Image Correction Research Articles

Mosaicking and Correction Method of Gaofen-3 ScanSAR Images in Coastal Areas with Subswath Overlap Range Constraints

The ScanSAR mode image obtained by the Gaofen-3 (GF-3) satellite has an imaging width of up to 130–500 km, which is of great significance in monitoring oceanography, meteorology, water conservancy, and transportation. To address the issues of subswath misalignment and the inability to correct in the processing of GF-3 ScanSAR images in coastal areas using software such as PIE, ENVI, and SNAP, a method for mosaicking and correcting GF-3 ScanSAR images with subswaths that overlap within specified range constraints is proposed. This method involves correlating the coefficients of each subswath thumbnail image in order to determine the extent of the overlap range. Given that the matching points are constrained to the overlap between subswaths, the normalized cross-correlation (NCC) matching algorithm is utilized to calculate the matching points between subswaths. Subsequently, the random sampling consistency (RANSAC) algorithm is employed to eliminate the mismatching points. Subsequently, the subswaths should be mosaicked together with the stitching translation of subswaths, based on the coordinates of the matching points. The image brightness correction coefficient is calculated based on the average grayscale value of pixels in the overlapping region. This is performed in order to correct the grayscale values of adjacent subswaths and thereby reducing the brightness difference at the junction of subswaths. The entire ScanSAR slant range image is produced. By employing the Range–Doppler model for indirect orthorectification, corrected images with geographic information are generated. The experiment utilized three coastal GF-3 ScanSAR images for mosaicking and correction, and the results were contrasted with those attained through PIE software V7.0 processing. This was conducted to substantiate the efficacy and precision of the methodology for mosaicking and correcting coastal GF-3 ScanSAR images.

Improving of computed tomography images for effective diagnosis of gunshot wounds

Background. The purpose of the work is to develop gradation correction models, methods, and test software that can be quickly applied to improve X-ray and computed tomography (CT) images in automatic mode under conditions of time constraints, as well as significant distortion of the dynamic range of density due to the presence of high-density metal objects, significant manifestation of the gloss effect. Materials and methods. To achieve this, experiments were planned and conducted to obtain CT scans of the organs of interest with metal fragments of the given types placed in them. All the fragments were photographed and measured by a group of independent experts for the possibility of further comparative analysis by classical and computer methods, evaluation of the quality of improved images by numerical and visual methods. Results. Based on experimental data, a new unified model, method and test software for gradation correction of X-ray and CT images have been developed, the use of which allows you to significantly improve the quality of images (up to 5 times in the sense of increasing contrast) in real time (most often, the processing time of one image does not exceed 1 second). The proposed model, method and software are unified in terms of file formats, automatically adjust to the density scale and process data. Conclusions. The developed model, method and software make it possible to achieve the goal of the work — to provide prompt improvement of X-ray and CT images in automatic mode in conditions of lack of time, as well as significant distortion of the dynamic range of density, significant manifestation of the gloss effect. This makes it possible to quickly and qualitatively diagnose gunshot wounds. High efficiency is confirmed by the results of numerous experiments and implementation. At the same time, thanks to a one-time adjustment by a highly qualified expert, the proposed software can be applied with high efficiency in a mass order using preset parameters.

A foundation model for enhancing magnetic resonance images and downstream segmentation, registration and diagnostic tasks.

In structural magnetic resonance (MR) imaging, motion artefacts, low resolution, imaging noise and variability in acquisition protocols frequently degrade image quality and confound downstream analyses. Here we report a foundation model for the motion correction, resolution enhancement, denoising and harmonization of MR images. Specifically, we trained a tissue-classification neural network to predict tissue labels, which are then leveraged by a 'tissue-aware' enhancement network to generate high-quality MR images. We validated the model's effectiveness on a large and diverse dataset comprising 2,448 deliberately corrupted images and 10,963 images spanning a wide age range (from foetuses to elderly individuals) acquired using a variety of clinical scanners across 19 public datasets. The model consistently outperformed state-of-the-art algorithms in improving the quality of MR images, handling pathological brains with multiple sclerosis or gliomas, generating 7-T-like images from 3 T scans and harmonizing images acquired from different scanners. The high-quality, high-resolution and harmonized images generated by the model can be used to enhance the performance of models for tissue segmentation, registration, diagnosis and other downstream tasks.

Fisheye image rectification and restoration based on Swin Transformer

Fisheye image rectification and restoration based on Swin Transformer

Ultrafast adaptive optics for imaging the living human eye

Adaptive optics (AO) is a powerful method for correcting dynamic aberrations in numerous applications. When applied to the eye, it enables cellular-resolution retinal imaging and enhanced visual performance and stimulation. Most ophthalmic AO systems correct dynamic aberrations up to 1−2 Hz, the commonly-known cutoff frequency for correcting ocular aberrations. However, this frequency may be grossly underestimated for more clinically relevant scenarios where the medical impact of AO will be greatest. Unfortunately, little is known about the aberration dynamics in these scenarios. A major bottleneck has been the lack of sufficiently fast AO systems to measure and correct them. We develop an ultrafast ophthalmic AO system that increases AO bandwidth by ~30× and improves aberration power rejection magnitude by 500×. We demonstrate that this much faster ophthalmic AO is possible without sacrificing other system performances. We find that the discontinuous-exposure AO-control scheme runs 32% slower yet achieves 53% larger AO bandwidth than the commonly used continuous-exposure scheme. Using the ultrafast system, we characterize ocular aberration dynamics in six clinically-relevant scenarios and find their power spectra to be 10−100× larger than normal. We show that ultrafast AO substantially improves aberration correction and retinal imaging performance in these scenarios compared with conventional AO.

A fisheye image correction method based on deep learning

Purpose Fisheye camera is a wide-angle camera with a large field of view, which can obtain more information than conventional cameras, but its own disadvantage of large distortion can lead to shape distortion of objects in the captured image. To correct lens distortion, most scholars use manual calibration methods. The traditional manual calibration method relies on complex data computation and specialized mathematical knowledge, but the method is complex and not universal. Considering the nonlinear features of neural networks can be used to fit the nonlinear distortion of distorted images, this paper aims to correct the distortion of a fisheye image based on convolutional neural networks. Design/methodology/approach By generating fisheye distortion images using readily available cityscape road data sets, this paper designs an effective correction model by taking advantage of the fact that the relationship between the pixel coordinates is basically stable after uniform distortion. In our training process, the corresponding distortion is firstly synthesized using the original image, the loss function is constructed using the geometric means of the Hough transform, the whole model is then trained with the help of the loss of the linear slope, and finally the predicted parameters are used to correct the fisheye image, which realizes the overall end-to-end framework. Findings Experimental results show that the method proposed in this paper outperforms similar methods in terms of correction performance. Originality/value This paper proposed a fisheye distortion correction algorithm based on convolutional neural network, which uses distortion-free images based on a generalized fisheye imaging model and maps to generate a fisheye distortion picture data set. It also builds a loss function training model based on line reconstruction error loss of Hough transforms.

Residual Pix2Pix networks: streamlining PET/CT imaging process by eliminating CT energy conversion.

Objective
Attenuation correction of PET data is commonly conducted through the utilization of a secondary imaging technique to produce attenuation maps. The customary approach to attenuation correction, which entails the employment of CT images, necessitates energy conversion. However, the present study introduces a novel deep learning-based method that obviates the requirement for CT images and energy conversion.
Methods
This study employs a residual Pix2Pix network to generate attenuation-corrected PET images using the 4033 2D PET images of 37 healthy adult brains for train and test. The model, implemented in TensorFlow and Keras, was evaluated by comparing image similarity, intensity correlation, and distribution against CT-AC images using metrics such as PSNR and SSIM for image similarity, while a 2D histogram plotted pixel intensities. Differences in standardized uptake values (SUV) demonstrated the model's efficiency compared to the CTAC method.
Results
The residual Pix2Pix demonstrated strong agreement with the CT-based attenuation correction, the proposed network yielding MAE, MSE, PSNR, and MS-SSIM values of 3×10-3, 2×10-4, 38.859, and 0.99, respectively. The residual Pix2Pix model's results showed a negligible mean SUV difference of 8×10-4(P-value = 0.10), indicating its accuracy in PET image correction. The residual Pix2Pix model exhibits high precision with a strong correlation coefficient of R2 = 0.99 to CT-based methods. The findings indicate that this approach surpasses the conventional method in terms of precision and efficacy.
Conclusions
The proposed residual Pix2Pix framework enables accurate and feasible attenuation correction of brain F-FDG PET without CT. However, clinical trials are required to evaluate its clinical performance. The PET images reconstructed by the framework have low errors compared to the accepted test reliability of PET/CT, indicating high quantitative similarity.&#xD.

Management of late postoperative capsular bag distension syndrome - two year case series.

Late capsular bag distension syndrome (CBS) is a rare complication of the ^lcataract surgery. The aim is to present 9 cases with delayed presentation and describe their successful management with surgical approach. A two-year retrospective review of 9 cases was undertaken. Anterior segment optical coherence tomography (AS-OCT) was used to confirm this diagnosis. Aspiration of the milky fluid with 26 gauge needle followed by capsular bag lavage was performed and aspirated fluid was examined. Patients showed signs of late CBS 6,56 ± 1,94 years after uncomplicated phacoemulsification with intraocular lens (IOL) implantation into the capsular bag. All 9 patients presented with a turbid fluid collection within the distended capsular bag. AS-OCT showed a hyper-reflective material in the space between the IOL and distended posterior capsule. Awareness of the manifestations of CBS and choice of the correct imaging modality may lead to regular diagnosis and successful treatment. Management with aspiration of the milky fluid and lavage of the capsular bag is technically safe and effective procedure. It has the advantage of microbial testing of the fluid. AS-OCT is useful tool to differentiate this condition clearly from IOL opacification and posterior capsule opacification.

Development and Evaluation of a Deep Learning Model to Reduce Exomass-Related Metal Artefacts in Cone-Beam Computed Tomography of the Jaws.

To develop and evaluate a deep learning (DL) model to reduce metal artefacts originating from the exomass in cone-beam computed tomography (CBCT) of the jaws. Five porcine mandibles, each featuring six tubes filled with a radiopaque solution, were scanned using four CBCT units before and after the incremental insertion of up to three titanium, titanium-zirconium, and zirconia dental implants in the exomass of a small field of view. A conditional denoising diffusion probabilistic model, using DL techniques, was employed to correct images from exomass-related metal artefacts across the CBCT units and implant scenarios. Three examiners independently scored the image quality of all datasets, including those without an implant (ground truth), with implants in the exomass (original), and DL-generated ones. Quantitative analysis compared contrast-to-noise ratio (CNR) to validate artefact reduction using repeated measures analysis of variance in a factorial design followed by Tukey test (α = 0.05). The visualisation of the hard tissues and overall image quality was reduced in the original and increased in the DL-generated images. The score variation observed in the original images was not observed in the DL-generated images, which generally scored higher than the original images. DL-generated images revealed significantly greater CNR than both the ground truth and their corresponding original images, regardless of the material and quantity of dental implants and the CBCT unit (p < 0.05). Original images revealed significantly lower CNR than the ground truth (p < 0.05). The developed DL model demonstrated promising performance in correcting exomass-related metal artefacts in CBCT of the jaws.

Noise-aware dynamic image denoising and positron range correction for Rubidium-82 cardiac PET imaging via self-supervision

Rubidium-82 (82Rb) is a radioactive isotope widely used for cardiac PET imaging. Despite numerous benefits of 82Rb, there are several factors that limits its image quality and quantitative accuracy. First, the short half-life of 82Rb results in noisy dynamic frames. Low signal-to-noise ratio would result in inaccurate and biased image quantification. Noisy dynamic frames also lead to highly noisy parametric images. The noise levels also vary substantially in different dynamic frames due to radiotracer decay and short half-life. Existing denoising methods are not applicable for this task due to the lack of paired training inputs/labels and inability to generalize across varying noise levels. Second, 82Rb emits high-energy positrons. Compared with other tracers such as 18F, 82Rb travels a longer distance before annihilation, which negatively affect image spatial resolution. Here, the goal of this study is to propose a self-supervised method for simultaneous (1) noise-aware dynamic image denoising and (2) positron range correction for 82Rb cardiac PET imaging. Tested on a series of PET scans from a cohort of normal volunteers, the proposed method produced images with superior visual quality. To demonstrate the improvement in image quantification, we compared image-derived input functions (IDIFs) with arterial input functions (AIFs) from continuous arterial blood samples. The IDIF derived from the proposed method led to lower AUC differences, decreasing from 11.09% to 7.58% on average, compared to the original dynamic frames. The proposed method also improved the quantification of myocardium blood flow (MBF), as validated against 15O-water scans, with mean MBF differences decreased from 0.43 to 0.09, compared to the original dynamic frames. We also conducted a generalizability experiment on 37 patient scans obtained from a different country using a different scanner. The presented method enhanced defect contrast and resulted in lower regional MBF in areas with perfusion defects. Lastly, comparison with other related methods is included to show the effectiveness of the proposed method.

Deep learning image burst stacking to reconstruct high-resolution ground-based solar observations

Large aperture ground-based solar telescopes allow the solar atmosphere to be resolved in unprecedented detail. However, ground-based observations are inherently limited due to Earth's turbulent atmosphere, requiring image correction techniques. Recent post-image reconstruction techniques are based on using information from bursts of short-exposure images. Shortcomings of such approaches are the limited success, in case of stronger atmospheric seeing conditions, and computational demand. Real-time post-image reconstruction is of high importance to enabling automatic processing pipelines and accelerating scientific research. In an attempt to overcome these limitations, we provide a deep learning approach to reconstruct an original image burst into a single high-resolution high-quality image in real time. We present a novel deep learning tool for image burst reconstruction based on image stacking methods. Here, an image burst of 100 short-exposure observations is reconstructed to obtain a single high-resolution image. Our approach builds on unpaired image-to-image translation. We trained our neural network with seeing degraded image bursts and used speckle reconstructed observations as a reference. With the unpaired image translation, we aim to achieve a better generalization and increased robustness in case of increased image degradations. We demonstrate that our deep learning model has the ability to effectively reconstruct an image burst in real time with an average of 0.5 s of processing time while providing similar results to standard reconstruction methods. We evaluated the results on an independent test set consisting of high- and low-quality speckle reconstructions. Our method shows an improved robustness in terms of perceptual quality, especially when speckle reconstruction methods show artifacts. An evaluation with a varying number of images per burst demonstrates that our method makes efficient use of the combined image information and achieves the best reconstructions when provided with the full-image burst.

Content-aware motion correction for multi-shot imaging.

Content-aware motion correction for multi-shot imaging.

Fatigue Life Prediction of LF6 Aluminum Alloy Laser‐Arc Hybrid Welded Joints Based on Energy Dissipation Method

ABSTRACTTo accurately characterize the heat dissipation behavior of LF6 aluminum alloy laser arc composite welded joint under low cycle fatigue, two fatigue life prediction methods based on dissipated energy were proposed. The experimental investigation has revealed four stages in the evolution of surface temperature increment, including initial temperature increase, subsequent decline, attainment of thermal equilibrium, and sudden temperature escalation leading to failure. Based on the energy dissipation method, two models predicting lifespan of welded joints have been formulated. Model I incorporates the effects of stress amplitude and mean stress, on lifetime demonstrating a strong linear correlation particularly under high‐stress level according to experimental comparisons. Model II introduces a relationship between plastic strain amplitude and inherent dissipated energy to assess fatigue life of welded joints. Digital imaging correction technique has been utilized to quantify plastic strain amplitude. The predicted results from Model II agree well with experimental data.

A robust approach for balancing the color and light integrity of underwater images

Abstract As light travels under the deep water, it scatters and is absorbed, resulting in a loss of intensity and altered color perception—a phenomenon known as underwater light attenuation. Images captured under these low light conditions suffered from color distortions, as you go deeper, colors fade in this order: red, orange, and yellow, while green and blue become more prominent. The red channel experiences significant attenuation due to the scattering properties of light under the deep water. As a consequence, deep water images often display noticeable color casts. Researchers encounter various challenges when enhancing low-light underwater images, such as reduced contrast, detail loss, artifacts, noise, and color distortion. In this paper, we present a novel Adaptive Color and Light Correction (ACLC) method for color correction and an Intuitionistic Fuzzy Generator (IFG) for enhancing low-light underwater images. The proposed Adaptive Color and Light Correction (ACLC) method tackles color casts on individual pixels by considering the scene depth. The proposed Intuitionistic Fuzzy Generator (IFG) method balances the image contrast by computing an intuitionistic fuzzy image representation using the proposed IFG approach. Experimental results reveal that the proposed approach significantly improves the color quality and contrast of the output image. The proposed ACLC and IFG methods exceed existing underwater color correction and low-light image enhancement techniques in visual and quantitative evaluations, as evidenced by extensive experimentation on well-established underwater image datasets, such as UIEB, Ocean dark, and LSUI.

Underwater-to-air distorted image correction based on the reconstructed water surface

Abstract The lights with spatial target information received by the underwater camera are refracted at the intersection with the water surface, resulting in geometric distortion of the image. Existing methods for correcting the water-to-air distorted images typically rely on a large amount of data, such as image sequences, making the restoration using a single frame challenging. To address the issue, we propose a spatial pixel correction algorithm based on the reconstructed water surface. Firstly, we introduce a gradient water surface reconstruction algorithm based on the discrete normal vector, ensuring high accuracy in the spatial position and amplitude of the reconstructed water surface. Thus, intersections of the lights with the reconstructed water surface can be solved based on the constructed water surface. Subsequently, we propose a camera’s reverse tracking algorithm, which skillfully links the images with the spatial pixel coordinates. Finally, based on the characteristics of pixel arrangement, we propose a spatial grid algorithm to separate the spatial coordinates obtained by the reverse tracking algorithm. This part can better handle the highly concentrated and over-dispersed pixels in the spatial coordinate system. The proposed correction algorithm has better correction performance. The similarity between the restored and real images is more than 80%, and the mean square error is less than 0.01.

A deep learning method for pointer meter reading recognition in inspection robots at refrigeration stations

Abstract To improve the intelligent operation and maintenance of large public building refrigeration stations, various automatic reading methods for pointer meters used in inspection robots have been developed. However, most methods exhibit low detection accuracy for pointer meters in refrigeration stations and poor segmentation of pointers and scale lines, ultimately leading to inaccurate readings. To address the challenges posed by the complex environments of refrigeration stations, this study proposes a deep learning-based image recognition method for precise pointer meter readings. Firstly, the pointer meters in the environment are detected and located by the YOLOV8-CBAM-Wise-IoU model. Secondly, an improved Fast Semantic Segmentation Network (Fast-SCNN) is used for image segmentation of the pointers and scale lines of the pointer meters, and a perspective transformation method is employed to correct images of tilted meters. Then, the image is transformed into a rectangular image using polar coordinate transformation. Finally, the accurate reading is calculated using the distance method, based on the relative distances between the pointers and scale lines. This research conducted experimental tests using an inspection robot in the actual environment of a large public building’s refrigeration station. The results demonstrate that the proposed method for pointer meter reading recognition achieves a fiducial error within 0.41%, which can realize the inspection task of the pointer meter in refrigeration stations.

Investigation of scatter energy window width and count levels for deep learning-based attenuation map estimation in cardiac SPECT/CT imaging

Objective.Deep learning (DL) is becoming increasingly important in generating attenuation maps for accurate attenuation correction (AC) in cardiac perfusion SPECT imaging. Typically, DL models take inputs from initial reconstructed SPECT images, which are performed on the photopeak window and often also on scatter windows. While prior studies have demonstrated improvements in DL performance when scatter window images are incorporated into the DL input, the comprehensive analysis of the impact of employing different scatter windows remains unassessed. Additionally, existing research mainly focuses on applying DL to SPECT scans obtained at clinical standard count levels. This study aimed to assess utilities of DL from two aspects: (1) investigating the impact when different scatter windows were used as input to DL, and (2) evaluating the performance of DL when applied on SPECT scans acquired at a reduced count level.Approach.We utilized 1517 subjects, with 386 subjects for testing and the remaining 1131 for training and validation.Main results.The results showed that as scatter window width increased from 4% to 30%, a slight improvement was observed in DL estimated attenuation maps. The application of DL models to quarter-count (¼-count) SPECT scans, compared to full-count scans, showed a slight reduction in performance. Nonetheless, discrepancies across different scatter window configurations and between count levels were minimal, with all normalized mean square error (NMSE) values remaining within 2.1% when comparing the different DL attenuation maps to the reference CT maps. For attenuation corrected SPECT slices using DL estimated maps, NMSE values were within 0.5% when compared to CT correction.Significance.This study, leveraging an extensive clinical dataset, showed that the performance of DL seemed to be consistent across the use of varied scatter window settings. Moreover, our investigation into reduced count studies indicated that DL could provide accurate AC even at a ¼-count level.

All-optical image transmission through a dynamically perturbed multimode fiber and a ring-core fiber using diffractive deep neural networks.

In this study, we present an all-optical image reconstruction technique leveraging a diffractive deep neural network (D2NN) within a ring-core fiber (RCF) architecture. Orbital angular momentum (OAM) modes are employed to facilitate imaging transmission. We experimentally validate the efficacy of our approach for complex field diffractive image reconstruction through a multimode fiber (MMF) and RCF at a 1550 nm operating wavelength. The experimental results demonstrate the superior performance of the proposed method in mitigating RCF scattering-to-restoration transformation issues, significantly outperforming traditional MMF-based imaging correction techniques.

Automatic assessment of nailfold capillaroscopy software: a pilot study.

Capillaroscopy is a simple method of nailfold capillary imaging, used to diagnose diseases from the systemic sclerosis spectrum. However, the assessment of the capillary image is time-consuming and subjective. This makes it difficult to use for a detailed comparison of studies assessed by various physicians. This pilot study aimed to validate software used for automatic capillary counting and image classification as normal or pathological. The study was based on the assessment of 200 capillaroscopic images obtained from patients suffering from systemic sclerosis or scleroderma spectrum diseases and healthy people. Dinolite MEDL4N Pro was used to perform capillaroscopy. Each image was analysed manually and described using working software. The neural network was trained using the fast.ai library (based on PyTorch). The ResNet-34 deep residual neural network was chosen; 10-fold cross-validation with the validation and test set was performed, using the Darknet-YoloV3 state of the art neural network in a GPU-optimized (P5000 GPU) environment. For the calculation of 1 mm capillaries, an additional detection mechanism was designed. The results obtained under neural network training were compared to the results obtained in manual analysis. The sensitivity of the automatic tool relative to manual assessment in classification of correct vs. pathological images was 89.0%, specificity 89.4% for the training group, in validation 89.0% and 86.9% respectively. For the average number of capillaries in 1 mm the precision of real images detected within the region of interest was 96.48%. The pilot software for fully automatic capillaroscopic image assessment can be a useful tool for the rapid classification of a normal and altered capillaroscopy pattern. In addition, it allows one to quickly calculate the number of capillaries. In the future, the tool will be developed and will make it possible to obtain full imaging characteristics independent of the experience of the examiner.

Automatic Defects Recognition of Lap Joint of Unequal Thickness Based on X-Ray Image Processing.

It is difficult to automatically recognize defects using digital image processing methods in X-ray radiographs of lap joints made from plates of unequal thickness. The continuous change in the wall thickness of the lap joint workpiece causes very different gray levels in an X-ray background image. Furthermore, due to the shape and fixturing of the workpiece, the distribution of the weld seam in the radiograph is not vertical which results in an angle between the weld seam and the vertical direction. This makes automatic defect detection and localization difficult. In this paper, a method of X-ray image correction based on invariant moments is presented to solve the problem. In addition, a novel background removal method based on image processing is introduced to reduce the difficulty of defect recognition caused by variations in grayscale. At the same time, an automatic defect detection method combining image noise suppression, image segmentation, and mathematical morphology is adopted. The results show that the proposed method can effectively recognize the gas pores in an automatic welded lap joint of unequal thickness, making it suitable for automatic detection.