A cardiac MRI motion artifact reduction method based on edge enhancement network

Cardiac magnetic resonance imaging (MRI) usually requires a long acquisition time. The movement of the patients during MRI acquisition will produce image artifacts. Previous studies have shown that clear MR image texture edges are of great significance for pathological diagnosis. In this paper, a motion artifact reduction method for cardiac MRI based on edge enhancement network is proposed. Firstly, the four-plane normal vector adaptive fractional differential mask is applied to extract the edge features of blurred images. The four-plane normal vector method can reduce the noise information in the edge feature maps. The adaptive fractional order is selected according to the normal mean gradient and the local Gaussian curvature entropy of the images. Secondly, the extracted edge feature maps and blurred images are input into the de-artifact network. In this network, the edge fusion feature extraction network and the edge fusion transformer network are specially designed. The former combines the edge feature maps with the fuzzy feature maps to extract the edge feature information. The latter combines the edge attention network and the fuzzy attention network, which can focus on the blurred image edges. Finally, extensive experiments show that the proposed method can obtain higher peak signal-to-noise ratio and structural similarity index measure compared to state-of-art methods. The de-artifact images have clear texture edges.

Edge Enhancement Optimization in Flexible Endoscopic Images to the Perception of Ear, Nose and Throat Professionals

OBJECTIVES

Digital endoscopes are connected to a video processor that applies various operations to process the image. One of those operations is edge enhancement that sharpens the image. The purpose of this study was to (1) quantify the level of edge enhancement, (2) measure the effect on sharpness and image noise, and (3) study the influence of edge enhancement on image quality perceived by ENT professionals.

METHODS

Three digital flexible endoscopic systems were included. The level of edge enhancement and the influence on sharpness and noise were measured in vitro, while systematically varying the levels of edge enhancement. In vivo images were captured at identical levels of one healthy larynx. Each series of in vivo images was presented to 39 ENT professionals according to a forced pairwise comparison test, to select the image with the best image quality for diagnostic purposes. The numbers of votes were converted to a psychometric scale of just noticeable differences (JND) according to the Thurstone V model.

RESULTS

The maximum level of edge enhancement varied per endoscopic system and ranged from 0.8 to 1.2. Edge enhancement increased sharpness and noise. Images with edge enhancement were unanimously preferred to images without edge enhancement. The quality difference with respect to zero edge enhancement reaches an optimum at levels between 0.7 and 0.9.

CONCLUSION

Edge enhancement has a major impact on sharpness, noise, and the resulting perceived image quality. We conclude that ENT professionals benefit from this video processing and should verify if their equipment is optimally configured.

LEVEL OF EVIDENCE

NA Laryngoscope, 134:842-847, 2024.

ETU-Net: edge enhancement-guided U-Net with transformer for skin lesion segmentation

Objective.Convolutional neural network (CNN)-based deep learning algorithms have been widely used in recent years for automatic skin lesion segmentation. However, the limited receptive fields of convolutional architectures hinder their ability to effectively model dependencies between different image ranges. The transformer is often employed in conjunction with CNN to extract both global and local information from images, as it excels at capturing long-range dependencies. However, this method cannot accurately segment skin lesions with blurred boundaries. To overcome this difficulty, we proposed ETU-Net.Approach.ETU-Net, a novel multi-scale architecture, combines edge enhancement, CNN, and transformer. We introduce the concept of edge detection operators into difference convolution, resulting in the design of the edge enhanced convolution block (EC block) and the local transformer block (LT block), which emphasize edge features. To capture the semantic information contained in local features, we propose the multi-scale local attention block (MLA block), which utilizes convolutions with different kernel sizes. Furthermore, to address the boundary uncertainty caused by patch division in the transformer, we introduce a novel global transformer block (GT block), which allows each patch to gather full-size feature information.Main results.Extensive experimental results on three publicly available skin datasets (PH2, ISIC-2017, and ISIC-2018) demonstrate that ETU-Net outperforms state-of-the-art hybrid methods based on CNN and Transformer in terms of segmentation performance. Moreover, ETU-Net exhibits excellent generalization ability in practical segmentation applications on dermatoscopy images contributed by the Wuxi No.2 People's Hospital.Significance.We propose ETU-Net, a novel multi-scale U-Net model guided by edge enhancement, which can address the challenges posed by complex lesion shapes and ambiguous boundaries in skin lesion segmentation tasks.

Nighttime Image Stitching Method Based on Image Decomposition Enhancement

Image stitching technology realizes alignment and fusion of a series of images with common pixel areas taken from different viewpoints of the same scene to produce a wide field of view panoramic image with natural structure. The night environment is one of the important scenes of human life, and the night image stitching technology has more urgent practical significance in the fields of security monitoring and intelligent driving at night. Due to the influence of artificial light sources at night, the brightness of the image is unevenly distributed and there are a large number of dark light areas, but often these dark light areas have rich structural information. The structural features hidden in the darkness are difficult to extract, resulting in ghosting and misalignment when stitching, which makes it difficult to meet the practical application requirements. Therefore, a nighttime image stitching method based on image decomposition enhancement is proposed to address the problem of insufficient line feature extraction in the stitching process of nighttime images. The proposed algorithm performs luminance enhancement on the structural layer, smoothes the nighttime image noise using a denoising algorithm on the texture layer, and finally complements the texture of the fused image by an edge enhancement algorithm. The experimental results show that the proposed algorithm improves the image quality in terms of information entropy, contrast, and noise suppression compared with other algorithms. Moreover, the proposed algorithm extracts the most line features from the processed nighttime images, which is more helpful for the stitching of nighttime images.

Compound feature attention network with edge enhancement for low-dose CT denoising

BACKGROUND

Low-dose CT (LDCT) images usually contain serious noise and artifacts, which weaken the readability of the image.

OBJECTIVE

To solve this problem, we propose a compound feature attention network with edge enhancement for LDCT denoising (CFAN-Net), which consists of an edge-enhanced module and a proposed compound feature attention block (CFAB).

METHODS

The edge enhancement module extracts edge details with the trainable Sobel convolution. CFAB consists of an interactive feature learning module (IFLM), a multi-scale feature fusion module (MFFM), and a joint attention module (JAB), which removes noise from LDCT images in a coarse-to-fine manner. First, in IFLM, the noise is initially removed by cross-latitude interactive judgment learning. Second, in MFFM, multi-scale and pixel attention are integrated to explore fine noise removal. Finally, in JAB, we focus on key information, extract useful features, and improve the efficiency of network learning. To construct a high-quality image, we repeat the above operation by cascading CFAB.

RESULTS

By applying CFAN-Net to process the 2016 NIH AAPM-Mayo LDCT challenge test dataset, experiments show that the peak signal-to-noise ratio value is 33.9692 and the structural similarity value is 0.9198.

CONCLUSIONS

Compared with several existing LDCT denoising algorithms, CFAN-Net effectively preserves the texture of CT images while removing noise and artifacts.

Influence of edge enhancement applied in endoscopic systems on sharpness and noise

SIGNIFICANCE

Flexible endoscopes are essential for medical internal examinations. Digital endoscopes are connected to a video processor that can apply various operations to enhance the image. One of those operations is edge enhancement, which has a major impact on the perceived image quality by medical professionals. However, the specific methods and parameters of this operation are undisclosed and the arbitrary units to express the level of edge enhancement differ per video processor.

AIM

Objectively quantify the level of edge enhancement from the recorded images alone, and measure the effect on sharpness and noise

APPROACH

Edge enhancement was studied in four types of flexible digital ear nose and throat endoscopes. Measurements were performed using slanted edges and gray patches. The level of edge enhancement was determined by subtracting the step response of an image without edge enhancement from images with selected settings of edge enhancement and measuring the resulting peak-to-peak differences. These values were then normalized by the step size. Sharpness was characterized by observing the normalized modulation transfer function (MTF) and computing the spatial frequency at 50% MTF. The noise was measured on the gray patches and computed as a weighted sum of variances from the luminance and two chrominance channels of the pixel values.

RESULTS

The measured levels were consistent with the level set via the user interface on the video processor and varied typically from 0 to 1.3. Both sharpness and noise increase with larger levels of edge enhancement with factors of 3 and 4 respectively.

CONCLUSIONS

The presented method overcomes the issue of vendors expressing the level of edge enhancement each differently in arbitrary units. This allows us to compare the effects, and we can start exploring the relationship with the subjectively perceived image quality by medical professionals to find substantiated optimal settings.

Effects of Image Postprocessing in Digital Radiography to Detect Wooden, Soft Tissue Foreign Bodies

PURPOSE

To investigate the effects of image postprocessing functions (ie, edge enhancement, noise reduction, and sharpening) that are available on digital radiography systems, including computed radiography (CR) and direct digital radiography (DDR), for detection of wooden, soft tissue foreign bodies.

METHODS

Dorsoplantar and lateral porcine foot radiographs with 4 lengths of wooden foreign bodies (no foreign bodies, 2 mm, 5 mm, and 10 mm) placed 1 mm (superficial) and 1 cm (deep) below the skin were acquired by CR and DDR systems using 10 exposure factors. Images were postprocessed to produce 960 images, including original CR, original DDR, sharpened CR, sharpened DDR, edge-enhanced DDR, and noised-reduced DDR images. Contrast-to-noise ratios (CNR) were used for objective assessments of foreign body visibility on the images. Six Australian radiologic technologists were recruited to review selected images. Australia allows radiologic technologists to provide initial comments on plain radiographs with the supervision of a radiologist. Technologists rated the visibility of foreign bodies using a 4-point scale to determine diagnostic performances of different image receptor and postprocessing types. Means, standard deviations, analyses of variance, and intraclass correlation coefficients were calculated for statistical analyses.

RESULTS

Among the CR and DDR images with and without postprocessing, the edge-enhanced DDR images had the highest overall mean CNR value (3.39, P = .003) and sensitivity (35.13%). The sensitivity of the edge-enhanced DDR images for detecting the 10 mm foreign body was 43.33%.

DISCUSSION

Edge-enhanced DDR can be considered an additional tool for suspected wooden, soft tissue foreign body diagnoses in rural areas where digital radiography is the only available imaging modality. This would allow some patients in rural areas to avoid long-distance travel to access sonography or computed tomography to detect foreign bodies, which could minimize emotional, financial, and social costs.

CONCLUSION

This study shows that the image postprocessing function of the DDR system can detect wooden, soft tissue foreign bodies. Edge enhancement, specifically, can improve wooden, soft tissue foreign body detection, especially for large foreign bodies (≥ 10 mm).

Flexible Krylov Methods for Edge Enhancement in Imaging

Many successful variational regularization methods employed to solve linear inverse problems in imaging applications (such as image deblurring, image inpainting, and computed tomography) aim at enhancing edges in the solution, and often involve non-smooth regularization terms (e.g., total variation). Such regularization methods can be treated as iteratively reweighted least squares problems (IRLS), which are usually solved by the repeated application of a Krylov projection method. This approach gives rise to an inner–outer iterative scheme where the outer iterations update the weights and the inner iterations solve a least squares problem with fixed weights. Recently, flexible or generalized Krylov solvers, which avoid inner–outer iterations by incorporating iteration-dependent weights within a single approximation subspace for the solution, have been devised to efficiently handle IRLS problems. Indeed, substantial computational savings are generally possible by avoiding the repeated application of a traditional Krylov solver. This paper aims to extend the available flexible Krylov algorithms in order to handle a variety of edge-enhancing regularization terms, with computationally convenient adaptive regularization parameter choice. In order to tackle both square and rectangular linear systems, flexible Krylov methods based on the so-called flexible Golub–Kahan decomposition are considered. Some theoretical results are presented (including a convergence proof) and numerical comparisons with other edge-enhancing solvers show that the new methods compute solutions of similar or better quality, with increased speedup.

An Advanced Noise Reduction and Edge Enhancement Algorithm

Complementary metal-oxide-semiconductor (CMOS) image sensors can cause noise in images collected or transmitted in unfavorable environments, especially low-illumination scenarios. Numerous approaches have been developed to solve the problem of image noise removal. However, producing natural and high-quality denoised images remains a crucial challenge. To meet this challenge, we introduce a novel approach for image denoising with the following three main contributions. First, we devise a deep image prior-based module that can produce a noise-reduced image as well as a contrast-enhanced denoised one from a noisy input image. Second, the produced images are passed through a proposed image fusion (IF) module based on Laplacian pyramid decomposition to combine them and prevent noise amplification and color shift. Finally, we introduce a progressive refinement (PR) module, which adopts the summed-area tables to take advantage of spatially correlated information for edge and image quality enhancement. Qualitative and quantitative evaluations demonstrate the efficiency, superiority, and robustness of our proposed method.

Non-destructive evaluation of teeth restored with different composite resins using synchrotron based micro-imaging

BACKGROUND

Application of high resolution synchrotron micro-imaging in microdefects studies of restored dental samples.

OBJECTIVE

The purpose of this study was to identify and compare the defects in restorations done by two different resin systems on teeth samples using synchrotron based micro-imaging techniques namely Phase Contrast Imaging (PCI) and micro-computed tomography (MCT). With this aim acquired image quality was also compared with routinely used RVG (Radiovisiograph).

METHODS

Crowns of human teeth samples were fractured mechanically involving only enamel and dentin, without exposure of pulp chamber and were divided into two groups depending on the restorative composite materials used. Group A samples were restored using a submicron Hybrid composite material and Group B samples were restored using a Nano-Hybrid restorative composite material. Synchrotron based PCI and MCT was performed with the aim of visualization of tooth structure, composite resin and their interface.

RESULTS

The quantitative and qualitative comparison of phase contrast and absorption contrast images along with MCT on the restored teeth samples shows comparatively large number of voids in Group A samples.

CONCLUSIONS

Quality assessment of dental restorations using synchrotron based micro-imaging suggests Nano-Hybrid resin restorations (Group B) are better than Group A.