Magnetic resonance imaging最新文献

{"title":"Comprehensive characterization of tumor therapeutic response via simultaneous mapping of cell size, density, and transcytolemmal water exchange","authors":"Diwei Shi ,&nbsp;Xiaoxia Wang ,&nbsp;Sisi Li ,&nbsp;Fan Liu ,&nbsp;Xiaoyu Jiang ,&nbsp;Li Chen ,&nbsp;Jiuquan Zhang ,&nbsp;Hua Guo ,&nbsp;Junzhong Xu","doi":"10.1016/j.mri.2025.110433","DOIUrl":"10.1016/j.mri.2025.110433","url":null,"abstract":"<div><div>The evaluation of tumor response to neoadjuvant chemotherapy is critical for the personalized management of cancer patients, aiming to minimize unnecessary toxicity, costs, and treatment delays. Current imaging techniques primarily depend on detecting tumor volume changes, which reflect downstream effects. In contrast, advanced microstructural diffusion MRI (dMRI) methods offer cellular-level insights but are limited by biased estimates of cell density due to oversimplified biophysical models. We present a novel dMRI-based approach, EXCHANGE, which incorporates transcytolemmal water exchange into a quantitative multi-compartmental biophysical model. This method enables simultaneous mapping of cell size, density, and transcytolemmal water exchange, providing a comprehensive characterization of tumor microstructure. Validation through computer simulations and in vitro studies demonstrated the good accuracy of EXCHANGE-derived metrics. In a proof-of-concept study, EXCHANGE was applied to animal models and patients with triple-negative breast cancer, showcasing its potential to evaluate tumor therapeutic response to neoadjuvant chemotherapy. EXCHANGE offers a unique capability to characterize tumor microstructural properties at the cellular level, paving the way for improved monitoring of treatment response in clinical settings.</div></div>","PeriodicalId":18165,"journal":{"name":"Magnetic resonance imaging","volume":"122 ","pages":"Article 110433"},"PeriodicalIF":2.1,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144216260","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correlation of pathologic features and prognostic factors in rectal adenocarcinoma based on APT imaging and IVIM-DWI histogram","authors":"Shiji Kan ,&nbsp;Yongwen Sun ,&nbsp;Kai Ai ,&nbsp;Yong Xia ,&nbsp;Bo Gao","doi":"10.1016/j.mri.2025.110430","DOIUrl":"10.1016/j.mri.2025.110430","url":null,"abstract":"<div><h3>Objective</h3><div>This study aimed to evaluate the effectiveness of amide proton transfer (APT) imaging and intravoxel incoherent motion (IVIM) histogram parameters in predicting pathologic prognostic factors (lymph node metastasis and vascular invasion) in rectal adenocarcinoma. Additionally, the study compared the diagnostic performance of these parameters through combined models.</div></div><div><h3>Methods</h3><div>This study enrolled 42 patients with rectal adenocarcinoma proved by pathology. The APT signal intensity (APTSI) of primary rectal cancer was measured. The IVIM images were postprocessed to generate quantitative parameter maps of pure diffusioncoefficient(D), pseudo-diffusion coefficient(D*), perfusion fraction(f). The histogram analysis was performed to obtain the minimum, maximum, mean, standard deviation, variance, median, 10th and 90th percentiles (10th and 90th henceforth), skewness, kurtosis, and entropy of each parameter.The postoperative pathologic results included T stage, lymph node N stage, and peripheral nerve and lymphovascular invasion.</div></div><div><h3>Results</h3><div>The histogram of D and D* were statistically significant between with and without lymph node metastasis (LNM) (<em>P</em> &lt; .05). The histogram of D value was significant between with lymphovascular invasion or not (<em>P</em> &lt; .05). No clear difference was noted between APTSI and prognostic factors of rectal adenocarcinoma (<em>P</em> &gt; .05). The area under the curve (AUC) of the combined model combining 90th, kurtosis, entropy, and D* maximum value for diagnosing LNM of rectal adenocarcinoma was 0.796. The AUC value of the combined model combining the mean, median, 10th and 90th, skewness, kurtosis, and entropy of D value in diagnosing the presence or absence of lymphovascular invasion of rectal adenocarcinoma was 0.821.</div></div><div><h3>Conclusions</h3><div>IVIM histogram parameters (e.g., 90th percentile of <em>D</em>, kurtosis, and entropy) displayed significant diagnostic value for detecting LNM and vascular invasion in rectal adenocarcinoma. In contrast, APTSI showed no significant correlation with these prognostic factors. These findings underscore the potential of IVIM imaging as a noninvasive tool for preoperative risk stratification in patients with rectal adenocarcinoma.</div></div><div><h3>Key points</h3><div>IVIM histogram parameters help distinguish LNM and lymphovascular invasion in rectal adenocarcinoma. No obvious difference was observed in APTSI between patients with rectal adenocarcinoma with various TN stages, peripheral nerve invasion, and vascular invasion.</div></div>","PeriodicalId":18165,"journal":{"name":"Magnetic resonance imaging","volume":"122 ","pages":"Article 110430"},"PeriodicalIF":2.1,"publicationDate":"2025-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144208883","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fully automated measurement of aortic pulse wave velocity from routine cardiac MRI studies","authors":"Yue Jiang ,&nbsp;Tina Yao ,&nbsp;Nikhil Paliwal ,&nbsp;Daniel Knight ,&nbsp;Karan Punjabi ,&nbsp;Jennifer Steeden ,&nbsp;Alun D. Hughes ,&nbsp;Vivek Muthurangu ,&nbsp;Rhodri Davies","doi":"10.1016/j.mri.2025.110442","DOIUrl":"10.1016/j.mri.2025.110442","url":null,"abstract":"<div><h3>Introduction</h3><div>Aortic pulse wave velocity (PWV) is a prognostic biomarker for cardiovascular disease, which can be measured by dividing the aortic path length by the pulse transit time. However, current MRI techniques require special sequences and time-consuming manual analysis. We aimed to fully automate the process using deep learning to measure PWV from standard sequences, facilitating PWV measurement in routine clinical and research scans.</div></div><div><h3>Methods</h3><div>A deep learning (DL) model was developed to generate high-resolution 3D aortic segmentations from routine 2D trans-axial SSFP localizer images, and the centerlines of the resulting segmentations were used to estimate the aortic path length. A further DL model was built to automatically segment the ascending and descending aorta in phase contrast images, and pulse transit time was estimated from the sampled flow curves. Quantitative comparison with trained observers was performed for path length, aortic flow segmentation and transit time, either using an external clinical dataset with both localizers and paired 3D images acquired or on a sample of UK Biobank subjects. Potential application to clinical research scans was evaluated on 1053 subjects from the UK Biobank.</div></div><div><h3>Results</h3><div>Aortic path length measurement was accurate with no major difference between the proposed method (125 ± 19 mm) and manual measurement by a trained observer (124 ± 19 mm) (<em>P</em> = 0.88). Automated phase contrast image segmentation was similar to that of a trained observer for both the ascending (Dice vs manual: 0.96) and descending (Dice 0.89) aorta with no major difference in transit time estimation (proposed method = 21 ± 9 ms, manual = 22 ± 9 ms; <em>P</em> = 0.15). 966 of 1053 (92 %) UK Biobank subjects were successfully analyzed, with a median PWV of 6.8 m/s, increasing 27 % per decade of age and 6.5 % higher per 10 mmHg higher systolic blood pressure.</div></div><div><h3>Conclusions</h3><div>We describe a fully automated method for measuring PWV from standard cardiac MRI localizers and a single phase contrast imaging plane. The method is robust and can be applied to routine clinical scans, and could unlock the potential of measuring PWV in large-scale clinical and population studies. All models and deployment codes are available online.</div></div>","PeriodicalId":18165,"journal":{"name":"Magnetic resonance imaging","volume":"122 ","pages":"Article 110442"},"PeriodicalIF":2.1,"publicationDate":"2025-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144199526","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MATI: A GPU-accelerated toolbox for microstructural diffusion MRI simulation and data fitting with a graphical user interface","authors":"Junzhong Xu ,&nbsp;Sean P. Devan ,&nbsp;Diwei Shi ,&nbsp;Adithya Pamulaparthi ,&nbsp;Nicholas Yan ,&nbsp;Zhongliang Zu ,&nbsp;David S. Smith ,&nbsp;Kevin D. Harkins ,&nbsp;John C. Gore ,&nbsp;Xiaoyu Jiang","doi":"10.1016/j.mri.2025.110428","DOIUrl":"10.1016/j.mri.2025.110428","url":null,"abstract":"<div><h3>Purpose</h3><div>To introduce MATI (Microstructural Analysis Toolbox for Imaging), a versatile MATLAB-based toolbox that combines both simulation and data fitting capabilities for microstructural dMRI research.</div></div><div><h3>Methods</h3><div>MATI provides a user-friendly, graphical user interface that enables researchers, including those without much programming experience, to perform advanced simulations and data analyses for microstructural MRI research. For simulation, MATI supports arbitrary microstructural tissues and pulse sequences. For data fitting, MATI supports a range of fitting methods, including traditional non-linear least squares, Bayesian approaches, machine learning, and dictionary matching methods, allowing users to tailor analyses based on specific research needs.</div></div><div><h3>Results</h3><div>Optimized with vectorized matrix operations and high-performance numerical libraries, MATI achieves high computational efficiency, enabling rapid simulations and data fitting on CPU and GPU hardware. While designed for microstructural dMRI, MATI's generalized framework can be extended to other imaging methods, making it a flexible and scalable tool for quantitative MRI research.</div></div><div><h3>Conclusion</h3><div>MATI offers a significant step toward translating advanced microstructural MRI techniques into clinical applications.</div></div>","PeriodicalId":18165,"journal":{"name":"Magnetic resonance imaging","volume":"122 ","pages":"Article 110428"},"PeriodicalIF":2.1,"publicationDate":"2025-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144151125","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MRI-based habitat analysis for Intratumoral heterogeneity quantification combined with deep learning for HER2 status prediction in breast cancer","authors":"Qing-Yu Li,&nbsp;Yue Liang,&nbsp;Lan Zhang,&nbsp;Jia-Hao Li,&nbsp;Bin-Jie Wang,&nbsp;Chang-Fu Wang","doi":"10.1016/j.mri.2025.110429","DOIUrl":"10.1016/j.mri.2025.110429","url":null,"abstract":"<div><h3>Background</h3><div>Human epidermal growth factor receptor 2 (HER2) is a crucial determinant of breast cancer prognosis and treatment options. The study aimed to establish an MRI-based habitat model to quantify intratumoral heterogeneity (ITH) and evaluate its potential in predicting HER2 expression status.</div></div><div><h3>Methods</h3><div>Data from 340 patients with pathologically confirmed invasive breast cancer were retrospectively analyzed. Two tasks were designed for this study: Task 1 distinguished between HER2-positive and HER2-negative breast cancer. Task 2 distinguished between HER2-low and HER2-zero breast cancer. We developed the ITH, deep learning (DL), and radiomics signatures based on the features extracted from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). Clinical independent predictors were determined by multivariable logistic regression. Finally, a combined model was constructed by integrating the clinical independent predictors, ITH signature, and DL signature. The area under the receiver operating characteristic curve (AUC) served as the standard for assessing the performance of models.</div></div><div><h3>Results</h3><div>In task 1, the ITH signature performed well in the training set (AUC = 0.855) and the validation set (AUC = 0.842). In task 2, the AUCs of the ITH signature were 0.844 and 0.840, respectively, which still showed good prediction performance. In the validation sets of both tasks, the combined model exhibited the best prediction performance, with AUCs of 0.912 and 0.917 respectively, making it the optimal model.</div></div><div><h3>Conclusion</h3><div>A combined model integrating clinical independent predictors, ITH signature, and DL signature can predict HER2 expression status preoperatively and noninvasively.</div></div>","PeriodicalId":18165,"journal":{"name":"Magnetic resonance imaging","volume":"122 ","pages":"Article 110429"},"PeriodicalIF":2.1,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144143172","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Denoising of high-resolution 3D UTE-MR angiogram data using lightweight and efficient convolutional neural networks","authors":"Abel Worku Tessema ,&nbsp;Dagnachew Tessema Ambaye ,&nbsp;HyungJoon Cho","doi":"10.1016/j.mri.2025.110426","DOIUrl":"10.1016/j.mri.2025.110426","url":null,"abstract":"<div><div>High-resolution magnetic resonance angiography (∼ 50 μm³ MRA) data plays a critical role in the accurate diagnosis of various vascular disorders. However, it is very challenging to acquire, and it is susceptible to artifacts and noise which limits its ability to visualize smaller blood vessels and necessitates substantial noise reduction measures. Among many techniques, the BM4D filter is a state-of-the-art denoising technique but comes with high computational cost, particularly for high-resolution 3D MRA data. In this research, five different optimized convolutional neural networks were utilized to denoise contrast-enhanced UTE-MRA data using a supervised learning approach. Since noise-free MRA data is challenging to acquire, the denoised image using BM4D filter was used as ground truth and this research mainly focused on reducing computational cost and inference time for denoising high-resolution UTE-MRA data. All five models were able to generate nearly similar denoised data compared to the ground truth with different computational footprints. Among all, the nested-UNet model generated almost similar images with the ground truth and achieved SSIM, PSNR, and MSE of 0.998, 46.12, and 3.38e-5 with 3× faster inference time than the BM4D filter. In addition, most optimized models like UNet and attention-UNet models generated nearly similar images with nested-UNet but 8.8× and 7.1× faster than the BM4D filter. In conclusion, using highly optimized networks, we have shown the possibility of denoising high-resolution UTE-MRA data with significantly shorter inference time, even with limited datasets from animal models. This can potentially make high-resolution 3D UTE-MRA data to be less computationally burdensome.</div></div>","PeriodicalId":18165,"journal":{"name":"Magnetic resonance imaging","volume":"121 ","pages":"Article 110426"},"PeriodicalIF":2.1,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144143171","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Harmonized connectome resampling for variance in voxel sizes","authors":"Elyssa M. McMaster ,&nbsp;Nancy R. Newlin ,&nbsp;Gaurav Rudravaram ,&nbsp;Adam M. Saunders ,&nbsp;Aravind R. Krishnan ,&nbsp;Lucas W. Remedios ,&nbsp;Michael E. Kim ,&nbsp;Hanliang Xu ,&nbsp;Jongyeon Yoon ,&nbsp;Derek B. Archer ,&nbsp;Kurt G. Schilling ,&nbsp;François Rheault ,&nbsp;Laurie E. Cutting ,&nbsp;Bennett A. Landman","doi":"10.1016/j.mri.2025.110424","DOIUrl":"10.1016/j.mri.2025.110424","url":null,"abstract":"<div><div>Diffusion MRI (dMRI) fiber tractography presents exciting opportunities to deepen our knowledge of human brain connectivity and discover novel alterations in white matter. To date, there has been no comprehensive study characterizing the effect of dMRI voxel resolution on the resulting connectome for subject data. We assessed the statistical significance of graph measures derived from dMRI data by comparing connectomes from the same scans across different resolutions with 44 subjects (32 female) from the Human Connectome Project – Young Adult dataset (HCP-YA) with scan/rescan data (88 scans). We explored 15 isotropic and anisotropic resolutions, generated tractography and connectomes, and compared graph measures between each resolution and its nearest larger and smaller resolutions. Nearly all pairwise comparisons yielded statistically significant differences in graph measures (<em>p</em> ≤ 0.05, Wilcoxon Sign-Rank Test). Upon up sampling the 14 down sampled resolutions in 0.5 mm increments, we observed mitigation of the spatial sampling effect on both the tractography and the connectome's complex graph measures. To investigate translational impact, we resampled 22 subjects from HCP-YA to the resolutions of two major national studies and up-sampled this data back to 1 mm isotropic with different interpolation methods. Similarity in results improved with higher resolution, even after initial down-sampling. To ensure robust tractography and connectomes, resample data to 1 mm isotropic resolution.</div></div>","PeriodicalId":18165,"journal":{"name":"Magnetic resonance imaging","volume":"121 ","pages":"Article 110424"},"PeriodicalIF":2.1,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144120097","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Microvascular functional and structural changes in early-stage CADASIL","authors":"Shan Tian ,&nbsp;Hongwei Li ,&nbsp;Junting Yang ,&nbsp;Yuna Li ,&nbsp;Yuan Qiao ,&nbsp;Chaohua Cong ,&nbsp;Lei Zhao ,&nbsp;Panlong Li ,&nbsp;He Wang ,&nbsp;Jingjing Su","doi":"10.1016/j.mri.2025.110402","DOIUrl":"10.1016/j.mri.2025.110402","url":null,"abstract":"<div><h3>Background</h3><div>Cerebral autosomal dominant arteriopathy with subcortical infarcts and leukoencephalopathy (CADASIL) is the most common monogenic form of hereditary cerebral small vessel disease (CSVD). While studies have demonstrated heterogeneous alterations in cerebrovascular reactivity (CVR) and gray matter structure in CADASIL patients, the diagnostic utility of CVR and brain structural imaging in identifying CADASIL remains uncertain.</div></div><div><h3>Methods</h3><div>This study investigated CVR and gray matter density (GMD) in 22 CADASIL patients compared to 21 age- and sex-matched healthy controls. Resting-state functional magnetic resonance imaging (fMRI) assessed regional CVR changes, while voxel-based morphometry (VBM) analyzed GMD differences. The study further explored the correlation between CVR and GMD alterations with clinical scores in CADASIL patients. Finally, receiver operating characteristic (ROC) curve analysis, including the area under curve (AUC) calculation, determined the diagnostic accuracy of CVR and morphological indices for CADASIL.</div></div><div><h3>Results</h3><div>Compared to controls, CADASIL patients exhibited significantly lower CVR in the left substantia nigra and higher CVR in the bilateral proximal anterior cerebral artery (ACA). VBM revealed reduced GMD in bilateral thalamic subregions in CADASIL patients, significantly correlating with several clinical measures. CVR indicators demonstrated superior diagnostic accuracy for CADASIL (AUC = 0.853) compared to GMD (AUC = 0.654).</div></div><div><h3>Conclusion</h3><div>The significant changes in CVR indices observed in CADASIL patients suggest that these indices may serve as potential biomarkers for CADASIL diagnosis.</div></div>","PeriodicalId":18165,"journal":{"name":"Magnetic resonance imaging","volume":"122 ","pages":"Article 110402"},"PeriodicalIF":2.1,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144120099","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Imaging of the renal allograft vasculature without gadolinium contrast: Intraindividual comparison between relaxation-enhanced angiography without contrast and triggering (REACT) and 4D contrast-enhanced MR-angiography.","authors":"Carsten Gietzen, Juliana Tristram, Jan Paul Janssen, Marielle Hummels, Johannes Bremm, Kenan Kaya, Thorsten Gietzen, Henry Pennig, Roman Gertz, Thorsten Persigehl, Dirk Stippel, Kilian Weiss, Lenhard Pennig","doi":"10.1016/j.mri.2025.110423","DOIUrl":"https://doi.org/10.1016/j.mri.2025.110423","url":null,"abstract":"<p><strong>Background: </strong>Complications after kidney transplantation include transplant renal artery stenosis (TRAS), which can be assessed using Doppler ultrasonography, computed tomography angiography, and magnetic resonance angiography (MRA). Contrast-enhanced MRA (CE-MRA) has limitations, including potential allergic reactions, limited use in kidney failure, and uncertain long-term effects of gadolinium retention.</p><p><strong>Purpose: </strong>To evaluate Relaxation-Enhanced Angiography without Contrast and Triggering (REACT), a novel 3D isotropic flow-independent non-CE-MRA pulse sequence, for imaging of the renal allograft vasculature by performing an intraindividual comparison to 4D CE-MRA at 3Tesla.</p><p><strong>Methods: </strong>Forty studies of 39 patients were included in this retrospective, single-centre study. Two board-certified radiologists independently evaluated MRA datasets for TRAS and rated their diagnostic confidence and the image quality of pelvic vessels using 5-point Likert scales (5 = excellent). Apparent signal- and contrast-to-noise ratios (aSNR/aCNR) were measured for arterial and venous graft vessels.</p><p><strong>Results: </strong>REACT (median acquisition time 04:33 min [IQR 3:58-5:20 min]) showed 90.0 % sensitivity and 100.0 % specificity for TRAS in almost perfect agreement (r = 0.97) with 4D CE-MRA (03:41 min [3:38-4:46 min], p = 0.001) and similar diagnostic confidence (REACT: 4.0 [4.0-4.0] vs. 4D CE-MRA: 4.0 [3.0-4.0], p = 0.54). Arterial image quality was comparable (4.0 [3.7-4.4] vs. 4.0 [4.0-4.4], p = 0.49) whereas veins yielded higher scores in REACT (3.2 [3.0-3.5] vs. 2.4 [2.0-3.0], p < 0.001). Transplant renal artery (mean ± SD; 44.5 ± 18.2 vs. 45.9 ± 21.0, p = 0.71; 36.3 ± 15.0 vs. 41.0 ± 20.0, p = 0.16) and vein (37.1 ± 19.8 vs. 30.3 ± 15.2, p = 0.06; 29.4 ± 17.1 vs. 25.0 ± 14.7, p = 0.17) showed no difference in aSNR and aCNR.</p><p><strong>Conclusion: </strong>REACT provides accurate detection of TRAS with image quality comparable to 4D CE-MRA, offering a risk-free alternative for imaging after renal transplantation.</p>","PeriodicalId":18165,"journal":{"name":"Magnetic resonance imaging","volume":" ","pages":"110423"},"PeriodicalIF":2.1,"publicationDate":"2025-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144111236","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluation of synthetic images derived from a neural network in pediatric brain magnetic resonance imaging","authors":"Usha D. Nagaraj ,&nbsp;Jakob Meineke ,&nbsp;Aakanksha Sriwastwa ,&nbsp;Jean A. Tkach ,&nbsp;James L. Leach ,&nbsp;Mariya Doneva","doi":"10.1016/j.mri.2025.110427","DOIUrl":"10.1016/j.mri.2025.110427","url":null,"abstract":"<div><div>Synthetic MRI (SyMRI) is a technique used to estimate tissue properties and generate multiple MR sequence contrasts from a single acquisition. However, image quality can be suboptimal.</div></div><div><h3>Purpose</h3><div>To evaluate a neural network approach using artificial intelligence-based direct contrast synthesis (AI-DCS) of the multi-contrast weighted images to improve image quality.</div></div><div><h3>Materials and methods</h3><div>This prospective, IRB approved study enrolled 50 pediatric patients undergoing clinical brain MRI. In addition to the standard of care (SOC) clinical protocol, 2D multi-delay multi-echo (MDME) sequence was obtained. SOC 3D T1-weighted (T1W), 2D T2-weighted (T2W) and 2D T2W fluid-attenuated inversion recovery (FLAIR) images from 35 patients were used to train a neural network generating synthetic T1W, T2W, and FLAIR images. Quantitative analysis of grey matter (GM) and white matter (WM) apparent signal to noise (aSNR) and grey-white matter (GWM) apparent contrast to noise (aCNR) ratios was performed.</div></div><div><h3>Results</h3><div>8 patients were evaluated. When compared to SyMRI, T1W AI-DCS had better overall image quality, reduced noise/artifacts, and better subjective SNR in 100 % (16/16) of evaluations. When compared to SyMRI, T2W AI-DCS overall image quality and diagnostic confidence was better in 93.8 % (15/16) and 87.5 % (14/16) of evaluations, respectively. When compared to SyMRI, FLAIR AI-DCS was better in 93.8 % (15/16) of evaluations in overall image quality and in 100 % (16/16) of evaluations for noise/artifacts and subjective SNR. Quantitative analysis revealed higher WM aSNR compared with SyMRI (<em>p</em> &lt; 0.05) for T1W, T2W and FLAIR.</div></div><div><h3>Conclusion</h3><div>AI-DCS demonstrates better overall image quality than SyMRI on T1W, T2W and FLAIR.</div></div>","PeriodicalId":18165,"journal":{"name":"Magnetic resonance imaging","volume":"121 ","pages":"Article 110427"},"PeriodicalIF":2.1,"publicationDate":"2025-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144102219","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}