Comparable Image Quality Research Articles

Latent diffusion model-based MRI superresolution enhances mild cognitive impairment prognostication and Alzheimer's disease classification

IntroductionTimely diagnosis and prognostication of Alzheimer's disease (AD) and mild cognitive impairment (MCI) are pivotal for effective intervention. Artificial intelligence (AI) in neuroradiology may aid in such appropriate diagnosis and prognostication. This study aimed to evaluate the potential of novel diffusion model-based AI for enhancing AD and MCI diagnosis through superresolution (SR) of brain magnetic resonance (MR) images. Methods1.5T brain MR scans of patients with AD or MCI and healthy controls (NC) from Alzheimer's Disease Neuroimaging Initiative 1 (ADNI1) were superresolved to 3T using a novel diffusion model-based generative AI (d3T*) and a convolutional neural network-based model (c3T*). Comparisons of image quality to actual 1.5T and 3T MRI were conducted based on signal-to-noise ratio (SNR), naturalness image quality evaluator (NIQE), and Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE). Voxel-based volumetric analysis was then conducted to study whether 3T* images offered more accurate volumetry than 1.5T images. Binary and multiclass classifications of AD, MCI, and NC were conducted to evaluate whether 3T* images offered superior AD classification performance compared to actual 1.5T MRI. Moreover, CNN-based classifiers were used to predict conversion of MCI to AD, to evaluate the prognostication performance of 3T* images. The classification performances were evaluated using accuracy, sensitivity, specificity, F1 score, Matthews correlation coefficient (MCC), and area under the receiver-operating curves (AUROC). ResultsAnalysis of variance (ANOVA) detected significant differences in image quality among the 1.5T, c3T*, d3T*, and 3T groups across all metrics. Both c3T* and d3T* showed superior image quality compared to 1.5T MRI in NIQE and BRISQUE with statistical significance. While the hippocampal volumes measured in 3T* and 3T images were not significantly different, the hippocampal volume measured in 1.5T images showed significant difference. 3T*-based AD classifications showed superior performance across all performance metrics compared to 1.5T-based AD classification. Classification performance between d3T* and actual 3T was not significantly different. 3T* images offered superior accuracy in predicting the conversion of MCI to AD than 1.5T images did. ConclusionsThe diffusion model-based MRI SR enhances the resolution of brain MR images, significantly improving diagnostic and prognostic accuracy for AD and MCI. Superresolved 3T* images closely matched actual 3T MRIs in quality and volumetric accuracy, and notably improved the prediction performance of conversion from MCI to AD.

Mobile vs Fixed Fluoroscopy System for EVAR Image Quality and Radiation Doses for Patients and Professionnals: Mobile C-Arm vs Hybrid Room for EVAR

Abstract Background Allowing less invasive treatments, endovascular aortic repair (EVAR) has become the gold standard worldwide for the treatment of abdominal aortic aneurysms, leading to questions regarding staff and patients’ exposure to radiation. Widely performed in our center, EVAR was initially carried out on mobile C-arm (Cios-alpha, Siemens). Since 2022, EVAR was then performed in a hybrid room (Artis-Pheno, Siemens). Aims The aim of this study is to compare image quality and patients and professionals’ radiation exposure between both systems. Methods Image quality has been tested for fluoroscopy and fluorography mode on the moving system, with PMMA plates and copper disc. A Radcal ionization chamber was used to measure patient skin dose. Dosimetric and clinical parameters (e.i. Kerma, fluoroscopy time, BMI…) were recorded for 79 and 43 patients, respectively, on mobile C-arm and hybrid room. Staff exposure was measured with thermoluminescent detectors, on an anthropomorphic phantom, representative of the physician. Scattered radiation was created by irradiating PMMA plates. Different radiation protection gears have been tested comparable to daily clinical use. Results We showed that using the fluoroscopy mode, Cios-alpha was more irradiating for similar image quality as compared to the Artis-Pheno. Moreover, using the fluorography mode, Artis-Pheno provided a comparable dose rate but significantly better image quality. When comparing similar patient cohorts (BMI, sex), kerma was twice higher on Artis-Pheno due to fluorography, accounting for 27% of the total dose. In terms of staff exposure, the dose rate decreased by 51% and 99% in fluoroscopy, and 22% and 99% in fluorography when using Artis-Pheno compared to Cios-alpha (respectively, without any and with radiation protection gear). Conclusion Our study highlights the advantage of a fixed system (hybrid room) in term of both image quality and staff exposure compared to mobile system. However, particular attention must be paid to optimize protocols of such a machine to guarantee the best possible radiation protection for the patient.

Comparative analysis of the image quality and diagnostic performance of the zooming technique with diffusion-weighted imaging using different b-values for thyroid papillary carcinomas and benign nodules.

To compare image quality and diagnostic performance using different b-values for the zooming technique with diffusion-weighted imaging (ZOOMit-DWI) in thyroid nodules. A total of 51 benign thyroid nodules and 50 thyroid papillary carcinomas were included. ZOOMit-DWI was performed with b-values of 0, 500, 1000, 1500 and 2000 s/mm2. The sharpness was evaluated as subjective index. The signal intensity ratio (SIR), signal-to-noise ratio (SNR) and apparent diffusion coefficient (ADC) were measured as objective indices. Pairwise comparisons were performed among the different b-value groups using the Friedman test. A receiver operating characteristic curve of the ADC value was used to evaluate diagnostic performance. The DeLong test was used to compare diagnostic effectiveness among the different b-value groups. In both the papillary carcinoma group (P = 0.670) and the benign nodule group (P = 0.185), the sharpness of nodules was similar between b-values of 1000 s/mm2and 1500 s/mm2. In the papillary carcinoma group, the SIRnodule was statistically higher in DWI images with a b-value of 1500 s/mm2than in DWI images with b-values of 500 s/mm2(P = 0.004), 1000 s/mm2(P = 0.002), and 2000 s/mm2(P = 0.003). When the b-values were 1500 s/mm2(P = 0.008) and 2000 s/mm2(P = 0.009), the SIRnodule significantly differed between the papillary carcinoma group and the benign nodule group. When b = 500 s/mm2, the ADC had an AUC of 0.888. When b = 1000 s/mm2, the ADC had an AUC of 0.881. When b = 1500 s/mm2, the ADC had an AUC of 0.896. When b = 2000 s/mm2, the ADC had an AUC of 0.871. The DeLong test showed comparable diagnostic effectiveness among the different b-value groups except for between b-values of 2000 s/mm2and 1500 s/mm2, with a b-value of 2000 s/mm2showing lower effectiveness. This study suggests that 1500 s/mm2may be a suitable b-value to differentiate benign and malignant thyroid nodules in ZOOMit-DWI images, which yielded better image quality.

Accelerated Diffusion-Weighted Magnetic Resonance Imaging of the Liver at 1.5 T With Deep Learning-Based Image Reconstruction: Impact on Image Quality and Lesion Detection.

To perform image quality comparison between deep learning-based multiband diffusion-weighted sequence (DL-mb-DWI), accelerated multiband diffusion-weighted sequence (accelerated mb-DWI), and conventional multiband diffusion-weighted sequence (conventional mb-DWI) in patients undergoing clinical liver magnetic resonance imaging (MRI). Fifty consecutive patients who underwent clinical MRI of the liver at a 1.5-T scanner, between September 1, 2021, and January 31, 2022, were included in this study. Three radiologists independently reviewed images using a 5-point Likert scale for artifacts and image quality factors, in addition to assessing the presence of liver lesions and lesion conspicuity. DL-mb-DWI acquisition time was 65.0 ± 2.4 seconds, significantly (P < 0.001) shorter than conventional mb-DWI (147.5 ± 19.2 seconds) and accelerated mb-DWI (94.3 ± 1.8 seconds). DL-mb-DWI received significantly higher scores than conventional mb-DWI for conspicuity of the left lobe (P < 0.001), sharpness of intrahepatic vessel margin (P < 0.001), sharpness of the pancreatic contour (P < 0.001), in-plane motion artifact (P = 0.002), and overall image quality (P = 0.005) by reader 2. DL-mb-DWI received significantly higher scores for conspicuity of the left lobe (P = 0.006), sharpness of the pancreatic contour (P = 0.020), and in-plane motion artifact (P = 0.042) by reader 3. DL-mb-DWI received significantly higher scores for strength of fat suppression (P = 0.004) and sharpness of the pancreatic contour (P = 0.038) by reader 1. The remaining quality parameters did not reach statistical significance for reader 1. Novel diffusion-weighted MRI sequence with deep learning-based image reconstruction demonstrated significantly decreased acquisition times compared with conventional and accelerated mb-DWI sequences, while maintaining or improving image quality for routine abdominal MRI. DL-mb-DWI offers a potential alternative to conventional mb-DWI in routine clinical liver MRI.

A New Method of Plane-Wave Ultrasound Imaging Based on Reverse Time Migration.

Coherent plane-wave compounding technique enables rapid ultrasound imaging with comparable image quality to traditional B-mode imaging that relies on focused beam transmission. However, existing methods assume homogeneity in the imaged medium, neglecting the heterogeneity in sound velocities and densities present in real tissues, resulting in noise reverberation. This study introduces the Reverse Time Migration (RTM) method for ultrasound plane-wave imaging to overcome this limitation, which is combined with a method for estimating the speed of sound in layered media. Simulation results in a homogeneous background demonstrate that RTM reduces side lobes and grating lobes by approximately 30 dB, enhancing the contrast-to-noise ratio by 20% compared to conventional delay and sum (DAS) beamforming. Moreover, RTM achieves superior imaging outcomes with fewer compounding angles. The lateral resolution of the RTM with 5-9 angle compounding is able to achieve the effectiveness of the DAS method with 15-19 angle compounding, and the CNR of the RTM with 11-angle compounding is almost the same as that of the DAS with 21-angle compounding. In a heterogeneous background, experimental simulations and in vitro wire phantom experiments confirm RTM's capability to correct depth imaging, focusing reflected waves on point targets. In vitro porcine tissue experiments enable accurate imaging of layer interfaces by estimating the velocities of multiple layers containing muscle and fat. The proposed imaging procedure optimizes velocity estimation in complex media, compensates for the impact of velocity differences, provides more reliable imaging results.

Low-dose versus standard-dose normal temporal bone CT in children: a comparison study

ObjectiveTo compare the image quality of normal anatomical structures and radiation dose on low-dose (LDCT) and standard-dose (SDCT) temporal bone CT in children.MethodsThe study included 45 LDCT (80 kV and 130 mAs) and 45 SDCT (120 kV and 170 mAs) scans in children, 1–15 years of age. LDCT and SDCT scans were analyzed on H60s and H70h reconstruction kernels, respectively. Two readers assessed the image quality for 25 anatomical structures, using a 5-point scale. A score of 3 and above was considered “sufficient” and 2 and below was considered “insufficient” image quality. Image noise, contrast, age and size-specific effective doses were calculated.ResultsDespite an increase in image noise on LDCT, image quality remained sufficient for most structures owing to increased image contrast. The median effective dose on LDCT, calculated with age-specific conversion factor, decreased by 72.9% and that calculated with size-specific conversion factor decreased by 81.8% compared to the dose on SDCT.ConclusionLDCT provides comparable image quality for evaluation of temporal bone with significant reduction in radiation dose in children.

Bladder MRI with deep learning-based reconstruction: a prospective evaluation of muscle invasiveness using VI-RADS.

To investigate the influence of deep learning reconstruction (DLR) on bladder MRI, specifically examination time, image quality, and diagnostic performance of vesical imaging reporting and data system (VI-RADS) within a prospective clinical cohort. Seventy participants with bladder cancer who underwent MRI between August 2022 and February 2023 with a protocol containing standard T2-weighted imaging (T2WIS), standard diffusion-weighted imaging (DWIS), fast T2WI with DLR (T2WIDL), and fast DWI with DLR (DWIDL) were enrolled in this prospective study. Imaging quality was evaluated by measuring signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and qualitative image quality scoring. Additionally, the apparent diffusion coefficient (ADC) of bladder lesions derived from DWIS and DWIDL was measured and VI-RADS scoring was performed. Paired t-test or paired Wilcoxon signed-rank test were performed to compare image quality score, SNR, CNR, and ADC between standard sequences and fast sequences with DLR. The diagnostic performance for VI-RADS was assessed using the areaunder the receiver operating characteristiccurve(AUC). Compared to T2WIS and DWIS, T2WIDL and DWIDL reduced the acquisition time from 5:57min to 3:13min and showed significantly higher SNR, CNR, qualitative image quality score of overall image quality, image sharpness, and lesion conspicuity. There were no significant differences in ADC and AUC of VI-RADS between standard sequences and fast sequences with DLR. The application of DLR to T2WI and DWI reduced examination time and significantly improved image quality, maintaining ADC and the diagnostic performance of VI-RADS for evaluating muscle invasion in bladder cancer.

Clinical feasibility of post-contrast accelerated 3D T1-Sampling Perfection with Application-optimized Contrasts using different flip angle Evolutions (SPACE) with iterative denoising for intracranial enhancing lesions: a retrospective study.

Post-contrast T1-Sampling Perfection with Application-optimized Contrasts using different flip angle Evolutions (SPACE) is the preferred 3D T1 spin-echo sequence for evaluating brain metastases, regardless of the prolonged scan time. To evaluate the application of accelerated post-contrast T1-SPACE with iterative denoising (ID) for intracranial enhancing lesions in oncologic patients. For evaluation of intracranial lesions, 108 patients underwent standard and accelerated T1-SPACE during the same imaging session. Two neuroradiologists evaluated the overall image quality, artifacts, degree of enhancement, mean contrast-to-noise ratiolesion/parenchyma, and number of enhancing lesions for standard and accelerated T1-SPACE without ID. Although there was a significant difference in the overall image quality and mean contrast-to-noise ratiolesion/parenchyma between standard and accelerated T1-SPACE without ID and accelerated SPACE with and without ID, there was no significant difference between standard and accelerated T1-SPACE with ID. Accelerated T1-SPACE showed more artifacts than standard T1-SPACE; however, accelerated T1-SPACE with ID showed significantly fewer artifacts than accelerated T1-SPACE without ID. Accelerated T1-SPACE without ID showed a significantly lower number of enhancing lesions than standard- and accelerated T1-SPACE with ID; however, there was no significant difference between standard and accelerated T1-SPACE with ID, regardless of lesion size. Although accelerated T1-SPACE markedly decreased the scan time, it showed lower overall image quality and lesion detectability than the standard T1-SPACE. Application of ID to accelerated T1-SPACE resulted in comparable overall image quality and detection of enhancing lesions in brain parenchyma as standard T1-SPACE. Accelerated T1-SPACE with ID may be a promising replacement for standard T1-SPACE.

Comparison of 3T and 7T magnetic resonance imaging for direct visualization of finger flexor pulley rupture: an ex-vivo study

ObjectiveTo compare image quality and diagnostic performance of 3T and 7T magnetic resonance imaging (MRI) for direct depiction of finger flexor pulleys A2, A3 and A4 before and after artificial pulley rupture in an ex-vivo model using anatomic preparation as reference.Materials and Methods30 fingers from 10 human cadavers were examined at 3T and 7T before and after being subjected to iatrogenic pulley rupture. MRI protocols were comparable in duration, both lasting less than 22 min. Two experienced radiologists evaluated the MRIs. Image quality was graded according to a 4-point Likert scale. Anatomic preparation was used as gold standard.ResultsIn comparison, 7T versus 3T had a sensitivity and specificity for the detection of A2, A3 and A4 pulley lesions with 100% vs. 95%, respectively 98% vs. 100%. In the assessment of A3 pulley lesions sensitivity of 7T was superior to 3T MRI (100% vs. 83%), whereas specificity was lower (95% vs. 100%). Image quality assessed before and after iatrogenic rupture was comparable with 2.74 for 7T and 2.61 for 3T. Visualization of the A3 finger flexor pulley before rupture creation was significantly better for 7 T (p < 0.001). Interobserver variability showed substantial agreement at 3T (κ = 0.80) and almost perfect agreement at 7T (κ = 0.90).ConclusionMRI at 3T allows a comparable diagnostic performance to 7T for direct visualization and characterization of finger flexor pulleys before and after rupture, with superiority of 7T MRI in the visualization of the normal A3 pulley.

Comparison of Image Quality and Radiation Dose in Pediatric Temporal Bone CT Using Photon-Counting Detector CT and Energy-Integrating Detector CT.

Currently, there is a lack of research directly comparing photon-counting detector CT (PCD-CT) and energy-integrating detector CT (EID-CT) in pediatric temporal bone CT imaging. The purpose of this study was to compare the image quality and radiation dose of temporal bone CT scans in pediatric patients acquired with PCD-CT and EID-CT. The retrospective study included a total of 110 pediatric temporal bone CT scans (PCD-CT, n = 52; EID-CT, n = 58). Two independent readers evaluated the spatial resolution of 4 anatomic structures (tympanic membrane, incudostapedial joint, stapedial crura, and cochlear modiolus) and overall image quality by using a 4-point scale. Interreader agreement was assessed. Dose-length product for each CT was compared, and subgroup analyses were performed based on age (younger than 3 years, 3-5 years, 6-11 years, and 12 years and above). PCD-CT demonstrated statistically significantly higher scores than EID-CT for all items (tympanic membrane, 2.9 versus 2.4; incudostapedial joint, 3.6 versus 2.6; stapedial crura, 3.2 versus 2.4; cochlear modiolus, 3.4 versus 2.8; overall image quality, 3.6 versus 2.8; P < .05). Interreader agreement ranged from good to excellent (interclass correlation coefficients, 0.6-0.81). PCD-CT exhibited a 43% dose reduction compared with EID-CT, with a particularly substantial reduction of over 70% in the subgroups of children younger than 6 years. PCD temporal bone CT achieves significantly superior imaging quality at a lower radiation dose compared with EID-CT.

Second-Order Motion-Compensated Echo-Planar Cardiac Diffusion-Weighted MRI: Usefulness of Compressed Sensitivity Encoding.

Cardiac diffusion-weighted imaging (DWI) using second-order motion-compensated spin echo (M2C) can provide noninvasive in-vivo microstructural assessment, but limited by relatively low signal-to-noise ratio (SNR). Echo-planar imaging (EPI) with compressed sensitivity encoding (EPICS) could address these issues. To combine M2C DWI and EPCIS (M2C EPICS DWI), and compare image quality for M2C DWI. Prospective. Ten ex-vivo hearts, 10 healthy volunteers (females, 5 [50%]; mean ± SD of age, 25 ± 4 years), and 12 patients with diseased hearts (female, 1 [8.3%]; mean ± SD of age, 44 ± 16 years; including coronary artery heart disease, congenital heart disease, dilated cardiomyopathy, amyloidosis, and myocarditis). 3-T, M2C EPICS DWI, and M2C DWI. The apparent SNR (aSNR) and the rating scores were used to evaluate and compared image quality of all three groups. The aSNR was calculated using , and the myocardium was segmented manually. Three observers independently rated subjective image quality using a 5-point Likert scale. Bland-Altman analysis and paired t-tests. The threshold for statistical significance was set at P < 0.05. In healthy volunteers, the aSNR with a b-value of 450 s/mm2 acquired by M2C EPICS DWI was significantly higher than M2C DWI at in-plane resolutions of 3.0 × 3.0, 2.5 × 2.5, and 2.0 × 2.0 mm2. In patients with diseased hearts, the aSNR ofM2C EPICS DWI was also significantly higher than that for M2C DWI (bias of M2C EPICS-M2C = 1.999, 95% limits of agreement, 0.362 to 3.636; mean ± SD, 7.80 ± 1.37 vs. 5.80 ± 0.81). The ADC values of M2C EPICS was significantly higher than M2C DWI in in-vivo hearts. Over 80% of the images with rating scores for M2C EPICS DWI were higher than M2C DWI in in-vivo hearts. Cardiac imaging by M2C EPICS DWI may demonstrate better overall image quality and higher aSNR than M2C DWI. 2 TECHNICAL EFFICACY: Stage 1.

Deep learning denoising reconstruction enables faster T2-weighted FLAIR sequence acquisition with satisfactory image quality.

Deep learning reconstruction (DLR) technologies are the latest methods attempting to solve the enduring problem of reducing MRI acquisition times without compromising image quality. The clinical utility of this reconstruction technique is yet to be fully established. This study aims to assess whether a commercially available DLR technique applied to 2D T2-weighted FLAIR brain images allows a reduction in scan time, without compromising image quality and thus diagnostic accuracy. 47 participants (24 male, mean age 55.9 ± 18.7 SD years, range 20-89 years) underwent routine, clinically indicated brain MRI studies in March 2022, that included a standard-of-care (SOC) T2-weighted FLAIR sequence, and an accelerated acquisition that was reconstructed using the DLR denoising product. Overall image quality, lesion conspicuity, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and artefacts for each sequence, and preferred sequence on direct comparison, were subjectively assessed by two readers. There was a strong preference for SOC FLAIR sequence for overall image quality (P = 0.01) and head-to-head comparison (P < 0.001). No difference was observed for lesion conspicuity (P = 0.49), perceived SNR (P = 1.0), and perceived CNR (P = 0.84). There was no difference in motion (P = 0.57) nor Gibbs ringing (P = 0.86) artefacts. Phase ghosting (P = 0.038) and pseudolesions were significantly more frequent (P < 0.001) on DLR images. DLR algorithm allowed faster FLAIR acquisition times with comparable image quality and lesion conspicuity. However, an increased incidence and severity of phase ghosting artefact and presence of pseudolesions using this technique may result in a reduction in reading speed, efficiency, and diagnostic confidence.

Image Quality and Radiation Exposure in Abdominal Angiography: A Head-to-Head Comparison of Conventional Detector-Dose-Driven Versus Contrast-to-Noise Ratio-Driven Exposure Control at Various Source-to-Image Receptor Distances and Collimations in a Pilot Phantom and Animal Study.

This phantom and animal pilot study aimed to compare image quality and radiation exposure between detector-dose-driven exposure control (DEC) and contrast-to-noise ratio (CNR)-driven exposure control (CEC) as functions of source-to-image receptor distance (SID) and collimation. First, an iron foil simulated a guide wire in a stack of polymethyl methacrylate and aluminum plates representing patient thicknesses of 15, 25, and 35 cm. Fluoroscopic images were acquired using 5 SIDs ranging from 100 to 130 cm and 2 collimations (full field of view, collimated field of view: 6 × 6 cm). The iron foil CNRs were calculated, and radiation doses in terms of air kerma rate were obtained and assessed using a multivariate regression. Second, 5 angiographic scenarios were created in 2 anesthetized pigs. Fluoroscopic images were acquired at 2 SIDs (110 and 130 cm) and both collimations. Two blinded experienced readers compared image quality to the reference image using full field of view at an SID of 110 cm. Air kerma rate was obtained and compared using t tests. Using DEC, both CNR and air kerma rate increased significantly at longer SID and collimation below the air kerma rate limit. When using CEC, CNR was significantly less dependent of SID, collimation, and patient thickness. Air kerma rate decreased at longer SID and tighter collimation. After reaching the air kerma rate limit, CEC behaved similarly to DEC. In the animal study using DEC, image quality and air kerma rate increased with longer SID and collimation ( P < 0.005). Using CEC, image quality was not significantly different than using longer SID or tighter collimation. Air kerma rate was not significantly different at longer SID but lower using collimation ( P = 0.012). CEC maintains the image quality with varying SID and collimation stricter than DEC, does not increase the air kerma rate at longer SID and reduces it with tighter collimation. After reaching the air kerma rate limit, CEC and DEC perform similarly.

Performance of the Iterative OSEM and HYPER Algorithm for Total-body PET at SUVmax with a Low 18F-FDG Activity, a Short Acquisition Time and Small Lesions.

The primary objective of this comparative investigation was to examine the qualitative attributes of image reconstructions utilizing two distinct algorithms, namely OSEM and HYPER Iterative, in total-body 18F- FDG PET/CT under various acquisition durations and injection activities. An initial assessment was executed using a NEMA phantom to compare image quality engendered by OSEM and HYPER Iterative algorithms. Parameters such as BV, COV, and CRC were meticulously evaluated. Subsequently, a prospective cohort study was conducted on 50 patients, employing both reconstruction algorithms. The study was compartmentalized into distinct acquisition time and dosage groups. Lesions were further categorized into three size-based groups. Quantifiable metrics including SD of noise, SUVmax, SNR, and TBR were computed. Additionally, the differences in values, namely &#916;SUVmax, &#916;TBR, %&#916;SUVmax, %&#916;SD, and %&#916;SNR, between OSEM and HYPER Iterative algorithms were also calculated. The HYPER Iterative algorithm showed reduced BV and COV compared to OSEM in the phantom study, with constant acquisition time. In the clinical study, lesion SUVmax, TBR, and SNR were significantly elevated in images reconstructed using the HYPER Iterative algorithm in comparison to those generated by OSEM (p &#60; 0.001). Furthermore, an amplified increase in SUVmax was predominantly discernible in lesions with dimensions less than 10 mm. Metrics such as %&#916;SNR and %&#916;SD in HYPER Iterative exhibited improvements correlating with reduced acquisition times and dosages, wherein a more pronounced degree of enhancement was observable in both &#916;SUVmax and &#916;TBR. The HYPER Iterative algorithm significantly improves SUVmax and reduces noise level, with particular efficacy in lesions measuring ≤ 10 mm and under conditions of abbreviated acquisition times and lower dosages.

Comparative analysis of image quality and interchangeability between standard and deep learning-reconstructed T2-weighted spine MRI

Rationale and objectivesMRI reconstruction of undersampled data using a deep learning (DL) network has been recently performed as part of accelerated imaging. Herein, we compared DL-reconstructed T2-weighted image (T2-WI) to conventional T2-WI regarding image quality and degenerative lesion detection. Materials and methodsSixty-two patients underwent C-spine (n = 27) or L-spine (n = 35) MRIs, including conventional and DL-reconstructed T2-WI. Image quality was assessed with non-uniformity measurement and 4-scale grading of structural visibility. Three readers (R1, R2, R3) independently assessed the presence and types of degenerative lesions. Student t-test was used to compare non-uniformity measurements. Interprotocol and interobserver agreement of structural visibility was analyzed with Wilcoxon signed-rank test and weighted-κ values, respectively. The diagnostic equivalence of degenerative lesion detection between two protocols was assessed with interchangeability test. ResultsThe acquisition time of DL-reconstructed images was reduced to about 21–58% compared to conventional images. Non-uniformity measurement was insignificantly different between the two images (p-value = 0.17). All readers rated DL-reconstructed images as showing the same or superior structural visibility compared to conventional images. Significantly improved visibility was observed at disk margin of C-spine (R1, p < 0.001; R2, p = 0.04) and dorsal root ganglia (R1, p = 0.03; R3, p = 0.02) and facet joint (R1, p = 0.04; R2, p < 0.001; R3, p = 0.03) of L-spine. Interobserver agreements of image quality were variable in each structure. Clinical interchangeability between two protocols for degenerative lesion detection was verified showing <5% in the upper bounds of 95% confidence intervals of agreement rate differences. ConclusionsDL-reconstructed T2-WI demonstrates comparable image quality and diagnostic performance with conventional T2-WI in spine imaging, with reduced acquisition time.

Exploring the Low-Dose Limit for Focal Hepatic Lesion Detection with a Deep Learning-Based CT Reconstruction Algorithm: A Simulation Study on Patient Images.

This study aims to investigate the maximum achievable dose reduction for applying a new deep learning-based reconstruction algorithm, namely the artificial intelligence iterative reconstruction (AIIR), in computed tomography (CT) for hepatic lesion detection. A total of 40 patients with 98 clinically confirmed hepatic lesions were retrospectively included. The mean volume CT dose index was 13.66 ± 1.73 mGy in routine-dose portal venous CT examinations, where the images were originally obtained with hybrid iterative reconstruction (HIR). Low-dose simulations were performed in projection domain for 40%-, 20%-, and 10%-dose levels, followed by reconstruction using both HIR and AIIR. Two radiologists were asked to detect hepatic lesion on each set of low-dose image in separate sessions. Qualitative metrics including lesion conspicuity, diagnostic confidence, and overall image quality were evaluated using a 5-point scale. The contrast-to-noise ratio (CNR) for lesion was also calculated for quantitative assessment. The lesion CNR on AIIR at reduced doses were significantly higher than that on routine-dose HIR (all p < 0.05). Lower qualitative image quality was observed as the radiation dose reduced, while there were no significant differences between 40%-dose AIIR and routine-dose HIR images. The lesion detection rate was 100%, 98% (96/98), and 73.5% (72/98) on 40%-, 20%-, and 10%-dose AIIR, respectively, whereas it was 98% (96/98), 73.5% (72/98), and 40% (39/98) on the corresponding low-dose HIR, respectively. AIIR outperformed HIR in simulated low-dose CT examinations of the liver. The use of AIIR allows up to 60% dose reduction for lesion detection while maintaining comparable image quality to routine-dose HIR.

Image quality and metal artifact reduction in total hip arthroplasty CT: deep learning-based algorithm versus virtual monoenergetic imaging and orthopedic metal artifact reduction

BackgroundTo compare image quality, metal artifacts, and diagnostic confidence of conventional computed tomography (CT) images of unilateral total hip arthroplasty patients (THA) with deep learning-based metal artifact reduction (DL-MAR) to conventional CT and 130-keV monoenergetic images with and without orthopedic metal artifact reduction (O-MAR).MethodsConventional CT and 130-keV monoenergetic images with and without O-MAR and DL-MAR images of 28 unilateral THA patients were reconstructed. Image quality, metal artifacts, and diagnostic confidence in bone, pelvic organs, and soft tissue adjacent to the prosthesis were jointly scored by two experienced musculoskeletal radiologists. Contrast-to-noise ratios (CNR) between bladder and fat and muscle and fat were measured. Wilcoxon signed-rank tests with Holm-Bonferroni correction were used.ResultsSignificantly higher image quality, higher diagnostic confidence, and less severe metal artifacts were observed on DL-MAR and images with O-MAR compared to images without O-MAR (p < 0.001 for all comparisons). Higher image quality, higher diagnostic confidence for bone and soft tissue adjacent to the prosthesis, and less severe metal artifacts were observed on DL-MAR when compared to conventional images and 130-keV monoenergetic images with O-MAR (p ≤ 0.014). CNRs were higher for DL-MAR and images with O-MAR compared to images without O-MAR (p < 0.001). Higher CNRs were observed on DL-MAR images compared to conventional images and 130-keV monoenergetic images with O-MAR (p ≤ 0.010).ConclusionsDL-MAR showed higher image quality, diagnostic confidence, and superior metal artifact reduction compared to conventional CT images and 130-keV monoenergetic images with and without O-MAR in unilateral THA patients.Relevance statementDL-MAR resulted into improved image quality, stronger reduction of metal artifacts, and improved diagnostic confidence compared to conventional and virtual monoenergetic images with and without metal artifact reduction, bringing DL-based metal artifact reduction closer to clinical application.Key points• Metal artifacts introduced by total hip arthroplasty hamper radiologic assessment on CT.• A deep-learning algorithm (DL-MAR) was compared to dual-layer CT images with O-MAR.• DL-MAR showed best image quality and diagnostic confidence.• Highest contrast-to-noise ratios were observed on the DL-MAR images.Graphical

Comparison of Low-Dose Computed Tomography Versus Conventional-Dose Computed Tomography in the Evaluation of Distal Radius Fractures.

Distal radius fractures (DRFs) are common upper extremity fractures and often require surgical fixation when they are intraarticular. Preoperative computed tomography (CT) has emerged as a surgical planning tool to evaluate intraarticular DRFs. Although CT affords additional details, patients receive higher radiation doses than standard radiographs. We aim to develop a low-dose CT (LDCT) protocol, relative to the institutional standard-dose CT wrist for intraarticular DRFs although providing adequate detail for surgical decision-making. A single-institution prospective study was conducted on patients with intraarticular DRFs who underwent closed reduction and below-elbow splinting who otherwise would undergo wrist CT. Observations were defined as total measurements taken, with each view undergoing 44 measurements. Patients underwent 2 scans with a standard dose and a 10× dose reduction. Articular step and gap measurements were recorded in the sagittal and coronal images. A total of 11 patients were enrolled (7 women and 4 men). The mean age was 55 years (SD = 20.1). There were a total of 4 reviewers: 1 attending surgeon, 2 resident physicians, and 1 student. When comparing LDCT and conventional-dose CT (CDCT), there were no significant differences in step and gap measurements across all reviewers. This study demonstrated that LDCT provides comparable imaging quality for surgical planning as a CDCT without significant diagnostic decay in the setting of DRFs. This comes with the added benefit of a 10-fold reduction in radiation exposure. These results suggest that LDCT is an opportunity to reduce effective radiation in patients although providing beneficial preoperative imaging.

Comparison of dose length product and image quality of a biphasic whole-body polytrauma CT protocol with and without the automatic tube voltage selection.

A significant source of man-made radiation is now linked to medical devices especially X-ray imaging based ones like CT scans which expose the body to cumulative ionizing radiation and thus attendant cancer risks. The aim of this study was to determine whether using a combination of Automatic Tube Current Modulation (ATCM) and Automatic Tube Voltage Selection (ATVS) during two-phase whole-body CT (2PWBCT) examinations would reduce the radiation dose while preserving the image quality. This was a prospective, observational, single-centre study of 127 adult patients who had undergone the 2PWBCT polytraumatic protocol. All were examined on a Somatom Drive scanner (Siemens). The patients were divided into two groups: ATCM only (42 patients) and ATCM +ATVS (85 patients). Patients' arm positions during examination and the examination dose length product (DLP) values were recorded, as well the standard deviations (SD) of the density in reference areas on CT scans for the image quality assessment. The DLP values and image quality in the groups were compared using ANOVA. Mean Total DLP (in mGy*cm): ATCM only: 3337 +/-797, ATCM+ATVS: 3402 +/-830; P=0.674. No effect of arm position (P=0.586). Mean density SD values in reference areas (in HU) in ATCM only: 49 +/-45, 15 +/-6, 9 +/-2, 12 +/-4, 10 +/-3, in ATCM+ATVS: 48 +/-45, 17 +/-6, 11 +/-3, 15 +/-6, 12 +/-4. SD values was higher in ATCM+ATVS group (P<0.001). Combination of ATVS and ATCM in polytraumatic 2PWBCT leads to no significant radiation load reduction compared with ATCM only but does lead to a slight degradation of image quality. The radiation load is significantly reduced if the patient has their arms behind the head when scanning, regardless of the activation of ATVS.

Effect of Matrix Size and Acquisition Mode on Image Quality and Radiation Dose of Ultra-High-Resolution CT of the Temporal Bone: An Anatomical Study.

Purpose: To compare image quality and radiation exposure between super- and ultra-high-resolution helical and super-high-resolution volumetric CT of the temporal bone. Methods: Six cadaveric temporal bone specimens were used to evaluate key temporal bone structures using the following CT reconstruction and acquisition modes: helical and single-volume acquisition modes in super-high resolution (0.25-mm slice thickness, 10242 matrix), and helical mode in ultra-high resolution (0.25-mm slice thickness, 20482 matrix). Two observers performed 5 previously described preoperative measurements, measured noise and signal-to-noise ratios for air, and noise for bone, and rated the visualization of 5 anatomical structures on a 4-point scale, for each reconstruction mode. Radiation dose exposure was recorded for each examination. Results: There was no significant difference between any of the quantitative or qualitative measurements in any of the reconstruction and acquisition modes. There was a slight increase in noise and a decrease in signal-to-noise ratio in the air using the single-volume mode (115 ± 13.1 HU and 8.37 ± 0.91, respectively) compared to the helicoidal super-high-resolution (92.4 ± 11.8 HU and 10.8 ± 1.26, respectively) and helicoidal ultra-high-resolution (91.1 ± 10.7 HU and 10.9 ± 1.39, respectively) modes (P < .002). The volumic CT dose index was 50.9 mGy with helical acquisition and 29.8 mGy with single-volume acquisition mode (P < .0001). Conclusion: The single-volume super-high-resolution acquisition mode allows a reduction in radiation dose exposure without compromising image quality compared to helical scanning, but with a slightly lower signal-to-noise ratio in air with the single-volume mode, while there was no difference in image quality between the helical super- and ultra-high-resolution modes.