Weighted Peak Signal To Noise Ratio Research Articles

Synthesizing High b-Value Diffusion-Weighted Imaging of Gastric Cancer Using an Improved Vision Transformer CycleGAN.

Diffusion-weighted imaging (DWI), a pivotal component of multiparametric magnetic resonance imaging (mpMRI), plays a pivotal role in the detection, diagnosis, and evaluation of gastric cancer. Despite its potential, DWI is often marred by substantial anatomical distortions and sensitivity artifacts, which can hinder its practical utility. Presently, enhancing DWI's image quality necessitates reliance on cutting-edge hardware and extended scanning durations. The development of a rapid technique that optimally balances shortened acquisition time with improved image quality would have substantial clinical relevance. This study aims to construct and evaluate the unsupervised learning framework called attention dual contrast vision transformer cyclegan (ADCVCGAN) for enhancing image quality and reducing scanning time in gastric DWI. The ADCVCGAN framework, proposed in this study, employs high b-value DWI (b = 1200 s/mm2) as a reference for generating synthetic b-value DWI (s-DWI) from acquired lower b-value DWI (a-DWI, b = 800 s/mm2). Specifically, ADCVCGAN incorporates an attention mechanism CBAM module into the CycleGAN generator to enhance feature extraction from the input a-DWI in both the channel and spatial dimensions. Subsequently, a vision transformer module, based on the U-net framework, is introduced to refine detailed features, aiming to produce s-DWI with image quality comparable to that of b-DWI. Finally, images from the source domain are added as negative samples to the discriminator, encouraging the discriminator to steer the generator towards synthesizing images distant from the source domain in the latent space, with the goal of generating more realistic s-DWI. The image quality of the s-DWI is quantitatively assessed using metrics such as the peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), feature similarity index (FSIM), mean squared error (MSE), weighted peak signal-to-noise ratio (WPSNR), and weighted mean squared error (WMSE). Subjective evaluations of different DWI images were conducted using the Wilcoxon signed-rank test. The reproducibility and consistency of b-ADC and s-ADC, calculated from b-DWI and s-DWI, respectively, were assessed using the intraclass correlation coefficient (ICC). A statistical significance level of p < 0.05 was considered. The s-DWI generated by the unsupervised learning framework ADCVCGAN scored significantly higher than a-DWI in quantitative metrics such as PSNR, SSIM, FSIM, MSE, WPSNR, and WMSE, with statistical significance (p < 0.001). This performance is comparable to the optimal level achieved by the latest synthetic algorithms. Subjective scores for lesion visibility, image anatomical details, image distortion, and overall image quality were significantly higher for s-DWI and b-DWI compared to a-DWI (p < 0.001). At the same time, there was no significant difference between the scores of s-DWI and b-DWI (p > 0.05). The consistency of b-ADC and s-ADC readings was comparable among different readers (ICC: b-ADC 0.87-0.90; s-ADC 0.88-0.89, respectively). The repeatability of b-ADC and s-ADC readings by the same reader was also comparable (Reader1 ICC: b-ADC 0.85-0.86, s-ADC 0.85-0.93; Reader2 ICC: b-ADC 0.86-0.87, s-ADC 0.89-0.92, respectively). ADCVCGAN shows excellent promise in generating gastric cancer DWI images. It effectively reduces scanning time, improves image quality, and ensures the authenticity of s-DWI images and their s-ADC values, thus providing a basis for assisting clinical decision making.

Sinogram domain metal artifact correction of CT via deep learning

PurposeMetal artifacts can significantly decrease the quality of computed tomography (CT) images. This occurs as X-rays penetrate implanted metals, causing severe attenuation and resulting in metal artifacts in the CT images. This degradation in image quality can hinder subsequent clinical diagnosis and treatment planning. Beam hardening artifacts are often manifested as severe strip artifacts in the image domain, affecting the overall quality of the reconstructed CT image. In the sinogram domain, metal is typically located in specific areas, and image processing in these regions can preserve image information in other areas, making the model more robust. To address this issue, we propose a region-based correction of beam hardening artifacts in the sinogram domain using deep learning. MethodsWe present a model composed of three modules: (a) a Sinogram Metal Segmentation Network (Seg-Net), (b) a Sinogram Enhancement Network (Sino-Net), and (c) a Fusion Module. The model starts by using the Attention U-Net network to segment the metal regions in the sinogram. The segmented metal regions are then interpolated to obtain a sinogram image free of metal. The Sino-Net is then applied to compensate for the loss of organizational and artifact information in the metal regions. The corrected metal sinogram and the interpolated metal-free sinogram are then used to reconstruct the metal CT and metal-free CT images, respectively. Finally, the Fusion Module combines the two CT images to produce the result. ResultsOur proposed method shows strong performance in both qualitative and quantitative evaluations. The peak signal-to-noise ratio (PSNR) of the CT image before and after correction was 18.22 and 30.32, respectively. The structural similarity index measure (SSIM) improved from 0.75 to 0.99, and the weighted peak signal-to-noise ratio (WPSNR) increased from 21.69 to 35.68. ConclusionsOur proposed method demonstrates the reliability of high-accuracy correction of beam hardening artifacts.

An Intelligent Black Widow Optimization on Image Enhancement with Deep Learning Based Ovarian Tumor Diagnosis model

ABSTRACT Ovarian tumour is a commonly affecting gynaecologic malignancy which necessitates effective image processing techniques for accurate diagnosis. This article presents an intelligent IE with a deep learning-based ovarian tumour diagnosis (IEDL-OVD) model. The goal of the IEDL-OVD model is to enhance the quality of the input medical image, thereby improving the diagnostic outcomes. The proposed IEDL-OVD model includes a black widow optimisation-based IE technique. In addition, the VGG16 model is applied as a feature extractor and a stacked autoencoder (SAE) is utilised as a classification model to determine the existence of the ovarian tumour. In order to inspect the diagnostic outcome of the IEDL-OVD model, an elaborative experimentation analysis is performed and the results are examined in terms of different evaluation parameters. With 100 images, the IEDL-OVD model has obtained an increased precision rate and recall rate of 0.735 and 0.612. The black widow optimization algorithm (BWOA) on the quality IE has achieved a maximum contrast of 0.97, a contrast-to-noise ratio (CNR) of 92.74%, a weighted peak signal-to-noise ratio (WPSNR) of 20.43 and a homogeneity of 0.94.

Simulated Annealing-Based Image Reconstruction for Patients With COVID-19 as a Model for Ultralow-Dose Computed Tomography.

The proposed algorithm of inverse problem of computed tomography (CT), using limited views, is based on stochastic techniques, namely simulated annealing (SA). The selection of an optimal cost function for SA-based image reconstruction is of prime importance. It can reduce annealing time, and also X-ray dose rate accompanying better image quality. In this paper, effectiveness of various cost functions, namely universal image quality index (UIQI), root-mean-squared error (RMSE), structural similarity index measure (SSIM), mean absolute error (MAE), relative squared error (RSE), relative absolute error (RAE), and root-mean-squared logarithmic error (RMSLE), has been critically analyzed and evaluated for ultralow-dose X-ray CT of patients with COVID-19. For sensitivity analysis of this ill-posed problem, the stochastically estimated images of lung phantom have been reconstructed. The cost function analysis in terms of computational and spatial complexity has been performed using image quality measures, namely peak signal-to-noise ratio (PSNR), Euclidean error (EuE), and weighted peak signal-to-noise ratio (WPSNR). It has been generalized for cost functions that RMSLE exhibits WPSNR of 64.33 ± 3.98 dB and 63.41 ± 2.88 dB for 8 × 8 and 16 × 16 lung phantoms, respectively, and it has been applied for actual CT-based image reconstruction of patients with COVID-19. We successfully reconstructed chest CT images of patients with COVID-19 using RMSLE with eighteen projections, a 10-fold reduction in radiation dose exposure. This approach will be suitable for accurate diagnosis of patients with COVID-19 having less immunity and sensitive to radiation dose.

Pipeline of Optimization Techniques for Multi-Level Thresholding in Medical Image Compression Using 2D Histogram

In recent times, medical scan images are crucial for accurate diagnosis by medical professionals. Due to the increasing size of the medical images, transfer and storage of images require huge bandwidth and storage space, and hence needs compression. In this paper, multilevel thresholding using 2-D histogram is proposed for compressing the images. In the proposed work, hybridization of optimization techniques viz., Genetic Algorithm (GA), Particle Swarm Optimization (PSO) and Symbiotic Organisms Search (SOS) is used to optimize the multilevel thresholding process by assuming the Renyi entropy as an objective function. Meaningful clusters are possible with optimal threshold values, which lead to better image compression. For performance evaluation, the proposed work has been examined on six Magnetic Resonance (MR) images of brain and compared with individual optimization techniques as well as with 1-D histogram. Recent study reveals that peak signal to noise ratio (PSNR) fail in measuring the visual quality of reconstructed image because of mismatch with the objective mean opinion scores (MOS). So, we incorporate weighted PSNR (WPSNR) and visual PSNR (VPSNR) as performance measuring parameters of the proposed method. Experimental results reveal that hGAPSO-SOS method can be accurately and efficiently used in problem of multilevel thresholding for image compression.

Geometric Regularized Hopfield Neural Network for Medical Image Enhancement.

One of the major shortcomings of Hopfield neural network (HNN) is that the network may not always converge to a fixed point. HNN, predominantly, is limited to local optimization during training to achieve network stability. In this paper, the convergence problem is addressed using two approaches: (a) by sequencing the activation of a continuous modified HNN (MHNN) based on the geometric correlation of features within various image hyperplanes via pixel gradient vectors and (b) by regulating geometric pixel gradient vectors. These are achieved by regularizing proposed MHNNs under cohomology, which enables them to act as an unconventional filter for pixel spectral sequences. It shifts the focus to both local and global optimizations in order to strengthen feature correlations within each image subspace. As a result, it enhances edges, information content, contrast, and resolution. The proposed algorithm was tested on fifteen different medical images, where evaluations were made based on entropy, visual information fidelity (VIF), weighted peak signal-to-noise ratio (WPSNR), contrast, and homogeneity. Our results confirmed superiority as compared to four existing benchmark enhancement methods.

An invisible DWT watermarking algorithm using noise removal with application to dermoscopic images

A new approach for the digital watermarking process is proposed to be part of the pre-processing stage of a computer-aided diagnosis system. We propose to embed a denoised image acting as the watermark image in the original host image with the final goal of improving the quality of demoscopic images for further image processing operation related to CAD. The proposed algorithm uses Discrete Wavelet Transform (DWT) corroborated with some basic properties of Human Visual System such as Contrast Sensitive Function (CSF) and Noise Visibility Function (NVF) with the goal of correlating the texture properties and noise. This approach hides the watermark (i.e. denoised version of the host image) in high-pass subbands that are focused on image features. The main concern is to evaluate the distortion produced to the host image by watermarking and an objective quality measure function, i.e. Weighted Peak Signal-to-Noise Ratio (WPSNR), is used to evaluate the existing differences between the original and watermarked images. The proposed approach is tested using the available skin lesion images from the digital image archive of the Department of Dermatology of the University Medical Center Groningen. The experiment results show the improved performance of the proposed scheme against a 3 × 3 median filtering attack in comparison with the a 5 × 5 median filtering attack.

Application of Image Registration Techniques to Medical CT and MR Images (Dept.E)

Image registration has become one of the most widely used techniques in computer vision. Its applications include optical flow, notion analysis, tracking, face detection, and biomedical image registration. In the present work, three different techniques of image registration were implemented and applied to both Computed Tomography (CT) and Magnetic Resonance (MR) images. The first technique is based on Cross Correlation (CC). The second approach depends on Control Points' Selection (CPS) from both the reference and the input images. The last technique is based on Maximization of Mutual Information (MMI) between We two images. The registrability is calculated for each image to measure its ability to provide unambiguous registration, by providing clear correlation peaks when registered with other subimage. Then, the three registration techniques were evaluated and compared using both the Weighted Peak Signal to Noise Ratio (WPSNR) and the Normalized Cross Correlation Coefficient (NCCC). The application of the selected techniques to CT and MR images has shown that registration based on MMI has given the best results and can be used efficiently for alignment of CT and MR images.

An effective robust and imperceptible blind color image watermarking using WHT

Digital image watermarking is the most widely used recognized approach to protect data against piracy. This paper proposes a new blind color image watermarking based on the Walsh Hadamard Transform (WHT). The proposed method subdivides the image into 4 × 4 non-overlapping blocks, which are then transformed using WHT. The color image watermark is embedded in the third and fourth-row WHT coefficients using the proposed technique as a slight change in those rows may not profoundly affect the visual quality of an image. Then the difference of the third and fourth row WHT coefficients of the watermarked image is obtained. The watermark information is extracted using the attained difference value. The performance evaluation of the proposed scheme outperforms in terms of embedding capacity, Peak Signal-to-Noise Ratio (PSNR), Weighted Peak Signal-to-Noise Ratio (WPSNR), Normalized cross-correlation (NC), and Structural Similarity Index (SSIM) than the conventional watermarking methods. This proposed method provides more robustness against several manipulations and lossy attacks.

Image compression using explored bat algorithm by Renyi 2-d histogram based on multilevel thresholding

The main objective of the image compression is to extract meaningful clusters from a given image. A meaningful cluster is possible with perfect threshold values, which are optimized by assuming Renyi entropy as an objective function. Due to the equal distribution of energy over the entire 1-D histogram, it is computationally complex. In order to improve the visual quality of a reconstructed image, a 2-D histogram based multilevel thresholding is proposed to maximize the Renyi entropy using explored bat algorithm. Thus procured results are compared with other optimization techniques and these are incorporated. It is the first time, incorporating a weighted peak signal to noise ratio (WPSNR) and the visual PSNR (VPSNR) in the proposed method, because of the failure in measuring the visual quality of peak signal to noise ratio (PSNR). Experimental results are examined on a standard set of images, which are observed precisely and efficiently in the multilevel thresholding problem.

Unequal Error Protection Aided Region of Interest Aware Wireless Panoramic Video

Panoramic video with its flawless immersive tele-presence is considered to be the near-future video format of choice since they carry 360 degree coverage of the designated scenes. However, the viewers may focus their specific attention on perfectly lip-synchronized video as part of the panoramic video scene, hence only have a peripheral vision of the remaining parts of a frame. Therefore, it is intuitive to allocate stronger protection to the panoramic video region of interest. As a solution, we propose Region of Interest Aware Unequal Error Protection (ROI-UEP) for wireless transmission of high-efficiency video code (HEVC) sequences. Specifically, the ROI of a panoramic frame may be deemed to be within the 120° angular range of the viewing center, which can be estimated from the viewing trajectory of a head mounted display. Then, the most appropriate unequal forward error correction (FEC) coding rates will be found for the ROI signals by minimizing the expected video distortion. Moreover, the so-called weighted peak signal-to-noise ratio (WPSNR) is proposed for evaluating the quality of the reconstructed panoramic video, where the weights of pixels are taken into account for calculating the distortion caused by the related pixels. Our simulation results show that the ROI based equal error protection (ROI-EEP) scheme substantially outperforms the EEP by a WPSNR of more than 10 dB, while the ROI-UEP scheme further improves its ROI-EEP counterpart by a WPSNR of 9.4 dB at a channel E b /N 0 of 6 dB.

An improved capacity data hiding technique based on image interpolation

Data hiding in multimedia objects such as text, images, audio and video clips is a technique that has been widely used to achieve security for applications requiring copyright protection, covert communication, and tampering detection. Data hiding can be irreversible or reversible, where the latter is used to ensure exact recovery of the media object after extracting the hidden data. Different approaches to achieve reversible data hiding have been proposed. One of the approaches is the interpolation-based data hiding which has been proposed to achieve high data hiding capacity. This paper presents a new computationally simple interpolation-based data hiding technique that increases data hiding capacity and limits the cover image distortion that is caused by the two major steps of interpolation-based techniques; the downscaling/expansion step and the data hiding step . Image distortion reduction in the downscaling/expansion step is achieved by using a new image interpolation algorithm, whereas the image distortion in the data hiding step is reduced utilizing a new adjustable data hiding algorithm, which adaptively adjusts the level of tradeoff between data hiding capacity and image quality. The performance of the proposed technique has been evaluated for data hiding capacity and image quality using three metrics: peak signal to noise ratio (PSNR), weighted PSNR (WPSNR), and structural similarity index (SSIM). The data hiding capacity achieved by the proposed technique can be as high as 1.7bpp, which is higher by 8.5 to 72% as compared to similar techniques. Moreover, for the data hiding step, the proposed algorithm achieved high quality images as reflected by values up to 54 dB for PSNR, 78 dB for WPSNR, and 0.9998 for SSIM.

An Efficient CRT based Digital Image Watermarking using Double Density Wavelet Transform

Digital Watermarking is an unpretentious and effective approach to afford copyright fortification. Watermark transparency is obligatory primarily for copyright protection. The challenge is to introduce a digital watermark that is both transparent and highly robust to common signal processing and possible attacks. The two basic requirements for an effective watermarking scheme, robustness and transparency, conflict with each other.This paper proposesa watermarking technique for digital gray scale images that is based on utilizing congruence’s in number theory and its generalizations in abstract algebra which have been developed in the context of image compression. Watermarking scheme is based on a Chinese Remainder Theorem along with Double Density Discrete Wavelet Transform framework individually which allows for the possibility of directly watermarking the Image bitstream, Watermark region selection is based on transformation level. In proposed scheme, initially, the cover image and watermark are transformed into spatial domain using Double Density Wavelet Transform and then singular values of these transformed images are combined using CRT coefficients. Our scheme is shown to provide very good results both in terms of image transparency and robustness. An optimal watermark embedding method is developed to achieve minimum watermarking distortion. Experimental results are provided in terms of Peak signal to noise ratio (PSNR), Mean Squared Error (MSE), Correlation and Weighted Peak signal to noise ratio (WPSNR) to demonstrate the effectiveness of the proposed algorithm.

유방조영 영상의 대비개선을 위한 형체기반 호모몰픽필터

본 논문은 유방 조영 영상의 대비를 향상시키기 위해 새로운 호모몰픽 필터(MBHF)를 제안한다. 제안된 필터는 영상을 형체적으로 다수 분할한 후 각각의 형체 즉, 서브-밴드에 대해 그 구성요소와 이득이 차분진화를 통해 최적의 값을 갖도록 설계된다. 결과 분석을 통해 제안된 방법이 영상 대비를 향상시키는 것을 보이며 웨이블렛 기반의 호모몰픽 필터와 성능이 비교된다. 성능평가 기준으로는 인간의 시각적 인식을 고려한 WPSNR(Weighted Peak Signal to Noise Ratio)을 사용한다. In this paper, a new MBHF(Morphology-Based Homomorphic filter) is presented to enhance contrast in mammographic images. The MBH filtering is performed based on the morphological sub-bands, in which an image is morphologically decomposed. The filter is designed to have optimal gain and structuring element in each sub-band through differential evolution. Experimental results show that the proposed method improves the contrast in mammographic images such that an evaluation criterion, WPSNR(Weighted Peak Signal to Noise Ratio) which takes into account human visual system is increased compared with a wavelet-based Homomorphic filter.