An Image Denoising Technique Using Wavelet-Anisotropic Gaussian Filter-Based Denoising Convolutional Neural Network for CT Images

Prediction of pleural invasion in lung cancer is crucial in planning appropriate operating procedures and can be assessed using dynamic chest radiography (DCR). However, this assessment is negatively affected by rib shadows in conventional images. The purpose of this study was to develop a deep learning-based bone suppression technique for DCR in various projection directions. Twenty breathing XCAT phantoms with lung tumors and a pair of phantoms consisting only of bone structures were generated. The XCAT phantoms were virtually projected from six directions, resulting in 54000 multidirectional chest X-ray images and were used for training a pix2pix model to estimate bone images from original images. Bone suppression (BS) images were created by subtracting the bone images from the original images and then evaluated based on the peak signal to noise ratio (PSNR), structural similarity index measure (SSIM), and Fréchet Video Distance (FVD). Clinical cases were processed using the trained model as well. Furthermore, lung tumors on the original and BS images were tracked using OpenCV template matching, and the tracking accuracy was compared. The PSNR, SSIM, and FVD were 0.9966, 52.20 and 136.9, respectively. In the visual evaluation, we confirmed the effect of BS without temporal fluctuation of pixel values in both the resulting images of the XCAT phantom and real patients. Furthermore, precise tracking of the targeted tumor was achieved on the resulting BS images even in oblique directions, without any interruption from the rib shadows. These results indicate that our proposed method can effectively reduce bone shadows as well as temporal variations in the effect of bone suppression.

CT image denoising using locally adaptive shrinkage rule in tetrolet domain

Sinogram domain metal artifact correction of CT via deep learning

Wavelet is one method that can be used as a step to recognition an individual . Wavelet is used to perform an image feature extraction . In the process of image texture analysis , showed the value of the coefficients of a wavelet . The magnitude of the coefficients obtained using wavelet feature extraction is influenced by several factors . Besides affected by the type of wavelet used , is also influenced by the magnitude of the wavelet decomposition level of itself. In the wavelet is known as the wavelet energy retention , which means the number of retained energy after undergoing a process of decomposition and cutting coefficients . During the decomposition process , the calculation for texture analysis is often a constraint . In order for the current calculation lighter texture analysis , necessary to the process of cutting coefficients based on the retention factor of the wavelet coefficients . Based on these issues , created a program to analyze the influence of variations in the level of wavelet decomposition and coefficient of variation coefficient of cutting a cut on the image . The object of this final project is 30 iris image that has been converted into polar form presented . Having experienced the process of cutting coefficients , to prevent the image of the reverse transformation has a big difference to the original image , in this study was calculated Mean Square Error ( MSE), Peak Signal to Noise Ratio ( PSNR), and Euclidean distance to determine the level of similarity of image input and output images . The Highest values of Retention ​, MSE and the Euclidean distance is obtained at the level of decomposition of 1 and the lowest at the level of decomposition 6 . While the truncated coefficient and PSNR values ​​obtained at the highest level of decomposition of 6 and the lowest level of decomposition of 6 . The variation coefficient of pieces , value retention and highest PSNR obtained at koefsien piece 5 and the lowest coefficient of 50 pieces . While the coefficient value is truncated , MSE and the highest Euclidean distance is obtained at koefsien pieces 50 and the lowest coefficient of 5 pieces . Keywords: iris, texture analysis, Haar wavelet transform, MSE, PSNR, E uclidean distance

A 2-D Adaptive Trimmed Mean Autoregressive (ATMAR) model has been proposed for denoising of medical images corrupted with poisson noise. Unfiltered images are divided into smaller chunks and ATMAR model is applied on each chunk separately. In this paper, two 5x5 windows with 40% overlapping are used to predict the center pixel value of the central row. The AR coefficients are updated by sliding both windows forward with 60% shift. The same process is repeated to scan the entire image for prediction of a new denoised image. The Adaptive Trimmed Mean Filter (ATMF) eradicates the lowest and highest variations in pixel values of the ATMAR model denoised image and also average out the remaining neighborhood pixel values. Finally, power-law transformation is applied on the resultant image of the ATMAR model for contrast stretching. Image quality is judged in terms of correlation, Mean Squared Error (MSE), Structural Similarity Index Measure (SSIM) and Peak Signal to Noise Ratio (PSNR) of the image with latest denoising techniques. The proposed technique showed an efficient way to scale down poisson noise in scintigraphic images on a pixel-by-pixel basis.

Denoising low dose computed tomography (CT) images can have great advantages for the aim of minimizing the radiation risk of the patients, as it can help lower the effective dose to the patient while providing constant image quality. In recent years, deep denoising methods became a popular way to accomplish this task. Conventional deep denoising algorithms, however, cannot handle the correlation between neighboring pixels or voxels very well, because the noise structure in CT is a resultant of the global attenuation properties of the patient and because the receptive field of most denoising approaches is rathersmall. The purpose of this study is to improve existing denoising networks, by providing them additional information about the imagenoise. We here propose to generate additional noise realizations by simulation, reconstruct them, and use these noise images as additional input into existing denoising networks. This noise augmentation is intended to guide the denoising process. The additional noise realizations are not only required during training, but also during inference. The rationale behind this noise-augmented deep denoising (NADD) is that CT image noise is strongly patient-specific and it is non-local since it depends on the attenuation of X-ray beams. NADD is architecture-agnostic and can thus be used to improve any previously proposed method. We demonstrate NADD using existing denoising networks that we slightly modified in their input layer in order to take the CT image that is to be denoised plus additional noise images as input. To do so, we modified three popular denoising networks, the CNN10, the ResNet, and the WGAN-VGG and apply them to clinical cases with 90% dose reduction. In all cases tested, the denoising networks strongly benefit from the noise augmentation. Noise artifacts that are being misinterpreted by the original networks as being anatomical structures, are correctly removed by the NADD version of the same networks. The more noise images are provided, the better the performance. Providing additional simulated noise realizations helps to significantly improve the performance of CT image denoisingnetworks.

Most of the medical images are usually affected by different types of noises during acquisition, storage, and transmission. These images need to be free from noise for better diagnosis, decision, and results. Thus, denoising technique plays an important role in medical image analysis. This paper presents a method of noise removal for brain magnetic resonance imaging (MRI) image using curvelet transform thresholding technique combined with the Wiener filter and compares the result with the curvelet and wavelet-based denoising techniques. To assess the quality of denoised image, the values of peak signal-to-noise ratio (PSNR), mean square error (MSE), and structural similarity index measure (SSIM) are considered. The experimental results show that curvelet denoising method depicts better result than wavelet denoising method, but the combined method of curvelet with Wiener filtering technique is more effective than the wavelet- and curvelet-based denoising method in terms of PSNR, MSE, and SSIM.

Cetacean Optimization Based Medical Image Contrast-Enhancement Technique for Improving Disease Diagnosis in Cardiac MRI

Apparent diffusion coefficient (ADC) maps derived from diffusion weighted magnetic resonance imaging (DWI MRI) provides functional measurements about the water molecules in tissues. However, DWI is time consuming and very susceptible to image artifacts, leading to inaccurate ADC measurements. This study aims to develop a deep learning framework to synthesize ADC maps from multi-parametric MR images. We proposed the multiparametric residual vision transformer model (MPR-ViT) that leverages the long-range context of vision transformer (ViT) layers along with the precision of convolutional operators. Residual blocks throughout the network significantly increasing the representational power of the model. The MPR-ViT model was applied to T1w and T2-fluid attenuated inversion recovery images of 501 glioma cases from a publicly available dataset including preprocessed ADC maps. Selected patients were divided into training (N=400), validation (N=50), and test (N=51) sets, respectively. Using the preprocessed ADC maps as ground truth, model performance was evaluated and compared against the Vision Convolutional Transformer (VCT) and residual vision transformer (ResViT) models with the peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and mean squared error (MSE). The results are as follows using T1w + T2-FLAIR MRI as inputs: MPR-ViT-PSNR: 31.0±2.1, MSE: 0.009±0.0005, SSIM: 0.950±0.015. In addition, ablation studies showed the relative impact on performance of each input sequence. Both qualitative and quantitative results indicate that the proposed MR-ViT model performs favorably against the ground truth data. We show that high-quality ADC maps can be synthesized from structural MRI using a MPR-ViT model. Our predicted images show better conformality to the ground truth volume than ResViT and VCT predictions. These high-quality synthetic ADC maps would be particularly useful for disease diagnosis and intervention, especially when ADC maps have artifacts or are unavailable.

Industrial computed tomography (CT) crack segmentation is a key technology in industrial CT image processing. Unfortunately, the interference of artifact and noise in CT image often bring great trouble to the crack segmentation. In order to improve the segmentation accuracy of cracks in CT images, we propose to develop and test a new crack segmentation algorithm based on linear feature enhancement by analyzing the features of cracks in CT images. Firstly, the total variational model is used to denoise the input image. Next, a Frangi multiscale filter is used to extract linear structures in the image, and then the extracted linear structures are used to enhance the contrast of the image. Finally, the cracks in the image are detected and segmented by Otsu algorithm. By comparing with the manual segmentation results, the average intersection-over-union (IOU) reaches 86.10% and the average F1 score reaches 92.44%, which verifies the effectiveness and correctness of the algorithm developed in this study. Overall, experiments demonstrate that the new algorithm improves the accuracy of crack segmentation and it is effective applying to industry CT images.

Computed Tomography (CT) images play a crucial role in medical diagnosis and treatment planning. However, acquiring CT images can be difficult in certain scenarios, such as patients inability to undergo radiation exposure or unavailability of CT scanner. An alternative solution can be generating CT images from other imaging modalities. In this work, we propose a medical image translation pipeline for generating high-quality CT images from Positron Emission Tomography (PET) images using a Pix2Pix Generative Adversarial Network (GAN), which are effective in image translation tasks. However, traditional GAN loss functions often fail to capture the structural similarity between generated and target image. To alleviate this issue, we introduce a Multi-Scale Structural Similarity Index Measure (MS-SSIM) loss in addition to the GAN loss to ensure that the generated images preserve the anatomical structures and patterns present in the real CT images. Experiments on the ‘QIN-Breast’ dataset demonstrate that our proposed architecture achieves a Peak Signal-to-Noise Ratio (PSNR) of 17.70 dB and a Structural Similarity Index Measure (SSIM) of 42.51% in the region of interest.

In this study, we propose a CNN-GAN-based real-time processing technique for filtering images of underwater cables used in power systems. This addresses the excessive interference impurities that are frequently observed in images captured by remotely operated vehicles (ROVs). The process begins with the input of the original image into the convolutional neural network (CNN). Subsequently, the training outcomes, which serve as input parameters for the generative adversarial network (GAN), facilitate the filtering process. The system also calculates both the structural similarity index measure (SSIM) and peak signal-to-noise ratio (PSNR), performing model updates via backward propagation. This technique utilizes deep learning technologies to achieve rapid, real-time filtering of underwater cable images. The experimental results reveal that the loss function of the CNN reaches 0.16 with an accuracy of 97.5%, while the loss function of the adversarial GAN network approaches 0.05. Compared with traditional methods such as DDN, JORDOR, RESCAN, and PRENet, the proposed CNN-GAN algorithm exhibits superior performance, as evidenced by the higher PSNR and SSIM values. Specifically, for clear water images, the PSNR reaches 29.86 dB and the SSIM is 0.9045. For severely polluted images, the PSNR is 28.67 dB and the SSIM is 0.8965, while for unevenly illuminated images, the PSNR and SSIM values are 24.37 dB and 0.88, respectively. These enhancements significantly benefit the monitoring and maintenance of power systems.

We use images in several important areas such as military, health, security, and science. Images can be distorted during the capturing, recording, processing, and storing. Image quality metrics are the techniques to measure the quality and quality accuracy level of the images and videos. Most of the quality measurement algorithms does not affect by small distortions in the image. Magnetic Resonance Imaging (MRI), Computed Tomography (CT), and Ultrasonic Imaging (UI) are widely used in the health sector. Because of several reasons it might be artifacts in the medical images. Doctor decisions might be affected by these image artifacts. Image quality measurement is an important and challenging area to work on. There are several metrics that have been done in the literature such as mean square error, peak signal-noise ratio, gradient similarity measure, structural similarity index, and universal image quality. Patient information can be an embedded corner of the medical image as a watermark. Watermark can be considered one of the image distortions types. The most common objective evaluation algorithms are simple pixel based which are very unreliable, resulting in poor correlation with the human visual system. In this work, we proposed a new image quality metric which is a Measure of Singular Value Decomposition (M-SVD). Experimental results show that novel M-SVD algorithm gives very promising results against Peak Signal to Noise Ratio (PSNR), the Mean Square Error (MSE), Structural Similarity Index Measures (SSIM), and 3.4. Universal Image Quality (UIQ) assessments in watermarked and distorted images such as histogram equalization, JPEG compression, Gamma Correction, Gaussian Noise, Image Denoising, and Contrast Change.

Speckle noise in ultrasound images compromises image quality and hinders diagnostic accuracy. Traditional ultrasound denoising methods often struggle to preserve anatomical details while effectively reducing noise, especially under high-noise conditions. In this study, we propose an innovative approach that integrates a lightweight channel attention mechanism (LCAM) within a convolutional variational autoencoder (CVAE) framework to enhance ultrasound image denoising. The proposed approach efficiently reduces speckle noise while maintaining essential anatomical features. Comprehensive evaluations across six diverse ultrasound datasets demonstrate that the LCAM-CVAE outperforms conventional denoising techniques in both subjective image quality and objective performance metrics, including peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), standard deviation in PSNR (SD-PSNR), standard deviation in SSIM (SD-SSIM), PSNR statistical relevance tests, and computational efficiency (CE). The LCAM-CVAE approach demonstrates exceptional performance, particularly under high-noise conditions, ensuring the preservation of key anatomical structures for accurate diagnosis. These results highlight the LCAM-CVAE approach as a robust and promising solution for ultrasound image denoising, with significant clinical potential to improve diagnostic quality in noisy environments.

Recent work has shown that deep convolutional neural network is capable of solving inverse problems in computational imaging, and recovering the stress field of the loaded object from the photoelastic fringe pattern can also be regarded as an inverse problem solving process. However, the formation of the fringe pattern is affected by the geometry of the specimen and experimental configuration. When the loaded object produces complex fringe distribution, the traditional stress analysis methods still face difficulty in unwrapping. In this study, a deep convolutional neural network based on the encoder–decoder structure is proposed, which can accurately decode stress distribution information from complex photoelastic fringe images generated under different experimental configurations. The proposed method is validated on a synthetic dataset, and the quality of stress distribution images generated by the network model is evaluated using mean squared error (MSE), structural similarity index measure (SSIM), peak signal-to-noise ratio (PSNR), and other evaluation indexes. The results show that the proposed stress recovery network can achieve an average performance of more than 0.99 on the SSIM.