Evaluating age-and gender-related changes in brain volumes in normal adult using synthetic magnetic resonance imaging.

OBJECTIVE: Normal aging is associated with brain volume change, and brain segmentation can be performed within an acceptable scan time using synthetic magnetic resonance imaging (MRI). This study aimed to investigate the brain volume changes in healthy adult according to age and gender, and provide age- and gender-specific reference values using synthetic MRI. METHODS: A total of 300 healthy adults (141 males, median age 48; 159 females, median age 50) were underwent synthetic MRI on 3.0 T. Brain parenchymal volume (BPV), gray matter volume (GMV), white matter volume (WMV), myelin volume (MYV), and cerebrospinal fluid volume (CSFV) were calculated using synthetic MRI software. These volumes were normalized by intracranial volume to normalized GMV (nGMV), normalized WMV (nWMV), normalized MYV (nMYV), normalized BPV (nBPV), and normalized CSFV (nCSFV). The normalized brain volumes were plotted against age in both males and females, and a curve fitting model that best explained the age dependence of brain volume was identified. The normalized brain volumes were compared between different age and gender groups. RESULTS: The approximate curves of nGMV, nWMV, nCSFV, nBPV, and nMYV were best fitted by quadratic curves. The nBPV decreased monotonously through all ages in both males and females, while the changes of nCSFV showed the opposite trend. The nWMV and nMYV in both males and females increased gradually and then decrease with age. In early adulthood (20s), nWMV and nMYV in males were lower and peaked later than that in females (p < .005). The nGMV in both males and females decreased in the early adulthood until the 30s and then remains stable. A significant decline in nWMV, nBPV, and nMYV was noted in the 60s (Turkey test, p < .05). CONCLUSIONS: Our study provides age- and gender-specific reference values of brain volumes using synthetic MRI, which could be objective tools for discriminating brain disorders from healthy brains.

The value of synthetic MRI in detecting the brain changes and hearing impairment of children with sensorineural hearing loss.

Introduction: Sensorineural hearing loss (SNHL) can arise from a diverse range of congenital and acquired factors. Detecting it early is pivotal for nurturing speech, language, and cognitive development in children with SNHL. In our study, we utilized synthetic magnetic resonance imaging (SyMRI) to assess alterations in both gray and white matter within the brains of children affected by SNHL. Methods: The study encompassed both children diagnosed with SNHL and a control group of children with normal hearing {1.5-month-olds (n = 52) and 3-month-olds (n = 78)}. Participants were categorized based on their auditory brainstem response (ABR) threshold, delineated into normal, mild, moderate, and severe subgroups.Clinical parameters were included and assessed the correlation with SNHL. Quantitative analysis of brain morphology was conducted using SyMRI scans, yielding data on brain segmentation and relaxation time.Through both univariate and multivariate analyses, independent factors predictive of SNHL were identified. The efficacy of the prediction model was evaluated using receiver operating characteristic (ROC) curves, with visualization facilitated through the utilization of a nomogram. It's important to note that due to the constraints of our research, we worked with a relatively small sample size. Results: Neonatal hyperbilirubinemia (NH) and children with inner ear malformation (IEM) were associated with the onset of SNHL both at 1.5 and 3-month groups. At 3-month group, the moderate and severe subgroups exhibited elevated quantitative T1 values in the inferior colliculus (IC), lateral lemniscus (LL), and middle cerebellar peduncle (MCP) compared to the normal group. Additionally, WMV, WMF, MYF, and MYV were significantly reduced relative to the normal group. Additionally, SNHL-children with IEM had high T1 values in IC, and LL and reduced WMV, WMF, MYV and MYF values as compared with SNHL-children without IEM at 3-month group. LL-T1 and WMF were independent risk factors associated with SNHL. Consequently, a prediction model was devised based on LL-T1 and WMF. ROC for training set, validation set and external set were 0.865, 0.806, and 0.736, respectively. Conclusion: The integration of T1 quantitative values and brain volume segmentation offers a valuable tool for tracking brain development in children affected by SNHL and assessing the progression of the condition's severity.

Radiomics Analysis of Quantitative Maps from Synthetic MRI for Predicting Grades and Molecular Subtypes of Diffuse Gliomas.

PURPOSE: To investigate the feasibility of using radiomics analysis of quantitative maps from synthetic MRI to preoperatively predict diffuse glioma grades, isocitrate dehydrogenase (IDH) subtypes, and 1p/19q codeletion status. METHODS: Data from 124 patients with diffuse glioma were used for analysis (n = 87 for training, n = 37 for testing). Quantitative T1, T2, and proton density (PD) maps were obtained using synthetic MRI. Enhancing tumour (ET), non-enhancing tumour and necrosis (NET), and peritumoral edema (PE) regions were segmented followed by manual fine-tuning. Features were extracted using PyRadiomics and then selected using Levene/T, BorutaShap and maximum relevance minimum redundancy algorithms. A support vector machine was adopted for classification. Receiver operating characteristic curve analysis and integrated discrimination improvement analysis were implemented to compare the performance of different radiomics models. RESULTS: Radiomics models constructed using features from multiple tumour subregions (ET + NET + PE) in the combined maps (T1 + T2 + PD) achieved the highest AUC in all three prediction tasks, among which the AUC for differentiating lower-grade and high-grade diffuse gliomas, predicting IDH mutation status and predicting 1p/19q codeletion status were 0.92, 0.95 and 0.86 respectively. Compared with those constructed on individual T1, T2, and PD maps, the discriminant ability of radiomics models constructed on the combined maps separately increased by 11, 17 and 10% in predicting glioma grades, 35, 52 and 19% in predicting IDH mutation status, and 16, 15 and 14% in predicting 1p/19q codeletion status (p < 0.05). CONCLUSION: Radiomics analysis of quantitative maps from synthetic MRI provides a new quantitative imaging tool for the preoperative prediction of grades and molecular subtypes in diffuse gliomas.

Multiparametric approach with synthetic MR imaging for diagnosing salivary gland lesions.

PURPOSE: To determine whether synthetic MR imaging can distinguish between benign and malignant salivary gland lesions. METHODS: The study population included 44 patients with 33 benign and 11 malignant salivary gland lesions. All MR imaging was obtained using a 3 Tesla system. The QRAPMASTER pulse sequence was used to acquire images with four TI values and two TE values, from which quantitative images of T1 and T2 relaxation times and proton density (PD) were generated. The Mann-Whitney U test was used to compare T1, T2, PD, and ADC values among the subtypes of salivary gland lesions. ROC analysis was used to evaluate diagnostic capability between malignant tumors (MTs) and either pleomorphic adenomas (PAs) or Warthin tumors (WTs). We further calculated diagnostic accuracy for distinguishing malignant from benign lesions when combining these parameters. RESULTS: PAs demonstrated significantly higher T1, T2, PD, and ADC values than WTs (all p < 0.001). Compared to MTs, PAs had significantly higher T1, T2, and ADC values (all p < 0.001), whereas WTs had significantly lower T1, T2, and PD values (p < 0.001, p = 0.008, and p = 0.003, respectively). T2 and ADC were most effective in differentiating between MTs and PAs (AUC = 0.928 and 0.939, respectively), and T1 and PD values for differentiating between MTs and WTs (AUC = 0.915 and 0.833, respectively). Combining T1 with T2 or ADC achieved accuracy of 86.4% in distinguishing between malignant and benign tumors. Similarly, combining PD with T2 or ADC reached accuracy of 86.4% for differentiating between malignant and benign tumors. CONCLUSIONS: Utilizing a combination of synthetic MRI parameters may assist in differentiating malignant from benign salivary gland lesions.

Association of serum glial fibrillary acidic protein with progression independent of relapse activity in multiple sclerosis.

OBJECTIVE: Insidious disability worsening is a common feature in relapsing-remitting multiple sclerosis (RRMS). Many patients experience progression independent of relapse activity (PIRA) despite being treated with high efficacy disease-modifying therapies. We prospectively investigated associations of body-fluid and imaging biomarkers with PIRA. METHODS: Patients with early RRMS (n = 104) were prospectively included and followed up for 60 months. All patients were newly diagnosed and previously untreated. PIRA was defined using a composite score including the expanded disability status scale, 9-hole peg test, timed 25 foot walk test, and the symbol digit modalities test. Eleven body fluid and imaging biomarkers were determined at baseline and levels of serum neurofilament light (sNfL) and glial fibrillary acidic protein (sGFAP) were also measured annually thereafter. Association of baseline biomarkers with PIRA was investigated in multivariable logistic regression models adjusting for clinical and demographic confounding factors. Longitudinal serum biomarker dynamics were investigated in mixed effects models. RESULTS: Only sGFAP was significantly higher in PIRA at baseline (median [IQR] 73.9 [60.9-110.1] vs. 60.3 [45.2-79.9], p = 0.01). A cut-off of sGFAP > 65 pg/mL resulted in a sensitivity of 68% and specificity of 61%, to detect patients at higher risk of PIRA. In a multivariable logistic regression, sGFAP > 65 pg/mL was associated with higher odds of developing PIRA (odds ratio 4.3, 95% CI 1.44-12.86, p = 0.009). Repeated measures of sGFAP levels showed that patients with PIRA during follow-up had higher levels of sGFAP along the whole follow-up compared to stable patients (p < 0.001). CONCLUSION: Determination of sGFAP at baseline and follow-up may be useful in capturing disability accrual independent of relapse activity in early RRMS.

Histogram analysis of MR quantitative parameters: are they correlated with prognostic factors in prostate cancer?

PURPOSE: To investigate the correlation between quantitative MR parameters and prognostic factors in prostate cancer (PCa). METHOD: A total of 186 patients with pathologically confirmed PCa who underwent preoperative multiparametric MRI (mpMRI), including synthetic MRI (SyMRI), were enrolled from two medical centers. The histogram metrics of SyMRI [T1, T2, proton density (PD)] and apparent diffusion coefficient (ADC) values were extracted. The Mann‒Whitney U test or Student's t test was employed to determine the association between these histogram features and the prognostically relevant factors. Receiver operating characteristic (ROC) curve analysis was conducted to evaluate the differentiation performance. Spearman's rank correlation coefficients were calculated to determine the correlations between histogram parameters and the International Society of Urological Pathology (ISUP) grade group as well as pathological T stage. RESULTS: Significant correlations were found between the histogram parameters and the ISUP grade as well as pathological T stage of PCa. Among these histogram parameters, ADC_minimum had the strongest correlation with the ISUP grade (r = - 0.481, p < 0.001), and ADC_Median showed the strongest association with pathological T stage (r = - 0.285, p = 0.008). The ADC_10th percentile exhibited the highest performance in identifying clinically significant prostate cancer (csPCa) (AUC 0.833; 95% CI 0.771-0.883). When discriminating between the status of different prognostically relevant factors, a significant difference was observed between extraprostatic extension-positive and -negative cancers with regard to histogram parameters of the ADC map (10th percentile, 90th percentile, mean, median, minimum) and T1 map (minimum) (p = 0.002-0.032). Moreover, histogram parameters of the ADC map (90th percentile, maximum, mean, median), T2 map (10th percentile, median), and PD map (10th percentile, median) were significantly lower in PCa with perineural invasion (p = 0.009-0.049). The T2 values were significantly lower in patients with seminal vesicle invasion (minimum, p = 0.036) and positive surgical margin (10th percentile, 90th percentile, mean, median, and minimum, p = 0.015-0.025). CONCLUSION: Quantitative histogram parameters derived from synthetic MRI and ADC maps may have great potential for predicting the prognostic features of PCa.

Assessment of brain structure and volume reveals neurodevelopmental abnormalities in preterm infants with low-grade intraventricular hemorrhage.

There is increasing evidence of abnormal neurodevelopmental outcomes in preterm infants with low-grade intraventricular hemorrhage (IVH). The purpose of the study was to explore whether brain microstructure and volume are associated with neuro-behavioral outcomes at 40 weeks corrected gestational age in preterm infants with low-grade IVH. MR imaging at term-equivalent age (TEA) was performed in 25 preterm infants with mild IVH (Papile grading I/II) and 40 control subjects without IVH. These subjects all had neonatal behavioral neurological assessment (NBNA) at 40 weeks' corrected age. Microstructure and volume evaluation of the brain were performed by using diffusion kurtosis imaging (DKI) and Synthetic MRI. Correlations among microstructure parameters, volume, and developmental outcomes were explored by using Spearman's correlation. In preterm infants with low-grade IVH, the volume of brain parenchymal fraction (BPF) was reduced. In addition, mean kurtosis (MK), fractional anisotropy (FA), radial kurtosis (RK), axial kurtosis (AK) in several major brain regions were reduced, while mean diffusivity (MD) was increased (P < 0.05). BPF, RK in the cerebellum, MK in the genu of the corpus callosum, and MK in the thalamus of preterm infants with low-grade IVH were associated with lower NBNA scores (r = 0.831, 0.836, 0.728, 0.772, P < 0.05). DKI and Synthetic MRI can quantitatively evaluate the microstructure alterations and brain volumes in preterm infants with low-grade IVH, which provides clinicians with a more comprehensive and accurate neurobehavioral assessment of preterm infants with low-grade IVH.

Whole-tumor histogram analysis of synthetic magnetic resonance imaging predicts isocitrate dehydrogenase mutation status in gliomas.

Background: An accurate assessment of isocitrate dehydrogenase (IDH) status in patients with glioma is crucial for treatment planning and is a key factor in predicting patient outcomes. In this study, we investigated the potential value of whole-tumor histogram metrics derived from synthetic magnetic resonance imaging (MRI) in distinguishing IDH mutation status between astrocytoma and glioblastoma. Methods: In this prospective study, 80 glioma patients were enrolled from September 2019 to June 2022. All patients underwent pre- and post-contrast synthetic MRI scan protocol. Immunohistochemistry (IHC) staining or gene sequencing were used to assess IDH mutation status in tumor tissue samples. Whole-tumor histogram metrics, including T1, T2, proton density (PD), etc., were extracted from the quantitative maps, while radiological features were assessed by synthetic contrast-weighted maps. Basic clinical features of the patients were also evaluated. Differences in clinical, radiological, and histogram metrics between IDH-mutant astrocytoma and IDH-wildtype glioblastoma were analyzed using univariate analyses. Variables with statistical significance in univariate analysis were included in multivariate logistic regression analysis to develop the combined model. Receiver operating characteristic (ROC) and area under the curve (AUC) were used to assess the diagnostic performance of metrics and models. Results: The histopathologic analysis revealed that of the 80 cases, 41 were classified as IDH-mutant astrocytoma and 39 as IDH-wildtype glioblastoma. Compared to IDH-wildtype glioblastoma, IDH-mutant astrocytoma showed significantly lower T1 [10th percentile (10th), mean, and median] and post-contrast PD (10th, 90th percentile, mean, median, and maximum) values as well as higher post-contrast T1 (cT1) (10th, mean, median, and minimum) values (all P<0.05). The combined model (T1-10th + cT1-10th + age) was developed by integrating the independent influencing factors of IDH-mutant astrocytoma using the multivariate logistic regression. The diagnostic performance of this model [AUC =0.872 (0.778-0.936), sensitivity =75.61%, and specificity =89.74%] was superior to the clinicoradiological model, which was constructed using age and enhancement degree (AUC =0.822 (0.870-0.898), P=0.035). Conclusions: The combined model constructed using histogram metrics derived from synthetic MRI could be a valuable preoperative tool to distinguish IDH mutation status between astrocytoma and glioblastoma, and subsequently, could assist in the decision-making process of pretreatment.

Generative Adversarial Networks for Brain MRI Synthesis: Impact of Training Set Size on Clinical Application.

We evaluated the impact of training set size on generative adversarial networks (GANs) to synthesize brain MRI sequences. We compared three sets of GANs trained to generate pre-contrast T1 (gT1) from post-contrast T1 and FLAIR (gFLAIR) from T2. The baseline models were trained on 135 cases; for this study, we used the same model architecture but a larger cohort of 1251 cases and two stopping rules, an early checkpoint (early models) and one after 50 epochs (late models). We tested all models on an independent dataset of 485 newly diagnosed gliomas. We compared the generated MRIs with the original ones using the structural similarity index (SSI) and mean squared error (MSE). We simulated scenarios where either the original T1, FLAIR, or both were missing and used their synthesized version as inputs for a segmentation model with the original post-contrast T1 and T2. We compared the segmentations using the dice similarity coefficient (DSC) for the contrast-enhancing area, non-enhancing area, and the whole lesion. For the baseline, early, and late models on the test set, for the gT1, median SSI was .957, .918, and .947; median MSE was .006, .014, and .008. For the gFLAIR, median SSI was .924, .908, and .915; median MSE was .016, .016, and .019. The range DSC was .625-.955, .420-.952, and .610-.954. Overall, GANs trained on a relatively small cohort performed similarly to those trained on a cohort ten times larger, making them a viable option for rare diseases or institutions with limited resources.

Age-stratified Assessment of Brain Volumetric Segmentation on the Indian Population Using Quantitative Magnetic Resonance Imaging.

BACKGROUND AND PURPOSE: Automated methods for quantifying brain tissue volumes have gained clinical interest for their objective assessment of neurological diseases. This study aimed to establish reference curves for brain volumes and fractions in the Indian population using Synthetic MRI (SyMRI), a quantitative imaging technique providing multiple contrast-weighted images through fast postprocessing. METHODS: The study included a cohort of 314 healthy individuals aged 15-65 years from multiple hospitals/centers across India. The SyMRI-quantified brain volumes and fractions, including brain parenchymal fraction (BPF), gray matter fraction (GMF), white matter fraction (WMF), and myelin. RESULTS: Normative age-stratified quantification curves were created based on the obtained data. The results showed significant differences in brain volumes between the sexes, but not after normalization by intracranial volume. CONCLUSION: The findings provide normative data for the Indian population and can be used for comparative analysis of brain structure values. Furthermore, our data indicate that the use of fractions rather than absolute volumes in normative curves, such as BPF, GMF, and WMF, can mitigate sex and population differences as they account for individual differences in head size or brain volume.

Comparison of diagnostic performance of radiologist- and AI-based assessments of T2-FLAIR mismatch sign and quantitative assessment using synthetic MRI in the differential diagnosis between astrocytoma, IDH-mutant and oligodendroglioma, IDH-mutant and 1p/19q-codeleted.

PURPOSE: This study aimed to compare assessments by radiologists, artificial intelligence (AI), and quantitative measurement using synthetic MRI (SyMRI) for differential diagnosis between astrocytoma, IDH-mutant and oligodendroglioma, and IDH-mutant and 1p/19q-codeleted and to identify the superior method. METHODS: Thirty-three cases (men, 14; women, 19) comprising 19 astrocytomas and 14 oligodendrogliomas were evaluated. Four radiologists independently evaluated the presence of the T2-FLAIR mismatch sign. A 3D convolutional neural network (CNN) model was trained using 50 patients outside the test group (28 astrocytomas and 22 oligodendrogliomas) and transferred to evaluate the T2-FLAIR mismatch lesions in the test group. If the CNN labeled more than 50% of the T2-prolonged lesion area, the result was considered positive. The T1/T2-relaxation times and proton density (PD) derived from SyMRI were measured in both gliomas. Each quantitative parameter (T1, T2, and PD) was compared between gliomas using the Mann-Whitney U-test. Receiver-operating characteristic analysis was used to evaluate the diagnostic performance. RESULTS: The mean sensitivity, specificity, and area under the curve (AUC) of radiologists vs. AI were 76.3% vs. 94.7%; 100% vs. 92.9%; and 0.880 vs. 0.938, respectively. The two types of diffuse gliomas could be differentiated using a cutoff value of 2290/128 ms for a combined 90th percentile of T1 and 10th percentile of T2 relaxation times with 94.4/100% sensitivity/specificity with an AUC of 0.981. CONCLUSION: Compared to the radiologists' assessment using the T2-FLAIR mismatch sign, the AI and the SyMRI assessments increased both sensitivity and objectivity, resulting in improved diagnostic performance in differentiating gliomas.

Whole-tumor histogram models based on quantitative maps from synthetic MRI for predicting axillary lymph node status in invasive ductal breast cancer.

PURPOSE: To investigate the potential of using histogram analysis of synthetic MRI (SyMRI) images before and after contrast enhancement to predict axillary lymph node (ALN) status in patients with invasive ductal carcinoma (IDC). METHODS: From January 2022 to October 2022, a total of 212 patients with IDC underwent breast MRI examination including SyMRI. Standard T2 weight images, DCE-MRI and quantitative maps of SyMRI were obtained. 13 features of the entire tumor were extracted from these quantitative maps, standard T2 weight images and DCE-MRI. Statistical analyses, including Student's t-test, Mann-Whiney U test, logistic regression, and receiver operating characteristic (ROC) curves, were used to evaluate the data. The mean values of SyMRI quantitative parameters derived from the conventional 2D region of interest (ROI) were also evaluated. RESULTS: The combined model based on T1-Gd quantitative map (energy, minimum, and variance) and clinical features (age and multifocality) achieved the best diagnostic performance in the prediction of ALN between N0 (with non-metastatic ALN) and N+ group (metastatic ALN ≥ 1) with the AUC of 0.879. Among individual quantitative maps and standard sequence-derived models, the synthetic T1-Gd model showed the best performance for the prediction of ALN between N0 and N+ groups (AUC = 0.823). Synthetic T2_entropy and PD-Gd_energy were useful for distinguishing N1 group (metastatic ALN ≥ 1 and ≤ 3) from the N2-3 group (metastatic ALN > 3) with an AUC of 0.722. CONCLUSIONS: Whole-tumor histogram features derived from quantitative parameters of SyMRI can serve as a complementary noninvasive method for preoperatively predicting ALN metastases.

Correcting synthetic MRI contrast-weighted images using deep learning.

Synthetic magnetic resonance imaging (MRI) offers a scanning paradigm where a fast multi-contrast sequence can be used to estimate underlying quantitative tissue parameter maps, which are then used to synthesize any desirable clinical contrast by retrospectively changing scan parameters in silico. Two benefits of this approach are the reduced exam time and the ability to generate arbitrary contrasts offline. However, synthetically generated contrasts are known to deviate from the contrast of experimental scans. The reason for contrast mismatch is the necessary exclusion of some unmodeled physical effects such as partial voluming, diffusion, flow, susceptibility, magnetization transfer, and more. The inclusion of these effects in signal encoding would improve the synthetic images, but would make the quantitative imaging protocol impractical due to long scan times. Therefore, in this work, we propose a novel deep learning approach that generates a multiplicative correction term to capture unmodeled effects and correct the synthetic contrast images to better match experimental contrasts for arbitrary scan parameters. The physics inspired deep learning model implicitly accounts for some unmodeled physical effects occurring during the scan. As a proof of principle, we validate our approach on synthesizing arbitrary inversion recovery fast spin-echo scans using a commercially available 2D multi-contrast sequence. We observe that the proposed correction visually and numerically reduces the mismatch with experimentally collected contrasts compared to conventional synthetic MRI. Finally, we show results of a preliminary reader study and find that the proposed method statistically significantly improves in contrast and SNR as compared to synthetic MR images.

Pushing MP2RAGE boundaries: Ultimate time-efficient parameterization combined with exhaustive T1 synthetic contrasts.

PURPOSE: MP2RAGE parameter optimization is redefined to allow more time-efficient MR acquisitions, whereas the T1 -based synthetic imaging framework is used to obtain on-demand T1 -weighted contrasts. Our aim was to validate this concept on healthy volunteers and patients with multiple sclerosis, using plug-and-play parallel-transmission brain imaging at 7 T. METHODS: A "time-efficient" MP2RAGE sequence was designed with optimized parameters including TI and TR set as small as possible. Extended phase graph formalism was used to set flip-angle values to maximize the gray-to-white-matter contrast-to-noise ratio (CNR). Several synthetic contrasts (UNI, EDGE, FGATIR, FLAWSMIN , FLAWSHCO ) were generated online based on the acquired T1 maps. Experimental validation was performed on 4 healthy volunteers at various spatial resolutions. Clinical applicability was evaluated on 6 patients with multiple sclerosis, scanned with both time-efficient and conventional MP2RAGE parameterizations. RESULTS: The proposed time-efficient MP2RAGE protocols reduced acquisition time by 40%, 30%, and 19% for brain imaging at (1 mm)3 , (0.80 mm)3 and (0.65 mm)3 , respectively, when compared with conventional parameterizations. They also provided all synthetic contrasts and comparable contrast-to-noise ratio on UNI images. The flexibility in parameter selection allowed us to obtain a whole-brain (0.45 mm)3 acquisition in 19 min 56 s. On patients with multiple sclerosis, a (0.67 mm)3 time-efficient acquisition enhanced cortical lesion visualization compared with a conventional (0.80 mm)3 protocol, while decreasing the scan time by 15%. CONCLUSION: The proposed optimization, associated with T1 -based synthetic contrasts, enabled substantial decrease of the acquisition time or higher spatial resolution scans for a given time budget, while generating all typical brain contrasts derived from MP2RAGE.

CT-based generation of synthetic-pseudo MR images with different weightings for human knee.

Synthetic MR images are generated for their high soft-tissue contrast avoiding the discomfort by the long acquisition time and placing claustrophobic patients in the MR scanner's confined space. The aim of this study is to generate synthetic pseudo-MR images from a real CT image for the knee region in vivo. 19 healthy subjects were scanned for model training, while 13 other healthy subjects were imaged for testing. The approach used in this work is novel such that the registration was performed between the MR and CT images, and the femur bone, patella, and the surrounding soft tissue were segmented on the CT image. The tissue type was mapped to its corresponding mean and standard deviation values of the CT# of a window moving on each pixel in the reconstructed CT images, which enabled the remapping of the tissue to its MRI intrinsic parameters: T1, T2, and proton density (ρ). To generate the synthetic MR image of a knee slice, a classic spin-echo sequence was simulated using proper intrinsic and contrast parameters. Results showed that the synthetic MR images were comparable to the real images acquired with the same TE and TR values, and the average slope between them (for all knee segments) was 0.98, while the average percentage root mean square difference (PRD) was 25.7%. In conclusion, this study has shown the feasibility and validity of accurately generating synthetic MR images of the knee region in vivo with different weightings from a single real CT image.

Synthetic MRI to Assess Neurological Injury in Recovered COVID-19 Patients / 中山大学学报(医学科学版)

ObjectiveTo assess the microstructural involvement of gray matter in recovered COVID-19 patients using Synthetic MRI. MethodsThis study was conducted in 29 recovered COVID-19 patients， including severe group （SG， n=11） and ordinary group （OG， n=18）. Healthy volunteers matched by age， sex， BMI and years of education were selected as a healthy control group （HC=23 cases）. Each subject underwent synthetic MRI to generate quantitative T1 and T2 maps， and the T1 and T2 maps were segmented into 90 regions of interest （ROIs） using automatic anatomical labeling （AAL） mapping. T1 and T2 values for each ROI were obtained by averaging all voxels within the ROIs. The T1 and T2 values of the 90 brain regions between the three groups were compared. ResultsRelative to HC， the SG had significantly higher T2 values in bilateral orbital superior frontal gyrus， bilateral parahippocampal gyrus， bilateral putamen， bilateral middle temporal gyrus， bilateral Inferior temporal gyrus， left orbital superior frontal gyrus， left orbital inferior frontal gyrus， left gyrus rectus， left anterior cingulate and paracingulate gyri， right median cingulate and paracingulate gyri， left posterior cingulate gyrus， and left supramarginal gyrus （P＜0.05）； Relative to OG， SG showed significantly increased T2 values in the left rectus gyrus， left parahippocampal gyrus， bilateral middle temporal gyrus， and bilateral inferior temporal gyrus （P＜0.05）. Relative to HC， the T1 values of SG were significantly increased in bilateral orbital superior frontal gyrus， left rectus gyrus， left anterior cingulate and paracingulate gyri， right posterior cingulate gyrus， left parahippocampal gyrus， left lingual gyrus， left putamen， left thalamus（P＜0.05）； Relative to OG， the T1 values of SG were significantly higher in the right posterior cingulate gyrus， right calcarine fissure and surrounding cortex， and left putamen （P＜0.05）. ConclusionsEven after recovering from COVID-19， patients may still have persistent or delayed damage to their brain gray matter structure， which is correlated with the severity of the condition. SyMRI can serve as a sensitive tool to assess the extent of microstructural damage to the central nervous system， aiding in early diagnosis of the disease.

Generalizable synthetic MRI with physics-informed convolutional networks.

BACKGROUND: Magnetic resonance imaging (MRI) provides state-of-the-art image quality for neuroimaging, consisting of multiple separately acquired contrasts. Synthetic MRI aims to accelerate examinations by synthesizing any desirable contrast from a single acquisition. PURPOSE: We developed a physics-informed deep learning-based method to synthesize multiple brain MRI contrasts from a single 5-min acquisition and investigate its ability to generalize to arbitrary contrasts. METHODS: A dataset of 55 subjects acquired with a clinical MRI protocol and a 5-min transient-state sequence was used. The model, based on a generative adversarial network, maps data acquired from the five-minute scan to "effective" quantitative parameter maps (q*-maps), feeding the generated PD, T1 , and T2 maps into a signal model to synthesize four clinical contrasts (proton density-weighted, T1 -weighted, T2 -weighted, and T2 -weighted fluid-attenuated inversion recovery), from which losses are computed. The synthetic contrasts are compared to an end-to-end deep learning-based method proposed by literature. The generalizability of the proposed method is investigated for five volunteers by synthesizing three contrasts unseen during training and comparing these to ground truth acquisitions via qualitative assessment and contrast-to-noise ratio (CNR) assessment. RESULTS: The physics-informed method matched the quality of the end-to-end method for the four standard contrasts, with structural similarity metrics above 0.75 ± 0.08 (±std), peak signal-to-noise ratios above 22.4 ± 1.9, representing a portion of compact lesions comparable to standard MRI. Additionally, the physics-informed method enabled contrast adjustment, and similar signal contrast and comparable CNRs to the ground truth acquisitions for three sequences unseen during model training. CONCLUSIONS: The study demonstrated the feasibility of physics-informed, deep learning-based synthetic MRI to generate high-quality contrasts and generalize to contrasts beyond the training data. This technology has the potential to accelerate neuroimaging protocols.

Quantification of myelination in children with attention-deficit/hyperactivity disorder: a comparative assessment with synthetic MRI and DTI.

Evaluation of myelin content is crucial for attention-deficit/hyperactivity disorder (ADHD). To estimate myelin content in ADHD based on synthetic MRI-based method and compare it with established diffusion tensor imaging (DTI) method. Fifth-nine ADHD and fifty typically developing (TD) children were recruited. Global and regional myelin content (myelin volume fraction [MVF] and myelin volume [MYV]) were assessed using SyMRI and compared with DTI metrics (fractional anisotropy and mean/radial/axial diffusivity). The relationship between significant MRI parameters and clinical variables were assessed in ADHD. No between-group differences of whole-brain myelin content were found. Compared to TDs, ADHD showed higher mean MVF in bilateral internal capsule, external capsule, corona radiata, and corpus callosum, as well as in left tapetum, left superior fronto-occipital fascicular, and right cingulum (all PFDR-corrected < 0.05). Increased MYV were found in similar regions. Abnormalities of DTI metrics were mainly in bilateral corticospinal tract. Besides, MVF in right retro lenticular part of internal capsule was negatively correlated with cancellation test scores (r = - 0.41, P = 0.002), and MYV in right posterior limb of internal capsule (r = 0.377, P = 0.040) and left superior corona radiata (r = 0.375, P = 0.041) were positively correlated with cancellation test scores in ADHD. Increased myelin content underscored the important pathway of frontostriatal tract, posterior thalamic radiation, and corpus callosum underlying ADHD, which reinforced the insights into myelin quantification and its potential role in pathophysiological mechanism and disease diagnosis. Prospectively registered trials number: ChiCTR2100048109; date: 2021-07.

Potential clinical feasibility of synthetic MRI in bladder tumors: a comparative study with conventional MRI.

Background: Synthetic magnetic resonance imaging (MRI) can provide quantitative information about inherent tissue properties and synthesize tailored contrast-weighted images simultaneously in a single scan. This study aimed to investigate the clinical feasibility of synthetic MRI in bladder tumors. Methods: A total of 47 patients (37 males; mean age: 66±10 years old) with postoperative pathology-confirmed papillary urothelial neoplasms of the bladder were enrolled in this retrospective study. A 2-dimensional (2D) multi-dynamic multi-echo pulse sequence was performed for synthetic MRI at 3T. The overall image quality, lesion conspicuity, contrast resolution, resolution of subtle anatomic structures, motion artifact, blurring, and graininess of images were subjectively evaluated by 2 radiologists independently using a 5-point Likert scale for qualitative analysis. The signal intensity ratio (SIR), signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were measured for quantitative analysis. Linear weighted Kappa, Wilcoxon's signed-rank test, and the Mann-Whitney U-test were used for statistical analysis. Results: The interobserver consistency was excellent (κ values: 0.607-1). Synthetic T1-weighted (syn-T1w) and synthetic T2-weighted (syn-T2w) images obtained scores of 4 in most subjective terms, which were relatively smaller than those of conventional images. The SIR and SNR of syn-T1w were significantly higher than those of con-T1w images (SIR 2.37±0.86 vs. 1.47±0.20, P<0.001; SNR 21.83±9.43 vs. 14.81±3.30, P<0.001). No difference was found in SIR between syn-T2w and conventional T2-weighted (con-T2w) images, whereas the SNR of the syn-T2w was significantly lower (8.79±4.06 vs. 26.49±6.80, P<0.001). Additionally, the CNR of synthetic images was significantly lower than that of conventional images (T1w 1.41±0.72 vs. 2.68±1.04; T2w 1.40±0.87 vs. 4.03±1.55, all P<0.001). Conclusions: Synthetic MRI generates morphologic magnetic resonance (MR) images with diagnostically acceptable image quality in bladder tumors, especially T1-weighted images with high image contrast of tumors relative to urine. Further technological improvements are needed for synthetic MRI to reduce noise. Combined with T1, T2, and proton density (PD) quantitative data, synthetic MRI has potential for clinical application in bladder tumors.

Toward deep learning replacement of gadolinium in neuro-oncology: A review of contrast-enhanced synthetic MRI.

Gadolinium-based contrast agents (GBCAs) have become a crucial part of MRI acquisitions in neuro-oncology for the detection, characterization and monitoring of brain tumors. However, contrast-enhanced (CE) acquisitions not only raise safety concerns, but also lead to patient discomfort, the need of more skilled manpower and cost increase. Recently, several proposed deep learning works intend to reduce, or even eliminate, the need of GBCAs. This study reviews the published works related to the synthesis of CE images from low-dose and/or their native -non CE- counterparts. The data, type of neural network, and number of input modalities for each method are summarized as well as the evaluation methods. Based on this analysis, we discuss the main issues that these methods need to overcome in order to become suitable for their clinical usage. We also hypothesize some future trends that research on this topic may follow.