Image Quality Of MRI Research Articles

Kiosk 3R-TC-03 - Deep Learning Denoising Reconstruction for Improved Image Quality in Fetal Cardiac Cine MRI

Kiosk 3R-TC-03 - Deep Learning Denoising Reconstruction for Improved Image Quality in Fetal Cardiac Cine MRI

Effect of the Relationship between Respiratory Interval and Temporal Resolution on Image Quality in Free-breathing Abdominal MR Imaging.

To evaluate how the relationship between respiratory interval (RI) and temporal resolution (TR) impacts image quality in free-breathing abdominal MRI (FB-aMRI) using golden-angle radial sparse parallel (GRASP). Ten healthy volunteers (25.9 ± 2.5 years, four women) underwent 2 mins free-breathing fat-suppression T1-weighted imaging using GRASP at RIs of 3 and 5s (RI3 and RI5, respectively) and retrospectively reconstructed at TR of 1.8, 2.9, 4.8, and 7.7s (TR1.8, TR2.9, TR4.8, and TR7.7, respectively) in each patient. The standard deviation (SD) under the diaphragm was measured using SD maps showing the discrepancy for each horizontal section at all TRs. Two radiologists evaluated image quality (visualization of the right hepatic vein at the confluence of the inferior vena cava, posterior segment branch of portal vein, pancreas, left kidney, and artifacts) at all TRs using a 5-point scale. The SD was significantly higher at TR1.8 compared to TR4.8 (P < 0.01) and TR7.7 (P < 0.001), as well as at TR2.9 compared to TR7.7 (P < 0.01) for both RIs. The SD between TR4.8 and TR7.7 did not differ for both RIs. For all visual assessment metrics, the TR1.8 scores were significantly lower than the TR4.8 and TR7.7 scores for both RIs. The pancreas and left kidney scores at TR2.9 were significantly lower than those at TR7.7 (P < 0.05) for RI5. Additionally, the left kidney score at TR1.8 was lower than that at TR2.9 (P < 0.05) for RI3. All scores at TR2.9, TR4.8, and TR7.7 were similar for RI3, while those at TR4.8 and TR7.7 were similar for RI5. Prolonging the TRs compared to RIs enhances image quality in FB-aMRI using GRASP.

The Impact of Contrast Media on Image Quality in MRI: Simple Review Article

The Impact of Contrast Media on Image Quality in MRI: Simple Review Article

Risk factors for prostate cancer in men with false-negative mpMRI: A retrospective single center cohort study of image quality scores and clinical parameters

PurposeTo identify predictors of prostate cancer (PCa) and clinically significant prostate cancer (csPCa) in men with prior false-negative multiparametric MRI (mpMRI), focusing on image quality scoring systems and clinical parameters. MethodsIn this IRB-approved retrospective single-center study, patients with a negative mpMRI (PI-RADS score ≤2) and subsequent prostate biopsies were included. Histopathological results served as reference standard. Welch’s t-Test was conducted to identify significant differences in image quality scores (PI-QUAL and PSHS) between patients with and without PCa/csPCA. In addition, clinical parameters (age, BMI, PSA density) and image quality scores (PI-QUAL and PSHS) were examined as potential predictors of PCa/csPCa detection after a false-negative mpMRI in uni- and multivariate analyses. ResultsAmong 96 patients with negative mpMRI results, 44.8 % had PCa and 16.7 % had csPCa upon biopsy with histopathological confirmation. PI-QUAL scores were significantly lower in patients with PCa (p = 0.03) and csPCa (p = 0.005). PSHS scores were lower in patients with csPCa, but the difference was not statistically significant (p = 0.1). Higher age (p = 0.035) and a lower PI-QUAL score (p < 0.004) were predictors of subsequent csPCa detection upon biopsy, however, a lower PI-QUAL score was the only independent predictor of missed csPCa in false-negative mpMRIs. ConclusionsLower image quality scores were associated with missed PCa/csPCa in patients with false-negative mpMRIs, with PI-QUAL being an independent predictor of failed csPCa detection. This highlights the importance of image quality for prostate MRI and advocats the inclusion of its measurement into the standardized report.

Image quality of DWI at breast MRI depends on the amount of fibroglandular tissue: implications for unenhanced screening

ObjectivesTo compare image quality of diffusion-weighted imaging (DWI) and contrast-enhanced breast MRI (DCE-T1) stratified by the amount of fibroglandular tissue (FGT) as a measure of breast density.MethodsRetrospective, multi-reader, bicentric visual grading analysis study on breast density (A–D) and overall image and fat suppression quality of DWI and DCE-T1, scored on a standard 5-point Likert scale. Cross tabulations and visual grading characteristic (VGC) curves were calculated for fatty breasts (A/B) versus dense breasts (C/D).ResultsImage quality of DWI was higher in the case of increased breast density, with good scores (score 3–5) in 85.9% (D) and 88.4% (C), compared to 61.6% (B) and 53.5% (A). Overall image quality of DWI was in favor of dense breasts (C/D), with an area under the VGC curve of 0.659 (p < 0.001). Quality of DWI and DCE-T1 fat suppression increased with higher breast density, with good scores (score 3–5) for 86.9% and 45.7% of density D, and 90.2% and 42.9% of density C cases, compared to 76.0% and 33.6% for density B and 54.7% and 29.6% for density A (DWI and DCE-T1 respectively).ConclusionsDense breasts show excellent fat suppression and substantially higher image quality in DWI images compared with non-dense breasts. These results support the setup of studies exploring DWI-based MR imaging without IV contrast for additional screening of women with dense breasts.Clinical relevance statementOur findings demonstrate that image quality of DWI is robust in women with an increased amount of fibroglandular tissue, technically supporting the feasibility of exploring applications such as screening of women with mammographically dense breasts.Key Points• Image and fat suppression quality of diffusion-weighted imaging are dependent on the amount of fibroglandular tissue (FGT) which is closely connected to breast density.• Fat suppression quality in diffusion-weighted imaging of the breast is best in women with a high amount of fibroglandular tissue.• High image quality of diffusion-weighted imaging in women with a high amount of FGT in MRI supports that the technical feasibility of DWI can be explored in the additional screening of women with mammographically dense breasts.Graphical

Evaluation of Image Quality of Motion-Corrected Supine Breast MRI.

Breast MRI is the most performant modality for breast cancer diagnosis and could be widespread in the future. The gold standard breast MRI is performed in the prone position, but comfort and correlation with surgery or biopsy positioning can be problematic, while supine MRI could be an interesting alternative. In this work, we evaluated the image quality of T2-weighted supine breast MRI in healthy volunteers after online correction of respiratory motion artifacts compared to standard vendor's reconstruction and to standard prone MRI. T2-weighted images were acquired in the prone and free-breathing supine position in 10 volunteers. Two types of reconstructions were evaluated for supine acquisitions: the standard vendor's reconstruction and an online version of a nonrigid motion correction technique (generalized reconstruction by inversion of coupled system). Image quality criteria, including overall quality, sharpness, uniformity, and different types of artifacts, were assessed and scored by 2 radiologists in a randomized fashion. Interobserver agreement was verified by Weighted Cohen's Kappa calculation and a comparison between the different acquisitions was made by Wilcoxon signed-rank test. Generalized Reconstruction by Inversion of Coupled Systems (GRICS) reconstruction method significantly increased image quality in comparison to the standard reconstruction of supine acquisition. It allows a comparable quality, slightly lower than the gold standard prone MRI in T2-weighted images but it needs to be assessed with more patients and with target lesions before it can be used in clinical practice.

On the comparison of two NIPAM gel dosimeters with high resolution 3D MRI sequences

Polymer gel dosimeters allow the measurement of a dose distribution in 3 dimensions. Irradiation induces polymerization reactions in the long chains of the gel molecules, which is characterized by a change in the transverse relaxation time T2. Gel dosimetry is mainly advantageous for its high resolution, but can also be expensive. The main goal of this project is to compare two normoxic polymer gel recipes made with NIPAM as monomer. The analysis is based on the quality of the images obtained for a fixed MRI scan time and a comparative cost of analysis of each 1L phantom. The ΔT2 maps are obtained by scanning the gels before and after irradiation with 3D sequences and the DESPOT2 technique is used to reconstruct the T2 maps. The phantoms were irradiated with 8 photon beams of 6 MV with a fixed 250 MU, 4 at two opposite sides of the jar (AP-PA configuration), to obtain 4 dose distributions of 4.7 Gy, 8.9 Gy, 13.2 Gy and 17.3 Gy. The SNR is then determined in the ΔT2 maps in function of the dose step and the concentration of NIPAM in the phantom. The first gel phantom is made with 15% NIPAM and has a total cost of $1561.65, including products and MRI scan costs. The SNR obtained for the 4 dose steps are 10.02, 31.18, 45.12 and 37.54. The contrast between the T2 before and after the irradiation in the 4 regions of dose are 0.45, 0.66, 0.78 and 0.85. The second phantom contained 5% NIPAM, cost 1186.85$ and the SNR obtained are 16.80, 27.08, 30.11 and 26.17 and the ΔT2 are of 0.61, 0.75, 0.79 and 0.77 for the 4 dose steps respectively. The comparison of the two recipes has shown that the increase of NIPAM concentration does not allow a significant increase in image quality for MRI. The recipe with 5% of NIPAM has a lower dynamic range but a better sensitivity at lower dose and is less expensive than the one with 15% of NIPAM. The results also show that by increasing the NIPAM concentration 3-fold, the cost of a 1L phantom increases by 30%.

Evaluation of a Deep Learning Reconstruction for High-Quality T2-Weighted Breast Magnetic Resonance Imaging.

Deep learning (DL) reconstruction techniques to improve MR image quality are becoming commercially available with the hope that they will be applicable to multiple imaging application sites and acquisition protocols. However, before clinical implementation, these methods must be validated for specific use cases. In this work, the quality of standard-of-care (SOC) T2w and a high-spatial-resolution (HR) imaging of the breast were assessed both with and without prototype DL reconstruction. Studies were performed using data collected from phantoms, 20 retrospectively collected SOC patient exams, and 56 prospectively acquired SOC and HR patient exams. Image quality was quantitatively assessed via signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and edge sharpness. Qualitatively, all in vivo images were scored by either two or four radiologist readers using 5-point Likert scales in the following categories: artifacts, perceived sharpness, perceived SNR, and overall quality. Differences in reader scores were tested for significance. Reader preference and perception of signal intensity changes were also assessed. Application of the DL resulted in higher average SNR (1.2-2.8 times), CNR (1.0-1.8 times), and image sharpness (1.2-1.7 times). Qualitatively, the SOC acquisition with DL resulted in significantly improved image quality scores in all categories compared to non-DL images. HR acquisition with DL significantly increased SNR, sharpness, and overall quality compared to both the non-DL SOC and the non-DL HR images. The acquisition time for the HR data only required a 20% increase compared to the SOC acquisition and readers typically preferred DL images over non-DL counterparts. Overall, the DL reconstruction demonstrated improved T2w image quality in clinical breast MRI.

Image quality in whole-body MRI using the MY-RADS protocol in a prospective multi-centre multiple myeloma study

BackgroundThe Myeloma Response Assessment and Diagnosis System (MY-RADS) guidelines establish a standardised acquisition and analysis pipeline for whole-body MRI (WB-MRI) in patients with myeloma. This is the first study to assess image quality in a multi-centre prospective trial using MY-RADS.MethodsThe cohort consisted of 121 examinations acquired across ten sites with a range of prior WB-MRI experience, three scanner manufacturers and two field strengths. Image quality was evaluated qualitatively by a radiologist and quantitatively using a semi-automated pipeline to quantify common artefacts and image quality issues. The intra- and inter-rater repeatability of qualitative and quantitative scoring was also assessed.ResultsQualitative radiological scoring found that the image quality was generally good, with 94% of examinations rated as good or excellent and only one examination rated as non-diagnostic. There was a significant correlation between radiological and quantitative scoring for most measures, and intra- and inter-rater repeatability were generally good.When the quality of an overall examination was low, this was often due to low quality diffusion-weighted imaging (DWI), where signal to noise ratio (SNR), anterior thoracic signal loss and brain geometric distortion were found as significant predictors of examination quality.ConclusionsIt is possible to successfully deliver a multi-centre WB-MRI study using the MY-RADS protocol involving scanners with a range of manufacturers, models and field strengths. Quantitative measures of image quality were developed and shown to be significantly correlated with radiological assessment. The SNR of DW images was identified as a significant factor affecting overall examination quality.Trial registrationClinicalTrials.gov, NCT03188172, Registered on 15 June 2017.Critical relevance statementGood overall image quality, assessed both qualitatively and quantitatively, can be achieved in a multi-centre whole-body MRI study using the MY-RADS guidelines.Key points• A prospective multi-centre WB-MRI study using MY-RADS can be successfully delivered.• Quantitative image quality metrics were developed and correlated with radiological assessment.• SNR in DWI was identified as a significant predictor of quality, allowing for rapid quality adjustment.Graphical

Brand ferumoxytol vs. generic ferumoxytol comparison across two dosing regimens: a cardiac MRI image quality study.

Ferumoxytol is becoming more widely used as an off-label blood-pool contrast agent for MR angiography (MRA) and four-dimensional (4D) flow imaging in pediatric cardiovascular disease. Brand and generic versions of ferumoxytol are available with no information on relative efficacy as a contrast agent and safety profiles. This study evaluates patient safety and image quality of comparable dosages of generic ferumoxytol (GF) versus brand ferumoxytol (BF) with the following hypotheses: (1) Reducing the contrast dosage from 3 to 2mg/kg will not affect imaging quality and diagnostic accuracy of MRA and four-dimensional 4D flow. (2) GF and BF have similar image quality. (3) GF and BF have similar patient safety profiles. In an IRB-approved retrospective study, changes in vitals/clinical status between baseline, during infusion, and 30min post-infusion were analyzed in 3 groups: group 1 (3mg/kg BF, 216 patients, age: 19.29 ± 11.71years ranging from 2months to 62years), group 2 (2mg/kg BF, 47 patients, age: 15.35 ± 8.56years ranging from 10days to 41years), and group 3 (2mg/kg GF, 127 patients, age: 17.16 ± 12.18years ranging from 6days to 58years). Both pediatric and adult patients with congenital heart disease (CHD) indications were included within the study. Adverse reactions were classified as mild, moderate, or severe. Quantitative analysis of MR image quality was performed with signal-to-noise ratio (SNR) on MRA and velocity-to-noise ratio (VNR) on 4D flow. Qualitative grading of imaging features was performed by 2 experienced observers. Two-way analysis of variance (ANOVA) and chi-square tests were used for comparison with a P value of ≤ 0.05 used for significance. No statistical difference was found in clinical status and vital signs (P>0.05). No severe reactions were reported. 7.9% of GF patients experienced an adverse reaction compared to 2.3% with 3mg/kg BF and 8.4% with 2mg/kg BF. There was no statistical difference in SNR between the 3 groups (P>0.05). For 4D flow, 2mg/kg GF demonstrated an increase in VNR compared to 2mg/kg BF (P = 0.005). The qualitative scores for MRA and 4D flow were high (≥ 3) across all 3 groups. No significant difference was identified between 2mg/kg GF and BF in terms of safety profile and image quality. Given the small sample size of this study, further studies are required to confirm these results.

Picture Perfect: The Status of Image Quality in Prostate MRI.

Magnetic resonance imaging is the gold standard imaging modality for the diagnosis of prostate cancer (PCa). Image quality is a fundamental prerequisite for the ability to detect clinically significant disease. In this critical review, we separate the issue of image quality into quality improvement and quality assessment. Beginning with the evolution of technical recommendations for scan acquisition, we investigate the role of patient preparation, scanner factors, and more advanced sequences, including those featuring Artificial Intelligence (AI), in determining image quality. As means of quality appraisal, the published literature on scoring systems (including the Prostate Imaging Quality score), is evaluated. Finally, the application of AI and teaching courses as ways to facilitate quality assessment are discussed, encouraging the implementation of future image quality initiatives along the PCa diagnostic and monitoring pathway. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 3.

Improving MR image quality with a multi-task model, using convolutional losses

PurposeDuring the acquisition of MRI data, patient-, sequence-, or hardware-related factors can introduce artefacts that degrade image quality. Four of the most significant tasks for improving MRI image quality have been bias field correction, super-resolution, motion-, and noise correction. Machine learning has achieved outstanding results in improving MR image quality for these tasks individually, yet multi-task methods are rarely explored.MethodsIn this study, we developed a model to simultaneously correct for all four aforementioned artefacts using multi-task learning. Two different datasets were collected, one consisting of brain scans while the other pelvic scans, which were used to train separate models, implementing their corresponding artefact augmentations. Additionally, we explored a novel loss function that does not only aim to reconstruct the individual pixel values, but also the image gradients, to produce sharper, more realistic results. The difference between the evaluated methods was tested for significance using a Friedman test of equivalence followed by a Nemenyi post-hoc test.ResultsOur proposed model generally outperformed other commonly-used correction methods for individual artefacts, consistently achieving equal or superior results in at least one of the evaluation metrics. For images with multiple simultaneous artefacts, we show that the performance of using a combination of models, trained to correct individual artefacts depends heavily on the order that they were applied. This is not an issue for our proposed multi-task model. The model trained using our novel convolutional loss function always outperformed the model trained with a mean squared error loss, when evaluated using Visual Information Fidelity, a quality metric connected to perceptual quality.ConclusionWe trained two models for multi-task MRI artefact correction of brain, and pelvic scans. We used a novel loss function that significantly improves the image quality of the outputs over using mean squared error. The approach performs well on real world data, and it provides insight into which artefacts it detects and corrects for. Our proposed model and source code were made publicly available.

Multi-parametric optimization of magnetic resonance imaging sequences for magnetic resonance-guided radiotherapy

Background and purposeMagnetic Resonance Imaging (MRI) is widely used in oncology for tumor staging, treatment response assessment, and radiation therapy (RT) planning. This study proposes a framework for automatic optimization of MRI sequences based on pulse sequence parameter sets (SPS) that are directly applied on the scanner, for application in RT planning. Materials and methodsA phantom with seven in-house fabricated contrasts was used for measurements. The proposed framework employed a derivative-free optimization algorithm to repeatedly update and execute a parametrized sequence on the MR scanner to acquire new data. In each iteration, the mean-square error was calculated based on the clinical application. Two clinically relevant optimization goals were pursued: achieving the same signal and therefore contrast as in a target image, and maximizing the signal difference (contrast) between specified tissue types. The framework was evaluated using two optimization methods: a covariance matrix adaptation evolution strategy (CMA-ES) and a genetic algorithm (GA). ResultsThe obtained results demonstrated the potential of the proposed framework for automatic optimization of MRI sequences. Both CMA-ES and GA methods showed promising results in achieving the two optimization goals, however, CMA-ES converged much faster as compared to GA. ConclusionsThe proposed framework enables for automatic optimization of MRI sequences based on SPS that are directly applied on the scanner and it may be used to enhance the quality of MRI images for dedicated applications in MR-guided RT.

Ambulatory sedation for children under 6 years with CHD in MRI and CT.

In infants and young children, good image quality in MRI and CT requires sedation or general anesthesia to prevent motion artefacts. This study aims to determine the safety of ambulatory sedation for children with CHD in an outpatient setting as a feasible alternative to in-hospital management. We recorded 91 consecutive MRI and CT examinations of patients with CHD younger than 6 years with ambulatory sedation. CHD diagnoses, vital signs, applied sedatives, and adverse events during or after ambulatory sedation were investigated. We analysed 91 patients under 72 months (6 years) of age (median 26.0, range 1-70 months; 36% female). Sixty-eight per cent were classified as ASA IV, 25% as ASA III, and 7% as ASA II (American Society of Anesthesiologists Physical Status Classification). Ambulatory sedation was performed by using midazolam, propofol, and/or S-ketamine. The median sedation time for MRI was 90 minutes (range 35-235 minutes) and 65 minutes for CT (range 40-280 minutes). Two male patients (age 1.5 months, ASA II, and age 17 months, ASA IV) were admitted for in-hospital observation due to unexpected severe airway obstruction. The patients were discharged without sequelae after 1 and 3 days, respectively. All other patients were sent home on the day of examination. In infants and young children with CHD, MRI or CT imaging can be performed under sedation in an outpatient setting by a well-experienced team. In-hospital backup should be available for unexpected events.

Accelerated 3D MR neurography of the brachial plexus using deep learning-constrained compressed sensing.

To explore the use of deep learning-constrained compressed sensing (DLCS) in improving image quality and acquisition time for 3D MRI of the brachial plexus. Fifty-four participants who underwent contrast-enhanced imaging and forty-one participants who underwent unenhanced imaging were included. Sensitivity encoding with an acceleration of 2 × 2 (SENSE4x), CS with an acceleration of 4 (CS4x), and DLCS with acceleration of 4 (DLCS4x) and 8 (DLCS8x) were used for MRI of the brachial plexus. Apparent signal-to-noise ratios (aSNRs), apparent contrast-to-noise ratios (aCNRs), and qualitative scores on a 4-point scale were evaluated and compared by ANOVA and the Friedman test. Interobserver agreement was evaluated by calculating the intraclass correlation coefficients. DLCS4x achieved higher aSNR and aCNR than SENSE4x, CS4x, and DLCS8x (all p < 0.05). For the root segment of the brachial plexus, no statistically significant differences in the qualitative scores were found among the four sequences. For the trunk segment, DLCS4x had higher scores than SENSE4x (p = 0.04) in the contrast-enhanced group and had higher scores than SENSE4x and DLCS8x in the unenhanced group (all p < 0.05). For the divisions, cords, and branches, DLCS4x had higher scores than SENSE4x, CS4x, and DLCS8x (all p ≤ 0.01). No overt difference was found among SENSE4x, CS4x, and DLCS8x in any segment of the brachial plexus (all p > 0.05). In three-dimensional MRI for the brachial plexus, DLCS4x can improve image quality compared with SENSE4x and CS4x, and DLCS8x can maintain the image quality compared to SENSE4x and CS4x. Deep learning-constrained compressed sensing can improve the image quality or accelerate acquisition of 3D MRI of the brachial plexus, which should be benefit in evaluating the brachial plexus and its branches in clinical practice. •Deep learning-constrained compressed sensing showed higher aSNR, aCNR, and qualitative scores for the brachial plexus than SENSE and CS at the same acceleration factor with similar scanning time. •Deep learning-constrained compressed sensing at acceleration factor of 8 had comparable aSNR, aCNR, and qualitative scores to SENSE4x and CS4x with approximately half the examination time. •Deep learning-constrained compressed sensing may be helpful in clinical practice for improving image quality and acquisition time in three-dimensional MRI of the brachial plexus.

Motion Robust MR Fingerprinting Scan to Image Neonates With Prenatal Opioid Exposure.

To explore whether MR fingerprinting (MRF) scans provide motion-robust and quantitative brain tissue measurements for non-sedated infants with prenatal opioid exposure (POE). Prospective. 13 infants with POE (3 male; 12 newborns (age 7-65 days) and 1 infant aged 9-months). 3T, 3D T1-weighted MPRAGE, 3D T2-weighted TSE and MRF sequences. The image quality of MRF and MRI was assessed in a fully crossed, multiple-reader, multiple-case study. Sixteen image quality features in three types-image artifacts, structure and myelination visualization-were ranked by four neuroradiologists (8, 7, 5, and 8 years of experience respectively), using a 3-point scale. MRF T1 and T2 values in 8 white matter brain regions were compared between babies younger than 1 month and babies between 1 and 2 months. Generalized estimating equations model to test the significance of differences of regional T1 and T2 values of babies under 1 month and those older. MRI and MRF image quality was assessed using Gwet's second order auto-correlation coefficient (AC2) with confidence levels. The Cochran-Mantel-Haenszel test was used to assess the difference in proportions between MRF and MRI for all features and stratified by the type of features. A P value <0.05 was considered statistically significant. The MRF of two infants were excluded in T1 and T2 value analysis due to severe motion artifact but were included in the image quality assessment. In infants under 1 month of age (N = 6), the T1 and T2 values were significantly higher compared to those between 1 and 2 months of age (N = 4). MRF images showed significantly higher image quality ratings in all three feature types compared to MRI images. MR Fingerprinting scans have potential to be a motion-robust and efficient method for nonsedated infants. 2 TECHNICAL EFFICACY STAGE: 1.

Assessment of deep learning-based reconstruction on T2-weighted and diffusion-weighted prostate MRI image quality

PurposeTo evaluate the impact of a commercially available deep learning-based reconstruction (DLR) algorithm with varying combinations of DLR noise reduction settings and imaging parameters on quantitative and qualitative image quality, PI-RADS classification and examination time in prostate T2-weighted (T2WI) and diffusion-weighted (DWI) imaging. MethodForty patients were included. Standard-of-care (SoC) prostate MRI sequences including T2WI and DWI were reconstructed without and with different DLR de-noising levels (low, medium, high). In addition, faster T2WI(Fast) and DWI(Fast) sequences, and a higher resolution T2WI(HR) sequence were evaluated. Quantitative analysis included signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR) and apparent diffusion coefficient (ADC) values. Two radiologists performed qualitative analysis, independently evaluating imaging datasets using 5-point scoring scales for image quality and artifacts. PI-RADS category assignment was also performed by the more experienced radiologist. ResultsAll DLR levels resulted in significantly higher SNR and CNR compared to the DLR(off) acquisitions. DLR allowed the acquisition time to be reduced by 33% for T2WI(Fast) and 49% for DWI(Fast) compared to SoC, without affecting image quality, whilst T2WI(HR) with DLR allowed for a 73% increase in spatial resolution in the phase encode direction compared to SoC. The inter-reader agreement for image quality and artifact scores was substantial for all subjective measurements on T2WI and DWI. The T2WI(Fast) protocol with DLR(medium) and DWI(Fast) with DLR(low) received the highest qualitative quality score. ConclusionDLR can reduce T2WI and DWI acquisition time and increase SNR and CNR without compromising image quality or altering PI-RADS classification.

Comparative Analysis of Image Processing Techniques for Enhanced MRI Image Quality: 3D Reconstruction and Segmentation Using 3D U-Net Architecture.

Osteosarcoma is a common type of bone tumor, particularly prevalent in children and adolescents between the ages of 5 and 25 who are experiencing growth spurts during puberty. Manual delineation of tumor regions in MRI images can be laborious and time-consuming, and results may be subjective and difficult to replicate. Therefore, a convolutional neural network (CNN) was developed to automatically segment osteosarcoma cancerous cells in three types of MRI images. The study consisted of five main stages. First, 3692 DICOM format MRI images were acquired from 46 patients, including T1-weighted, T2-weighted, and T1-weighted with injection of Gadolinium (T1W + Gd) images. Contrast stretching and median filter were applied to enhance image intensity and remove noise, and the pre-processed images were reconstructed into NIfTI format files for deep learning. The MRI images were then transformed to fit the CNN's requirements. A 3D U-Net architecture was proposed with optimized parameters to build an automatic segmentation model capable of segmenting osteosarcoma from the MRI images. The 3D U-Net segmentation model achieved excellent results, with mean dice similarity coefficients (DSC) of 83.75%, 85.45%, and 87.62% for T1W, T2W, and T1W + Gd images, respectively. However, the study found that the proposed method had some limitations, including poorly defined borders, missing lesion portions, and other confounding factors. In summary, an automatic segmentation method based on a CNN has been developed to address the challenge of manually segmenting osteosarcoma cancerous cells in MRI images. While the proposed method showed promise, the study revealed limitations that need to be addressed to improve its efficacy.

MR image quality in local staging of prostate cancer: Role of PI-QUAL in the detection of extraprostatic extension

PurposeTo assess the impact of prostate MRI image quality by means of the Prostate Imaging Quality (PI-QUAL) score, on the identification of extraprostatic extension of disease (EPE), predicted using the EPE Grade Score, Likert Scale Score (LSS) and a clinical nomogram (MSKCCn). MethodsWe retrospectively included 105 patients with multiparametric prostate MRI prior to prostatectomy. Two radiologists evaluated image quality using PI-QUAL (≥4 was considered high quality) in consensus. All cases were also scored using the EPE Grade, the LSS, and the MSKCCn (dichotomized). Inter-rater reproducibility for each score was also assessed. Accuracy was calculated for the entire population and by image quality, considering two thresholds for EPE Grade (≥2 and = 3) and LSS (≥3 and ≥ 4) and using McNemar’s test for comparison. ResultsOverall, 66 scans achieved high quality. The accuracy of EPE Grade ranged from 0.695 to 0.743, while LSS achieved values between 0.705 and 0.733. Overall sensitivity for the radiological scores (range = 0.235–0.529) was low irrespective of the PI-QUAL score, while specificity was higher (0.775–0.986). The MSKCCn achieved an AUC of 0.76, outperforming EPE Grade (=3 threshold) in studies with suboptimal image quality (0.821 vs 0.564, p = 0.016). EPE Grade (=3 threshold) accuracy was also better in high image quality studies (0.849 vs 0.564, p = 0.001). Reproducibility was good to excellent overall (95 % Confidence Interval range = 0.782–0.924). ConclusionAssessing image quality by means of PI-QUAL is helpful in the evaluation of EPE, as a scan of low quality makes its performance drop compared to clinical staging tools.

3D Synthetic Brain MRI with Compressed Sensing: Can It Be a Promising Way Forward for Daily Neuroimaging?

Synthetic MRI can provide multiple contrast-weighted brain images with high resolution from a single scan via a 3D sequence using an interleaved Look-Locker acquisition sequence with a T2 preparation pulse (3D-QALAS). This study aimed to assess the diagnostic image quality of 3D synthetic MRI using compressed sensing (CS) in clinical practice. We retrospectively reviewed the imaging data of 47 patients who underwent brain MRI, including 3D synthetic MRI using CS in a single session, between December 2020 and February 2021. Two neuroradiologists independently evaluated the overall image quality, anatomic demarcation, and artifacts for synthetic 3D T1-weighted, T2-weighted, FLAIR, phase-sensitive inversion recovery (PSIR), and double inversion recovery images, using a 5-point Likert scale. The interobserver agreement between the two readers was assessed using percent agreement and weighted κ statistics. The overall image quality of 3D synthetic T1WI and PSIR was good to excellent, with easy or excellent anatomic demarcation and mild or no visible artifact. However, other 3D synthetic MRI-derived images showed insufficient image quality and anatomic demarcation with marked CSF pulsation artifacts. In particular, 3D synthetic FLAIR showed high-signal artifacts on the brain surface. 3D synthetic MRI, at its current status, cannot completely replace conventional brain MRI in daily clinical practice. However, 3D synthetic MRI can achieve scan-time reduction using CS and parallel imaging and may be useful for motion-prone or pediatric patients requiring 3D images where time-efficiency is important.