) metric and mean squared error (MSE). Pix2pix demonstrated the best performance both quantitatively and qualitatively with mean PSNR, SSIM, and MSE metrics of 23.41 dB, 0.8, 0.004, respectively for MD generation, and 24.05 dB, 0.78, 0.004, respectively for FA generation. The new histogram similarity metric demonstrated sensitivity to differences in fine details between generated and real images with mean pix2pix MD and FA Hist-KL metrics of 11.73 and 3.74, respectively. Detailed analysis of clinically relevant regions of white matter (WM) and gray matter (GM) in the pix2pix images also showed strong significant (p < 0.001) correlations between real and synthetic FA values in both tissue types (R = 0.714 for GM, R = 0.877 for WM). Our results show that pix2pix's FA and MD models had significantly better structural similarity of tissue structures and fine details than other models, including WM tracts and CSF spaces, between real and generated images. Regional analysis of synthetic volumes showed that synthetic DWI images can not only be used to supplement clinical datasets, but demonstrates potential utility in bypassing or correcting registration in data pre-processing.

Generation of Conventional 18F-FDG PET Images from 18F-Florbetaben PET Images Using Generative Adversarial Network: A Preliminary Study Using ADNI Dataset.

Background and Objectives: 18F-fluorodeoxyglucose (FDG) positron emission tomography (PET) (PETFDG) image can visualize neuronal injury of the brain in Alzheimer's disease. Early-phase amyloid PET image is reported to be similar to PETFDG image. This study aimed to generate PETFDG images from 18F-florbetaben PET (PETFBB) images using a generative adversarial network (GAN) and compare the generated PETFDG (PETGE-FDG) with real PETFDG (PETRE-FDG) images using the structural similarity index measure (SSIM) and the peak signal-to-noise ratio (PSNR). Materials and Methods: Using the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, 110 participants with both PETFDG and PETFBB images at baseline were included. The paired PETFDG and PETFBB images included six and four subset images, respectively. Each subset image had a 5 min acquisition time. These subsets were randomly sampled and divided into 249 paired PETFDG and PETFBB subset images for the training datasets and 95 paired subset images for the validation datasets during the deep-learning process. The deep learning model used in this study is composed of a GAN with a U-Net. The differences in the SSIM and PSNR values between the PETGE-FDG and PETRE-FDG images in the cycleGAN and pix2pix models were evaluated using the independent Student's t-test. Statistical significance was set at p ≤ 0.05. Results: The participant demographics (age, sex, or diagnosis) showed no statistically significant differences between the training (82 participants) and validation (28 participants) groups. The mean SSIM between the PETGE-FDG and PETRE-FDG images was 0.768 ± 0.135 for the cycleGAN model and 0.745 ± 0.143 for the pix2pix model. The mean PSNR was 32.4 ± 9.5 and 30.7 ± 8.0. The PETGE-FDG images of the cycleGAN model showed statistically higher mean SSIM than those of the pix2pix model (p < 0.001). The mean PSNR was also higher in the PETGE-FDG images of the cycleGAN model than those of pix2pix model (p < 0.001). Conclusions: We generated PETFDG images from PETFBB images using deep learning. The cycleGAN model generated PETGE-FDG images with a higher SSIM and PSNR values than the pix2pix model. Image-to-image translation using deep learning may be useful for generating PETFDG images. These may provide additional information for the management of Alzheimer's disease without extra image acquisition and the consequent increase in radiation exposure, inconvenience, or expenses.

JPEG2000-Based Semantic Image Compression using CNN

Some of the computer vision applications such as understanding, recognition as well as image processing are some areas where AI techniques like convolutional neural network (CNN) have attained great success. AI techniques are not very frequently used in applications like image compression which are a part of low-level vision applications. Intensifying the visual quality of the lossy video/image compression has been a huge obstacle for a very long time. Image processing tasks and image recognition can be addressed with the application of deep learning CNNs as a result of the availability of large training datasets and the recent advances in computing power. This paper consists of a CNN-based novel compression framework comprising of Compact CNN (ComCNN) and Reconstruction CNN (RecCNN) where they are trained concurrently and ideally consolidated into a compression framework, along with MS-ROI (Multi Structure-Region of Interest) mapping which highlights the semiotically notable portions of the image. The framework attains a mean PSNR value of 32.9dB, achieving a gain of 3.52dB and attains mean SSIM value of 0.9262, achieving a gain of 0.0723dB over the other methods when compared using the 6 main test images. Experimental results in the proposed study validate that the architecture substantially surpasses image compression frameworks, that utilized deblocking or denoising post- processing techniques, classified utilizing Peak Signal to Noise Ratio (PSNR) and Structural Similarity Index Measures (SSIM) with a mean PSNR, SSIM and Compression Ratio of 38.45, 0.9602 and 1.75x respectively for the 50 test images, thus obtaining state-of-art performance for Quality Factor (QF)=5.

Improved Tucker decomposition algorithm for noise suppression of 3D GPR data in road detection

AbstractThe echo data of ground‐penetrating radar (GPR) have a low signal‐to‐noise ratio. Denoising and interference suppression are important for improving the accuracy of underground target recognition and detection. In this paper, a new method of noise analysis and suppression of 3D GPR is proposed, transforming the problem of noise reduction into an optimization problem regarding a third‐order tensor. This method is improved with the following features; a bidimensional empirical mode decomposition (BEMD) algorithm is employed to decompose the 3D GPR noise. The main source of the noise is determined by computing the standard deviation of each component decomposed. For the shortcoming of the existing GPR denoising methods that reduce the dimension of 3D GPR data, the proposed approach can denoise 3D GPR data directly to avoid the loss of data caused by reducing the dimension. This preserves the desired signal and extracts noise through the Tucker decomposition of 3D GPR data. An improved high‐order orthogonal iteration algorithm is utilized to optimize the decomposition. The peak signal‐to‐noise ratio (PSNR) of the signal for each survey line is calculated to evaluate the effectiveness of noise reduction. Simulations and real data sets are provided to compare the performance of algorithms. The results show that the mean PSNR after noise suppression with our method is 8.915 dB and 16.458 dB higher than wavelet transform and singular value decomposition algorithms, respectively. This demonstrates that the proposed approach can better suppress 3D GPR noise and provides technical support for improving 3D GPR data quality and road detection accuracy.

Hyperspectral Remote Sensing Image Synthesis Based on Implicit Neural Spectral Mixing Models

Hyperspectral image (HSI) synthesis, as an emerging research topic, is of great value in overcoming sensor limitations and achieving low-cost acquisition of high-resolution remote sensing HSIs. However, the linear spectral mixing model used in recent studies oversimplifies the real-world hyperspectral imaging process, making it difficult to effectively model the imaging noise and multiple reflections of the object spectrum. As a prerequisite for hyperspectral data synthesis, accurate modeling of nonlinear spectral mixtures has long been a challenge. Considering the above difficulties, we propose a novel method for modeling nonlinear spectral mixtures based on implicit neural representations (INRs) in this article. The proposed method learns from INR and adaptively implements different mixture models for each pixel according to their spectral signature and surrounding environment. Based on the above neural mixing model, we also propose a new method for HSI synthesis. Given an RGB image as input, our method can generate an accurate and physically meaningful HSI. As a set of by-products, our method can also generate subpixel-level spectral abundance as well as the solar atmosphere signature. The whole framework is trained end-to-end in a self-supervised manner. We constructed a new dataset for HSI synthesis based on a wide range of Airborne Visible Infrared Imaging Spectrometer (AVIRIS) data. Our method achieves a mean peak signal-to-noise ratio (MPSNR) of 52.36 dB and outperforms other state-of-the-art hyperspectral synthesis methods. Finally, our method shows great benefits to downstream data-driven applications. With the HSIs and abundance directly generated from low-cost RGB images, the proposed method improves the accuracy of HSI classification tasks by a large margin, particularly for those with limited training samples.

Learning low-dose CT degradation from unpaired data with flow-based model.

There has been growing interest in low-dose computed tomography (LDCT) for reducing the X-ray radiation to patients. However, LDCT always suffers from complex noise in reconstructed images. Although deep learning-based methods have shown their strong performance in LDCT denoising, most of them require a large number of paired training data of normal-dose CT (NDCT) images and LDCT images, which are hard to acquire in the clinic. Lack of paired training data significantly undermines the practicability of supervised deep learning-based methods. To alleviate this problem, unsupervised or weakly supervised deep learning-based methods arerequired. We aimed to propose a method that achieves LDCT denoising without training pairs. Specifically, we first trained a neural network in a weakly supervised manner to simulate LDCT images from NDCT images. Then, simulated training pairs could be used for supervised deep denoisingnetworks. We proposed a weakly supervised method to learn the degradation of LDCT from unpaired LDCT and NDCT images. Concretely, LDCT and normal-dose images were fed into one shared flow-based model and projected to the latent space. Then, the degradation between low-dose and normal-dose images was modeled in the latent space. Finally, the model was trained by minimizing the negative log-likelihood loss with no requirement of paired training data. After training, an NDCT image can be input to the trained flow-based model to generate the corresponding LDCT image. The simulated image pairs of NDCT and LDCT can be further used to train supervised denoising neural networks fortest. Our method achieved much better performance on LDCT image simulation compared with the most widely used image-to-image translation method, CycleGAN, according to the radial noise power spectrum. The simulated image pairs could be used for any supervised LDCT denoising neural networks. We validated the effectiveness of our generated image pairs on a classic convolutional neural network, REDCNN, and a novel transformer-based model, TransCT. Our method achieved mean peak signal-to-noise ratio (PSNR) of 24.43dB, mean structural similarity (SSIM) of 0.785 on an abdomen CT dataset, mean PSNR of 33.88dB, mean SSIM of 0.797 on a chest CT dataset, which outperformed several traditional CT denoising methods, the same network trained by CycleGAN-generated data, and a novel transfer learning method. Besides, our method was on par with the supervised networks in terms of visualeffects. We proposed a flow-based method to learn LDCT degradation from only unpaired training data. It achieved impressive performance on LDCT synthesis. Next, we could train neural networks with the generated paired data for LDCT denoising. The denoising results are better than traditional and weakly supervised methods, comparable to supervised deep learningmethods.

Deformable CT image registration via a dual feasible neural network.

A quality assurance (QA) CT scans are usually acquired during cancer radiotherapy to assess for any anatomical changes, which may cause an unacceptable dose deviation and therefore warrant a replan. Accurate and rapid deformable image registration (DIR) is needed to support contour propagation from the planning CT (pCT) to the QA CT to facilitate dose volume histogram (DVH) review. Further, the generated deformation maps are used to track the anatomical variations throughout the treatment course and calculate the corresponding accumulated dose from one or more treatment plans. In this study, we aim to develop a deep learning (DL)-based method for automatic deformable registration to align the pCT and the QA CT. Our proposed method, named dual-feasible framework, was implemented by a mutual network that functions as both a forward module and a backward module. The mutual network was trained to predict two deformation vector fields (DVFs) simultaneously, which were then used to register the pCT and QA CT in both directions. A novel dual feasible loss was proposed to train the mutual network. The dual-feasible framework was able to provide additional DVF regularization during network training, which preserves the topology and reduces folding problems. We conducted experiments on 65 head-and-neck cancer patients (228 CTs in total), each with 1 pCT and 2-6 QA CTs. For evaluations, we calculated the mean absolute error (MAE), peak-signal-to-noise ratio (PSNR), structural similarity index (SSIM), target registration error (TRE) between the deformed and target images and the Jacobian determinant of the predicted DVFs. Within the body contour, the mean MAE, PSNR, SSIM, and TRE are 122.7 HU, 21.8 dB, 0.62 and 4.1 mm before registration and are 40.6 HU, 30.8 dB, 0.94, and 2.0 mm after registration using the proposed method. These results demonstrate the feasibility and efficacy of our proposed method for pCT and QA CT DIR. In summary, we proposed a DL-based method for automatic DIR to match the pCT to the QA CT. Such DIR method would not only benefit current workflow of evaluating DVHs on QA CTs but may also facilitate studies of treatment response assessment and radiomics that depend heavily on the accurate localization of tissues across longitudinal images.