Post-processed Images Research Articles

Image-Quality Assessment of Polyenergetic and Virtual Monoenergetic Reconstructions of Unenhanced CT Scans of the Head: Initial Experiences with the First Photon-Counting CT Approved for Clinical Use.

In 2021, the first clinical photon-counting CT (PCCT) was introduced. The purpose of this study is to evaluate the image quality of polyenergetic and virtual monoenergetic reconstructions in unenhanced PCCTs of the head. A total of 49 consecutive patients with unenhanced PCCTs of the head were retrospectively included. The signals ± standard deviations of the gray and white matter were measured at three different locations in axial slices, and a measure of the artifacts below the cranial calvaria and in the posterior fossa between the petrous bones was also obtained. The signal-to-noise ratios (SNRs) and contrast-to-noise ratios (CNRs) were calculated for all reconstructions. In terms of the SNRs and CNRs, the polyenergetic reconstruction is superior to all virtual monoenergetic reconstructions (p < 0.001). In the MERs, the highest SNR is found in the 70 keV MER, and the highest CNR is in the 65 keV MER. In terms of artifacts below the cranial calvaria and in the posterior fossa, certain MERs are superior to polyenergetic reconstruction (p < 0.001). The PCCT provided excellent image contrast and low-noise profiles for the differentiation of the grey and white matter. Only the artifacts below the calvarium and in the posterior fossa still underperform, which is attributable to the lack of an artifact reduction algorithm in image postprocessing. It is conceivable that the usual improvements in image postprocessing, especially with regard to glaring artifacts, will lead to further improvements in image quality.

Atrial CARdiac Magnetic resonance imaging in patients with embolic stroke of unknown source without documented Atrial Fibrillation (CARM-AF): Study design and clinical protocol.

BackgroundInitiation of anticoagulation therapy in ischemic stroke patients is contingent on a clinical diagnosis of atrial fibrillation (AF). Results from previous studies suggest thromboembolic risk may predate clinical manifestations of AF. Early identification of this cohort of patients may allow early initiation of anticoagulation and reduce the risk of secondary stroke.ObjectiveThis study aims to produce a substrate-based predictive model using cardiac magnetic resonance imaging (CMR) and baseline noninvasive electrocardiographic investigations to improve the identification of patients at risk of future thromboembolism.MethodsCARM-AF is a prospective, multicenter, observational cohort study. Ninety-two patients will be recruited following an embolic stroke of unknown source (ESUS) and undergo atrial CMR followed by insertion of an implantable loop recorder (ILR) as per routine clinical care within 3 months of index stroke. Remote ILR follow-up will be used to allocate patients to a study or control group determined by the presence or absence of AF as defined by ILR monitoring.ResultsBaseline data collection, noninvasive electrocardiographic data analysis, and imaging postprocessing will be performed at the time of enrollment. Primary analysis will be performed following 12 months of continuous ILR monitoring, with interim and delayed analyses performed at 6 months and 2 and 3 years, respectively.ConclusionThe CARM-AF Study will use atrial structural and electrocardiographic metrics to identify patients with AF, or at high risk of developing AF, who may benefit from early initiation of anticoagulation.

Results of clinical application of the color contrasting method of digitalx-rays

Introduction. Color processing of X-ray images has a long history and initially was directed for improvement of analysis of medical diagnostic images. Purpose — to evaluate the results of clinical application of the method for color contrast enhancement of digital radiographs.Material and methods. The study was carried out in the X-ray department of the city Mariinsky hospital in St. Petersburg, having installed a computer program on the workstations of the radiologists for carrying out color contrasting of digital radiographs (CCDR). The CCDR program allowed the radiologist to select one of 63 trajectories in 8 colors. Choosing options for coloring, we settled on a warm, cold, full scale, as well as 4 combinations of one color from cold and warm scales with a saturation from 0 to 100%. The CCDR performed 100 digital radiographs of various anatomical areas.We analyzed a variety of colors and their percentage of saturation in terms of optimal transmission of pathological signs of anatomical areas. 27 radiologists assessed the possibilities of CCDR in X-ray diagnostics.Results. Clinical application of CCDR showed that thanks to this method, tissues of different densities were distinguished in more detail on the X-ray image, since their contours were more expressively emphasized. Pathological symptoms, indistinctly expressed on a black-and-white radiograph, were convincingly reflected in the colorized image, which increased the sensitivity and specificity of the diagnosis. Thanks to color post-processing, it was possible to optimize subtle radiological signs of structural bone changes, traumatic injuries of the ribs, impaired pneumatization of the lungs (infiltration, hypoventilation), pneumo-, hydrothorax, and others. Of the radiologists, 77% considered it important to use CCDR in X-ray diagnostics.Conclusion. A digital radiograph, contrasted with a color of optimal saturation, has distinct advantages over a traditional blackand-white X-ray image, since it reveals hidden or subtle diagnostic information. The diagnostic efficiency of the method of color contrasting of radiographs is higher than the analysis of black-and-white images up to 13%.To increase the diagnostic capabilities of X-ray diagnostics, it is advisable to include the method of color contrasting in the package of computer post-processing of images, using at least three gamuts in the standard, the saturation of which is 25–50%.The colorized image does not replace black and white, but complements it, resolving the diagnostic doubts of the radiologist.

AI Denoising Significantly Improves Image Quality in Whole-Body Low-Dose Computed Tomography Staging.

(1) Background: To evaluate the effects of an AI-based denoising post-processing software solution in low-dose whole-body computer tomography (WBCT) stagings; (2) Methods: From 1 January 2019 to 1 January 2021, we retrospectively included biometrically matching melanoma patients with clinically indicated WBCT staging from two scanners. The scans were reconstructed using weighted filtered back-projection (wFBP) and Advanced Modeled Iterative Reconstruction strength 2 (ADMIRE 2) at 100% and simulated 50%, 40%, and 30% radiation doses. Each dataset was post-processed using a novel denoising software solution. Five blinded radiologists independently scored subjective image quality twice with 6 weeks between readings. Inter-rater agreement and intra-rater reliability were determined with an intraclass correlation coefficient (ICC). An adequately corrected mixed-effects analysis was used to compare objective and subjective image quality. Multiple linear regression measured the contribution of “Radiation Dose”, “Scanner”, “Mode”, “Rater”, and “Timepoint” to image quality. Consistent regions of interest (ROI) measured noise for objective image quality; (3) Results: With good–excellent inter-rater agreement and intra-rater reliability (Timepoint 1: ICC ≥ 0.82, 95% CI 0.74–0.88; Timepoint 2: ICC ≥ 0.86, 95% CI 0.80–0.91; Timepoint 1 vs. 2: ICC ≥ 0.84, 95% CI 0.78–0.90; all p ≤ 0.001), subjective image quality deteriorated significantly below 100% for wFBP and ADMIRE 2 but remained good–excellent for the post-processed images, regardless of input (p ≤ 0.002). In regression analysis, significant increases in subjective image quality were only observed for higher radiation doses (≥0.78, 95%CI 0.63–0.93; p < 0.001), as well as for the post-processed images (≥2.88, 95%CI 2.72–3.03, p < 0.001). All post-processed images had significantly lower image noise than their standard counterparts (p < 0.001), with no differences between the post-processed images themselves. (4) Conclusions: The investigated AI post-processing software solution produces diagnostic images as low as 30% of the initial radiation dose (3.13 ± 0.75 mSv), regardless of scanner type or reconstruction method. Therefore, it might help limit patient radiation exposure, especially in the setting of repeated whole-body staging examinations.

Developing effective thermal signal processing to improve thermographic non-destructive inspection of metallic components

ABSTRACT A broad range of defects can be formed in metallic equipment . The present study adopted active infrared thermography with optical excitation sources to detect the artificial flat-bottom holes in a steel sample. Raw thermal data always have some problems, such as noise and blurred edge. A proposed method, namely TPPT, was adopted to eliminate these problems. In addition to the developed technique, several well-known processes such as PCT were employed. The Contrast Enhancement parameter (CE) was defined to compare preprocessed images. CE data indicate that the TPPT has the best performance in improving the raw data. A post-processing procedure was also proposed to improve the segmentation results. This strategy consisted of two steps, histogram equalisation of preprocessed images and applying 2D wavelet noise-reduction. Ultimately, several segmentation methods were applied to the post-processed images. The outstanding performance of TPPT was proved one more time as the TPPT segmented images revealed the highest number of defects, almost 14 out of 20, on average. Moreover, the performance of segmentation algorithms was compared together regarding the number of detectable defects and estimation of defective regions’ area. FCM was recognised as the most appropriate segmentation algorithm for this study based on the obtained results.

MRI Brain Tumor Segmentation with Intuitionist Possibilistic Fuzzy Clustering and Morphological Operations

Digital Image Processing (DIP) is a well-developed field in the biological sciences which involves classification and detection of tumour. In medical science, automatic brain tumor diagnosis is an important phase. Brain tumor detection is performed by Computer-Aided Diagnosis (CAD) systems. The human image creation is greatly achieved by an approach namely medical imaging which is exploited for medical and research purposes. Recently Automatic brain tumor detection from MRI images has become the emerging research area of medical research. Brain tumor diagnosis mainly performed for obtaining exact location, orientation and area of abnormal tissues. Cancer and edema regions inference from brain magnetic resonance imaging (MRI) information is considered to be great challenge due to brain tumors complex structure, blurred borders, besides exterior features like noise. The noise compassion is mainly reduced along with segmentation stability by suggesting efficient hybrid clustering method merged with morphological process for brain cancer segmentation. Combined form of Median Modified Wiener filter (CMMWF) is chiefly deployed for denoising, and morphological operations which in turn eliminate nonbrain tissue, efficiently dropping technique’s sensitivity to noise. The proposed system contains the main phases such as preprocessing, brain tumor extraction and post processing. Image segmentation is greatly achieved by presenting Intuitionist Possibilistic Fuzzy Clustering (IPFC) algorithm. The algorithm’s stability is greatly enhanced by this clustering along with clustering parameters sensitivity reduction. Then, the post processing of images are done through morphological operations along with Hybrid Median filtering (HMF) for attaining exact tumors representations. Additionally, suggested algorithm is substantiated by comparing with other existing segmentation algorithms. The outcomes reveal that suggested algorithm achieves improved outcomes pertaining to accuracy, sensitivity, specificity, and recall.

Tomographic Images Generated from Measurements in Standing Trees Using Ultrasound and Postprocessed Images: Methodological Proposals for Cutting Velocity, Interpolation Algorithm and Confusion Matrix Metrics Focusing on Image Quality

Tomographic Images Generated from Measurements in Standing Trees Using Ultrasound and Postprocessed Images: Methodological Proposals for Cutting Velocity, Interpolation Algorithm and Confusion Matrix Metrics Focusing on Image Quality

DO: A Differentiable Engine for Deep Lens Design of Computational Imaging Systems

Computational imaging systems algorithmically post-process acquisition images either to reveal physical quantities of interest or to increase image quality, e.g., deblurring. Designing a computational imaging system requires co-design of optics and algorithms, and recently Deep Lens systems have been proposed in which both components are end-to-end designed using data-driven end-to-end training. However, progress on this exciting concept has so far been hampered by the lack of differentiable forward simulations for complex optical design spaces. Here, we introduce <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\mathbf{dO}$</tex-math></inline-formula> (DiffOptics) to provide derivative insights into the design pipeline to chain variable parameters and their gradients to an error metric through differential ray tracing. However, straightforward back-propagation of many millions of rays requires unaffordable device memory, and is not resolved by prior works. <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\mathbf{dO}$</tex-math></inline-formula> alleviates this issue using two customized memory-efficient techniques: differentiable ray-surface intersection and adjoint back-propagation. Broad application examples demonstrate the versatility and flexibility of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\mathbf{dO}$</tex-math></inline-formula> , including classical lens designs in asphere, double-Gauss, and freeform, reverse engineering for metrology, and joint designs of optics-network in computational imaging applications. We believe <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\mathbf{dO}$</tex-math></inline-formula> enables a radically new approach to computational imaging system designs and relevant research domains.

A multi-view deep learning approach for quality assessment in laser welding of hairpin windings based on 2D image captures

Electric traction motors must meet high requirements in terms of efficiency in driving operation as well as cost-effectiveness in manufacturing. The so-called hairpin technology yields potential for both aspects. However, a central bottleneck in hairpin stator manufacturing is the contacting process, commonly performed by laser welding, where a large number of joints must be created. Since a single defective weld can lead to a failure of the whole stator, effective methods for quality assessment are needed. Building on preliminary work, this paper proposes a novel multi-view deep learning architecture for combined processing of pre- and post-process images to detect welded joints with an insufficient cross-section.

Применение виртуальных панорам в цифровом тематическом картографировании

The article discusses the development of thematic mapping in terms of creating virtual panoramas, as an element of a modern digital thematic map. The features of mapping using virtual panoramas are described, the advantages and disadvantages of this method of displaying geospace are given. Based on the experimental work, the authors propose a general technological scheme for creating a thematic map with elements of a virtual panoramic tour. All technological stages are considered in detail: the creation of a digital cartographic basis, planning of field work, photography, image processing, for-mation of panoramic images, creation of a panoramic tour and its publication. The use of various shooting equipment (smartphone, camera with standard and fisheye lens, specialized camera for pano-ramic shooting) is analyzed in terms of the speed, quality and cost of post-processing images. Frag-ments of virtual tours created in the course of the study are shown.

Should pre-operative computer tomography with post-processed three-dimensional images become the benchmark in mitral valve surgery?

Should pre-operative computer tomography with post-processed three-dimensional images become the benchmark in mitral valve surgery?

Effect of acoustic perturbation on particle dispersion in a swirl-stabilized pulverized fuel burner: Cold-flow conditions

Inter-particle distance and particle dispersion during gasification of biomass have been found to significantly affect soot emission. Consequently, enhanced particle dispersion decreases energy losses and the risk for blockages of downstream equipment, increasing the efficiency and reliability of entrained flow reactors (EFRs). In this work, we investigated the interactions between imposed acoustic oscillations and particle dispersion under non-reacting conditions in a co-axial burner for a lab-scale EFR. A flow of air, laden with pulverized stem wood particles (Norwegian Spruce) of three different sizes (63–112 μm, 200–250 μm, and 500–600 μm), was forced axially through the burner center tube at Reynolds numbers ranged from 800 to 1700, and loading ratio of 0.7–4.2. The influences on particle dispersion from variations of the Strouhal number (0.12–0.6), the pressure amplitude at synthetic jet cavity (0.5–4.0 kPap-p), the swirl number (0–2.3), and the center jet velocity (1.9–3.9 m s−1) were investigated. Post-processed shadowgraph images revealed the influence of acoustic perturbations, which generate large structures with high particle concentration for both swirling and non-swirling conditions. Time-averaged contour maps showed a significantly higher particle dispersion, quantified as dispersion angle, for higher values of forcing amplitude and swirl numbers, with a stronger influence from the forcing amplitude, especially at lower Stokes number.

Cardiovascular magnetic resonance determinants of ventricular arrhythmic events after myocardial infarction.

To non-invasively characterize, by means of late gadolinium enhancement cardiac magnetic resonance (LGE-CMR), scar differences, and potential variables associated with ventricular tachycardia (VT) occurrence in chronic post-myocardial infarction (MI) patients. A case-control study was designed through retrospective LGE-CMR data analysis of chronic post-MI patients (i) consecutively referred for VT substrate ablation after a first VT episode (n = 66) and (ii) from a control group (n = 84) with no arrhythmia evidence. The myocardium was characterized differentiating core, border zone (BZ), and BZ channels (BZCs) using the ADAS 3D post-processing imaging platform. Clinical and scar characteristics, including a novel parameter, the BZC mass, were compared between both groups. One hundred and fifty post-MI patients were included. Four multivariable Cox proportional hazards regression models were created for total scar mass, BZ mass, core mass, and BZC mass, adjusting them by age, sex, and left ventricular ejection fraction (LVEF). A cut-off of 5.15 g of BZC mass identified the cases with 92.4% sensitivity and 86.9% specificity [area under the ROC curve (AUC) 0.93 (0.89-0.97); P < 0.001], with a significant increase in the AUC compared to other scar parameters (P < 0.001 for all pairwise comparisons). Adding BZC mass to LVEF allowed to reclassify 33.3% of the cases and 39.3% of the controls [net reclassification improvement = 0.73 (0.71-0.74)]. The mass of BZC is the strongest independent variable associated with the occurrence of sustained monomorphic ventricular tachycardia in post-MI patients after adjustment for age, sex, and LVEF. Border zone channel mass measurement could permit a more accurate VT risk stratification than LVEF in chronic post-MI patients.

NIMG-17. SYSTEMATIC REVIEW OF LITERATURE EVALUATING MACHINE LEARNING ALGORITHMS TO DEVELOP OUTCOME PREDICTION MODELS IN GLIOMA USING MOLECULAR IMAGING WITH AMINO ACID PET

Abstract PURPOSE Machine learning (ML) algorithms demonstrate accurate prediction of tumor segmentation, molecular pathology, and outcomes in gliomas using MRI and recently application of ML tools has expanded into molecular imaging with PET. We performed a systematic review to evaluate the role and applications of ML in characterization of gliomas with PET. METHODS Four databases were searched by medical school librarian and confirmed by an independent librarian: Ovid Embase, Ovid MEDLINE, Cochrane trials (CENTRAL), and Web of Science-Core Collection. The search strategy used keywords and controlled vocabulary combining the terms for: artificial intelligence, machine learning, deep learning, radiomics, magnetic resonance imaging, glioma, and related terms. All articles were reviewed by at least 2 independent reviewers at abstract screening, full text review, data extraction, and bias analysis using TRIPOD. RESULTS An initial 11,727 publications were imported to Covidence for screening. After review, 1135 studies moved to full-text review and 715 articles were included. Twelve publications included PET imaging of gliomas. All publications used single-center databases (3-73 patients) with distribution of tracers being [18F]-FDG (1), [18F]-FET (6), [11C]-MET (3), [18F]-FDOPA (1), and [18F]-AMP (1). All but 2 papers used supervised machine learning algorithms. Number of features ranged from 4-19,284. Nine papers manually extracted semiquantitative features TBRmax, TBRmean, SUV, TTP, in addition to demographics. Study outcomes included prediction of treatment response, survival, molecular subtypes, tumor grade, segmentation, and accuracy of image fusion. Accuracy ranged from 0.64-0.95 with AUC 0.43-0.9. CONCLUSION ML can be used on small datasets of PET imaging of brain tumors. While majority of the clinical scans are performed with FDG-PET, the machine learning approaches are being applied to mostly amino acid tracers. Extending ML approaches to FDG-PET, which is more common in clinical practice, is recommended. Overall, ML has potential as a useful tool for predicting patient outcomes and improving image postprocessing.

Detection of Ureteral Stones in Kidney Ureter Bladder Radiography: Usefulness of Digital Post-processing.

Kidney, Ureter, and Bladder radiography (KUB) has frequently been used in suspected urolithiasis, but its performance is known to be lower than that of Computed Tomography (CT). This study aimed to investigate the diagnostic performance of digitally KUB in the detection of ureteral stones. Thirty patients who underwent digital KUB and CT were included in this retrospective study. The original digital KUB underwent post-processing that involved noise estimation, reduction, and whitening in improving the visibility of ureteral stones. Thus, 60 digital original or post-processed KUB images were obtained and ordered randomly for blinded review. After a period, a second review was performed after unblinding stone laterality. The detection rates were evaluated at both initial and second reviews, using CT as a reference standard. The objective (size) and subjective (visibility) parameters of ureteral stones were analyzed. Fisher's exact test was used to compare the detection sensitivity between the original and post-processed KUB data set. Visibility analysis was assessed with a paired t-test. The correlation of stone size between CT and digital KUB data sets was assessed with the Pearson's correlation test. The detection rate was higher for most reviewers once stone laterality was provided and was non-significantly better for the post-processed KUB images (p > 0.05). There was no significant difference in stone size among CT and digital KUB data sets. In all reviews, visibility grade was higher in the post-processed KUB images, irrespective of whether stone laterality was provided. Digital post-processing of KUB yielded higher visibility of ureteral stones and could improve stone detection, especially when stone laterality was available. Thus, digitally post-processed KUB can be an excellent modality for detecting ureteral stones and measuring their exact size.

Iterative Metal Artifact Reduction (iMAR) of the Non-adhesive Liquid Embolic Agent Onyx in Computed Tomography

BackgroundA drawback of Onyx, one of the most used embolic agents for endovascular embolization of intracranial arteriovenous malformations (AVM), is the generation of imaging artifacts (IA) in computed tomography (CT). Since these artifacts can represent an obstacle for the detection of periprocedural bleeding, this study investigated the effect of artifact reduction by an iterative metal artifact reduction (iMAR) software in CT in a brain phantom.MethodsTwo different in vitro models with two-dimensional tube and three-dimensional AVM-like configuration were filled with Onyx 18. The models were inserted into a brain imaging phantom and images with (n = 5) and without (n = 10) an experimental hemorrhage adjacent were acquired. Afterwards, the iMAR algorithm was applied for artifact reduction. The IAs of the original and the post-processed images were graded quantitatively and qualitatively. Moreover, qualitative definition of the experimental hemorrhage was investigated.ResultsComparing the IAs of the original and the post-processed CT images, quantitative and qualitative analysis showed a lower degree of IAs in the post-processed images, i.e. quantitative analysis: 2D tube model: 23.92 ± 8.02 Hounsfield units (HU; no iMAR; mean ± standard deviation) vs. 5.93 ± 0.43 HU (with iMAR; p < 0.001); qualitative analysis: 3D AVM model: 4.93 ± 0.18 vs. 3.40 ± 0.48 (p < 0.001). Furthermore, definition of the experimental hemorrhage was better in the post-processed images of both in vitro models (2D tube model: p = 0.004; 3D AVM model: p = 0.002).ConclusionThe iMAR algorithm can significantly reduce the IAs evoked by Onyx 18 in CT. Applying iMAR could thus improve the accuracy of postprocedural CT imaging after embolization with Onyx in clinical practice.

Reproducibility of non-invasive VT substrate characterization: finding the same paths

Abstract Background Delayed enhancement gadolinium MRI is a useful technique to identify myocardial scar. The objective of this study is compare the reproducibility of the scar quantification and characterization based on cardiac MRI. Methods 10 patients with ischemic ethology underwent to 1,5T DE-MRI acquisition for myocardial scar analysis. Images were processed using a commercial software (ADAS3D-Galgo Medical) and different parameters from scar tissue (mass of the scar, core of scar and border zone expressed in grams) were analysed. Conducting channels evaluation was obtained by the number of corridors and the mass of the border zone of those corridors. To perform this analysis, 2 experienced and 1 non experienced users segmented DE-MRI acquisition in order to evaluate the inter observer variability. Bland-Altman analysis was employed to evaluate the comparison between the measurements. Results Inter observer agreement between experienced users was high (table). The mean and the standard deviation of the differences between two measurements for the scar mass was −3,9±14,66 gr. Analysing the scar tissue divided in core and border zone, the mass of these volume tissues were very similar (−3,51±4,56gr and −0,4±12,87gr respectively. Regarding conducting channels characteristics, the mean of the differences was 0±2 for the number of channels and 1,71±7,76 gr for the mass on the border zone of the corridors. Comparing the measurements between one of the experienced users and the beginner user, results were similar but significant differences were found on the mass of the core and the number of channels, with a variability of ±2 channels (table). Conclusions Left ventricular scar size and characteristics derived from late gadolinium enhanced post-processed images are highly reproducible between experienced observers. Funding Acknowledgement Type of funding sources: None. Table 1Scar analysis performed by 3 users

Dual energy CT arthrography in shoulder instability: successful iodine removal with virtual non-contrast images and accurate 3D reformats of the glenoid for assessment of bone loss

ObjectiveTo evaluate the image quality of dual energy CT (DECT) of the shoulder after arthrography and of virtual non-contrast (VNC) 3D reformats of the glenoid and to compare glenoid measurements on VNC 3D reformats and on 2D CTs.Materials and methodsDECT arthrography (80 kV/140 kV) was performed in 42 shoulders of 41 patients with instability using diluted iodinated contrast media (80 mg/ml). VNC images and VNC 3D reformats of the glenoid were calculated using image postprocessing. Dose parameters, CT values of intraarticular iodine and muscle, image contrast (iodine/muscle), and image quality (5-point scale: 1 = worst, 5 = best) were evaluated. Two independent readers assessed glenoid morphology and performed glenoid measurements on 2D and 3D images.ResultsCalculation of VNC images and VNC 3D reformats was successful in 42/42 shoulders (100%). The effective dose was mean 1.95 mSv (± 0.9 mSv). CT values of iodine and muscle were mean 1014.6 HU (± 235.8 HU) and 64.5 HU(± 8.6 HU), respectively, and image contrast was mean 950.2 HU (± 235.5 HU). Quality of cross-sectional images, VNC images, and VNC 3D reformats was rated good (median 4 (4–5), 4 (3–4), 4 (3–5), respectively). Detection of an osseous defect was equal on 2D and 3D images (13/42, P > 0.99) with no difference for measurement of the glenoid diameter with mean 28.3 mm (± 2.8 mm) vs. 28.4 mm (± 2.9 mm) (P = 0.5), width of the glenoid defect with 3.2 mm (± 2.1 mm) vs. 3.1 mm (± 2.3 mm) (P = 0.84), surface area with 638.5 mm2 (± 127 mm2) vs. 640.8 mm2 (± 129.5 mm2) (P = 0.47), and surface area of the defect with 46.6 mm2 (± 44.3 mm2) vs. 47.2 mm2 (± 48.0 mm2) (P = 0.73), respectively.ConclusionDECT shoulder arthrography is feasible and allows successful iodine removal with generation of VNC images and accurate VNC 3D reformats of the glenoid for assessment of bone loss.

Localization and Detection of Copy-Move Forgeries in Post-processed Images Using U-Net

Localization and Detection of Copy-Move Forgeries in Post-processed Images Using U-Net

Peering into lunar permanently shadowed regions with deep learning

The lunar permanently shadowed regions (PSRs) are expected to host large quantities of water-ice, which are key for sustainable exploration of the Moon and beyond. In the near future, NASA and other entities plan to send rovers and humans to characterize water-ice within PSRs. However, there exists only limited information about the small-scale geomorphology and distribution of ice within PSRs because the orbital imagery captured to date lacks sufficient resolution and/or signal. In this paper, we develop and validate a new method of post-processing LRO NAC images of PSRs. We show that our method is able to reveal previously unseen geomorphological features such as boulders and craters down to 3 meters in size, whilst not finding evidence for surface frost or near-surface ice. Our post-processed images significantly facilitate the exploration of PSRs by reducing the uncertainty of target selection and traverse/mission planning.