Synthetic MRI in the Detection of Multiple Sclerosis Plaques

Zero-DeepSub: Zero-shot deep subspace reconstruction for rapid multiparametric quantitative MRI using 3D-QALAS

PURPOSE

To develop and evaluate methods for (1) reconstructing 3D-quantification using an interleaved Look-Locker acquisition sequence with T2 preparation pulse (3D-QALAS) time-series images using a low-rank subspace method, which enables accurate and rapid T1 and T2 mapping, and (2) improving the fidelity of subspace QALAS by combining scan-specific deep-learning-based reconstruction and subspace modeling.

THEORY AND METHODS

A low-rank subspace method for 3D-QALAS (i.e., subspace QALAS) and zero-shot deep-learning subspace method (i.e., Zero-DeepSub) were proposed for rapid and high fidelity T1 and T2 mapping and time-resolved imaging using 3D-QALAS. Using an ISMRM/NIST system phantom, the accuracy and reproducibility of the T1 and T2 maps estimated using the proposed methods were evaluated by comparing them with reference techniques. The reconstruction performance of the proposed subspace QALAS using Zero-DeepSub was evaluated in vivo and compared with conventional QALAS at high reduction factors of up to nine-fold.

RESULTS

Phantom experiments showed that subspace QALAS had good linearity with respect to the reference methods while reducing biases and improving precision compared to conventional QALAS, especially for T2 maps. Moreover, in vivo results demonstrated that subspace QALAS had better g-factor maps and could reduce voxel blurring, noise, and artifacts compared to conventional QALAS and showed robust performance at up to nine-fold acceleration with Zero-DeepSub, which enabled whole-brain T1, T2, and PD mapping at 1 mm isotropic resolution within 2 min of scan time.

CONCLUSION

The proposed subspace QALAS along with Zero-DeepSub enabled high fidelity and rapid whole-brain multiparametric quantification and time-resolved imaging.

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.

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 above0.75 ± 0.08 $0.75\pm 0.08$ ( ± $\pm$ std), peak signal-to-noise ratios above22.4 ± 1.9 $22.4\pm 1.9$ , 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.

Multi-contrast echo-planar imaging sequence (Echo-planar imaging mix) in clinical situations demanding faster MRI-brain scans

Objectives

The excellent resolution offered by magnetic resonance imaging (MRI) has a trade-off in the form of scan duration. The purpose of the present study was to assess the clinical utility of echo-planar imaging mix (EPIMix), an echo-planar imaging-based MRI sequence for the brain with a short acquisition time.

Materials and Methods

This was a retrospective observational study of 50 patients, who could benefit from faster MRI brain scans. The T1, T2, fluid attenuated inversion recovery, diffusion-weighted imaging (DWI), and T2*/susceptibility-weighted imaging sequences were acquired, conventionally and with EPIMix. Conventional and EPIMix images were assessed by two radiologists for overall quality, motion, and susceptibility artifacts and scored on a Likert scale. The scores given for conventional and EPIMix images were compared. The diagnostic performance of EPIMix was also assessed by the ability to detect clinically relevant findings.

Results

The acquisition time for conventional MRI was 11 min and 45 s and for EPIMix 1 min and 15 s. All EPIMix images were sufficient for diagnostic use. On assessment of the diagnostic performance, it was excellent for ischemic and hemorrhagic strokes. Smaller lesions, lesions adjacent to bone, and post-operative tumors were difficult to identify. Moderate to perfect agreement (Kappa values 0.41-1) was seen between radiologists for all categories except skull base, calvarial, and orbital lesions. Image quality, artifact assessment showed excellent interobserver agreement (>90%) for the scores. All EPIMix images showed reduced motion artifacts. The EPIMix-DWI was comparable to conventional-DWI in terms of quality and artifacts. The remaining sequences showed reduced quality and increased susceptibility.

Conclusion

The EPIMix has a significantly reduced acquisition time than conventional MRI and could be used instead of conventional MRI in situations demanding faster scans such as suspected acute ischemic or hemorrhagic stroke. In other clinical scenarios, it could help tailor the MRI examination for each patient.

Brain volume measured by synthetic magnetic resonance imaging in adult moyamoya disease correlates with cerebral blood flow and brain function

Moyamoya disease (MMD) is characterized by progressive arterial occlusion, causing chronic hemodynamic impairment, which can reduce brain volume. A novel quantitative technique, synthetic magnetic resonance imaging (SyMRI), can evaluate brain volume. This study aimed to investigate whether brain volume measured with SyMRI correlated with cerebral blood flow (CBF) and brain function in adult MMD. In this retrospective study, 18 adult patients with MMD were included. CBF was measured using iodine-123-N-isopropyl-p-iodoamphetamine single photon emission computed tomography. Cerebrovascular reactivity (CVR) to acetazolamide challenge was also evaluated. Brain function was measured using the Wechsler Adult Intelligence Scales (WAIS)-III/IV and the WAIS-R tests. Gray matter (GM), white matter, and myelin-correlated volumes were evaluated in six areas. Resting CBF was positively correlated with GM fractions in the right anterior cerebral arterial and right middle cerebral arterial (MCA) territories. CVR was positively correlated with GM fraction in the right posterior cerebral arterial (PCA) territory. Full-Scale Intelligence Quotient and Verbal Comprehension Index scores were marginally positively correlated with GM fractions in the left PCA territory. Processing Speed Index score was marginally positively correlated with GM fraction in the right MCA territory. The SyMRI-measured territorial GM fraction correlated with CBF and brain function in patients with MMD.

Deep Learning Accelerated Image Reconstruction of Fluid-Attenuated Inversion Recovery Sequence in Brain Imaging: Reduction of Acquisition Time and Improvement of Image Quality

RATIONALE AND OBJECTIVES

Fluid-attenuated inversion recovery (FLAIR) imaging is playing an increasingly significant role in the detection of brain metastases with a concomitant increase in the number of magnetic resonance imaging (MRI) examinations. Therefore, the purpose of this study was to investigate the impact on image quality and diagnostic confidence of an innovative deep learning-based accelerated FLAIR (FLAIRDLR) sequence of the brain compared to conventional (standard) FLAIR (FLAIRS) imaging.

MATERIALS AND METHODS

Seventy consecutive patients with staging cerebral MRIs were retrospectively enrolled in this single-center study. The FLAIRDLR was conducted using the same MRI acquisition parameters as the FLAIRS sequence, except for a higher acceleration factor for parallel imaging (from 2 to 4), which resulted in a shorter acquisition time of 1:39 minute instead of 2:40 minutes (-38%). Two specialized neuroradiologists evaluated the imaging datasets using a Likert scale that ranged from 1 to 4, with 4 indicating the best score for the following parameters: sharpness, lesion demarcation, artifacts, overall image quality, and diagnostic confidence. Additionally, the image preference of the readers and the interreader agreement were assessed.

RESULTS

The average age of the patients was 63 ± 11years. FLAIRDLR exhibited significantly less image noise than FLAIRS, with P-values of< .001 and< .05, respectively. The sharpness of the images and the ability to detect lesions were rated higher in FLAIRDLR, with a median score of 4 compared to a median score of 3 in FLAIRS (P-values of<.001 for both readers). In terms of overall image quality, FLAIRDLR was rated superior to FLAIRS, with a median score of 4 vs 3 (P-values of<.001 for both readers). Both readers preferred FLAIRDLR in 68/70 cases.

CONCLUSION

The feasibility of deep learning FLAIR brain imaging was shown with additional 38% reduction in examination time compared to standard FLAIR imaging. Furthermore, this technique has shown improvement in image quality, noise reduction, and lesion demarcation.

[Usefulness of Voxel-Based Quantification (VBQ) Smoothing in Relaxation Time Mapping]

PURPOSE

Voxel-based quantification (VBQ) smoothing is a technique used to smooth quantitative parametric maps in the Montreal Neurological Institute standard space. Although VBQ smoothing could suppress changes in quantitative values at tissue boundaries, its effectiveness on relaxation time (T1 and T2 values and proton density PD) maps has not been investigated. The purpose of this study was to clarify the usefulness of VBQ smoothing in relaxation time mapping.

METHOD

T1 and T2 values and PD maps of the brains of 20 healthy participants were obtained using a two-dimensional multi-dynamic multi-echo sequence. VBQ and Gaussian smoothing were applied to the relaxation time maps by varying the kernel size by 1 mm from 1 to 6 mm. Changes in relaxation time before and after VBQ and Gaussian smoothing for the putamen, caudate nucleus, substantia nigra, and corpus callosum on the relaxation time maps were evaluated.

RESULT

The changes in relaxation time after VBQ smoothing application were smaller than those in that after Gaussian smoothing application. Although the differences in the relaxation time for all tissues before and after VBQ and Gaussian smoothing applications increased with increasing kernel size for all relaxation times for both methods, the changes in the relaxation time for VBQ smoothing were smaller than those in that for Gaussian smoothing.

CONCLUSION

VBQ smoothing can suppress the change in the relaxation time on the boundary of the tissue and is thus a useful smoothing technique in relaxation time mapping.

Quantitative T1 mapping detects blood-brain barrier breakdown in apparently non-enhancing multiple sclerosis lesions

OBJECTIVES

The disruption of the blood-brain barrier (BBB) is a key and early feature in the pathogenesis of demyelinating multiple sclerosis (MS) lesions and has been neuropathologically demonstrated in both active and chronic plaques. The local overt BBB disruption in acute demyelinating lesions is captured as signal hyperintensity in post-contrast T1-weighted images because of the contrast-related shortening of the T1 relaxation time. On the contrary, the subtle BBB disruption in chronic lesions is not visible at conventional radiological evaluation but it might be of clinical relevance. Indeed, persistent, subtle BBB leakage might be linked to low-grade inflammation and plaque evolution. Here we hypothesised that 3D Quantitative Transient-state Imaging (QTI) was able to reveal and measure T1 shortening (ΔT1) reflecting small amounts of contrast media leakage in apparently non-enhancing lesions (ANELs).

MATERIALS AND METHODS

Thirty-four patients with relapsing remitting MS were included in the study. All patients underwent a 3 T MRI exam of the brain including conventional sequences and QTI acquisitions (1.1 mm isotropic voxel) performed both before and after contrast media administration. For each patient, a ΔT1 map was obtained via voxel-wise subtraction of pre- and post- contrast QTI-derived T1 maps. ΔT1 values measured in ANELs were compared with those recorded in enhancing lesions and in the normal appearing white matter. A reference distribution of ΔT1 in the white matter was obtained from datasets acquired in 10 non-MS patients with unrevealing MR imaging.

RESULTS

Mean ΔT1 in ANELs (57.45 ± 48.27 ms) was significantly lower than in enhancing lesions (297.71 ± 177.52 ms; p < 0. 0001) and higher than in the normal appearing white matter (36.57 ± 10.53 ms; p < 0.005). Fifty-two percent of ANELs exhibited ΔT1 higher than those observed in the white matter of non-MS patients.

CONCLUSIONS

QTI-derived quantitative ΔT1 mapping enabled to measure contrast-related T1 shortening in ANELs. ANELs exhibiting ΔT1 values that deviate from the reference distribution in non-MS patients may indicate persistent, subtle, BBB disruption. Access to this information may be proved useful to better characterise pathology and objectively monitor disease activity and response to therapy.

Generating Synthetic Radiological Images with PySynthMRI: An Open-Source Cross-Platform Tool

Synthetic MR Imaging allows for the reconstruction of different image contrasts from a single acquisition, reducing scan times. Commercial products that implement synthetic MRI are used in research. They rely on vendor-specific acquisitions and do not include the possibility of using custom multiparametric imaging techniques. We introduce PySynthMRI, an open-source tool with a user-friendly interface that uses a set of input images to generate synthetic images with diverse radiological contrasts by varying representative parameters of the desired target sequence, including the echo time, repetition time and inversion time(s). PySynthMRI is written in Python 3.6, and it can be executed under Linux, Windows, or MacOS as a python script or an executable. The tool is free and open source and is developed while taking into consideration the possibility of software customization by the end user. PySynthMRI generates synthetic images by calculating the pixelwise signal intensity as a function of a set of input images (e.g., T1 and T2 maps) and simulated scanner parameters chosen by the user via a graphical interface. The distribution provides a set of default synthetic contrasts, including T1w gradient echo, T2w spin echo, FLAIR and Double Inversion Recovery. The synthetic images can be exported in DICOM or NiFTI format. PySynthMRI allows for the fast synthetization of differently weighted MR images based on quantitative maps. Specialists can use the provided signal models to retrospectively generate contrasts and add custom ones. The modular architecture of the tool can be exploited to add new features without impacting the codebase.

Estimation of white matter hyperintensities with synthetic MRI myelin volume fraction in patients with multiple sclerosis and non-multiple-sclerosis white matter hyperintensities: A pilot study among the Indian population

AIM

Synthetic MRI (SyMRI) works on the MDME sequence, which acquires the relaxation properties of the brain and helps to measure the accurate tissue properties in 6 minutes. The aim of this study was to evaluate the synthetic MRI (SyMRI)-generated myelin (MyC) to white matter (WM) ratio, the WM fraction (WMF), MyC partial maps performing normative brain volumetry to investigate MyC loss in multiple sclerosis (MS) patients with white-matter hyperintensites (WMHs) and non-MS patients with WMHs in a clinical setting.

MATERIALS and METHODS

Synthetic MRI images were acquired from 15 patients with MS, and from 15 non-MS patients on a 3T MRI scanner (Discovery MR750w; GE Healthcare; Milwaukee, USA) using MAGiC, a customized version of SyntheticMR's SyMRI® IMAGE software marketed by GE Healthcare under a license agreement. Fast multi-delay multi-echo acquisition was performed with a 2D axial pulse sequence with different combinations of echo time (TEs) and saturation delay times. The total image acquisition time was 6 minutes. SyMRI image analysis was done using SyMRI software (SyMRI Version: 11.3.6; Synthetic MR, Linköping, Sweden). SyMRI data were used to generate the MyC partial maps and WMFs to quantify the signal intensities of test group and control group, andcontrol group , and their mean values were recorded. All patients also underwent conventional diffusion-weighted imaging, i.e., T1w and T2w imaging.

RESULTS

The results showed that the WMF was significantly lower in the test group than in the control group (38.8% vs 33.2%, p < 0.001). The Mann-Whitney U nonparametric t-test revealed a significant difference in the mean myelin volume between the test group and the control group (158.66 ± 32.31 vs. 138.29 ± 29.28, p = 0.044). Also, there were no significant differences in the gray matter fraction and intracranial volume between the test group and the control group.

CONCLUSIONS

We observed MyC loss in test group using quantitative SyMRI. Thus, myelin loss in MS patients can be quantitatively evaluated using SyMRI.

[Evaluation of the Accuracy of Relaxation Time Measurements Using 3D-QALAS at 3.0 T MRI and Comparison with 2D-MDME]

PURPOSE

Three-dimensional (3D) quantification using an interleaved Look-Locker acquisition sequence with a T₂ preparation pulse (QALAS) is a quantitative sequence used to measure relaxation times. The accuracy of the relaxation time measurement of 3D-QALAS at 3.0 T and the bias of 3D-QALAS have not yet been assessed. The purpose of this study was to clarify the accuracy of the relaxation time measurements using 3D-QALAS at 3.0 T MRI.

METHODS

The accuracy of the T₁ and T₂ values for 3D-QALAS was evaluated using a phantom. Subsequently, the T₁ and T₂ values and proton density of the brain parenchyma in healthy subjects were measured using 3D-QALAS and compared with those of 2D multi-dynamic multi-echo (MDME).

RESULTS

In the phantom study, the average T₁ value of 3D-QALAS was 8.3% prolonged than that for conventional inversion recovery spin-echo; the average T₂ value for 3D-QALAS was 18.4% shorter than that for multi-echo spin-echo. The in vivo assessment showed that the mean T₁ and T₂ values and PD for 3D-QALAS were prolonged by 5.3%, shortened by 9.6%, and increased by 7.0%, respectively, compared with those for 2D-MDME.

CONCLUSION

Although 3D-QALAS at 3.0 T has high accuracy T₁ value, which is less than 1000 ms, the T₁ value could be overestimated for tissues with it longer than that T₁ value. The T₂ value for 3D-QALAS could be underestimated for tissues with T₂ values, and this tendency increases with longer T₂ values.

Image quality using synthetic brain MRI: an age-stratified study

BACKGROUND

Synthetic magnetic resonance imaging (MRI) might replace the conventional MR sequences in brain evaluation to shorten scan time and obtain multiple quantitative parameters.

PURPOSE

To evaluate the image quality of multiple-delay-multiple-echo (MDME) sequence-derived synthetic brain MR images compared to conventional images by considering a multi-age sample.

MATERIAL AND METHODS

Image sets of conventional and synthetic MRI of 200 participants were included. On the basis of the presence of intracranial lesions, the participants were divided into a normal group and a pathological group. Two neuroradiologists compared the anonymous and unordered images. Image quality, artifacts, and diagnostic performance were analyzed.

RESULTS

In the quantitative analysis, comparing with conventional images, MDME sequence-derived synthetic MRI demonstrated an equal/greater signal-to-noise ratio and contrast-to-noise ratio (CNR) in all age groups. Specifically, for participants aged ≤2 years, synthetic T2-fluid-attenuated inversion recovery imaging showed a significantly higher cerebellum gray/white matter CNR (P < 0.05). In the qualitative and artifact analyses, except for the superior sagittal sinus and cranial nerves, synthetic MRI showed good imaging quality (≥3 points) in all brain structures. On synthetic T1-weighted imaging, high signal intensity within the superior sagittal sinus was found in most of our participants (107/118, 90.7%). No difference was observed between synthetic and conventional MRI in diagnosing the lesions.

CONCLUSION

MDME sequence-derived synthetic MRI showed similar image quality and diagnostic performance with a shorter acquisition time than conventional MRI. However, the high signal intensity within the superior sagittal sinus on synthetic T1-weighted images requires consideration.

Current state of pediatric neuro-oncology imaging, challenges and future directions

Imaging plays a central role in neuro-oncology including primary diagnosis, treatment planning, and surveillance of tumors. The emergence of quantitative imaging and radiomics provided an uprecedented opportunity to compile mineable databases that can be utilized in a variety of applications. In this review, we aim to summarize the current state of conventional and advanced imaging techniques, standardization efforts, fast protocols, contrast and sedation in pediatric neuro-oncologic imaging, radiomics-radiogenomics, multi-omics and molecular imaging approaches. We will also address the existing challenges and discuss future directions.

Tissue Characteristics of Endometrial Carcinoma Analyzed by Quantitative Synthetic MRI and Diffusion-Weighted Imaging

BACKGROUND

This study investigates the association of T1, T2, proton density (PD) and the apparent diffusion coefficient (ADC) with histopathologic features of endometrial carcinoma (EC).

METHODS

One hundred and nine EC patients were prospectively enrolled from August 2019 to December 2020. Synthetic magnetic resonance imaging (MRI) was acquired through one acquisition, in addition to diffusion-weighted imaging (DWI) and other conventional sequences using 1.5T MRI. T1, T2, PD derived from synthetic MRI and ADC derived from DWI were compared among different histopathologic features, namely the depth of myometrial invasion (MI), tumor grade, cervical stromal invasion (CSI) and lymphovascular invasion (LVSI) of EC by the Mann-Whitney U test. Classification models based on the significant MRI metrics were constructed with their respective receiver operating characteristic (ROC) curves, and their micro-averaged ROC was used to evaluate the overall performance of these significant MRI metrics in determining aggressive histopathologic features of EC.

RESULTS

EC with MI had significantly lower T2, PD and ADC than those without MI (p = 0.007, 0.006 and 0.043, respectively). Grade 2-3 EC and EC with LVSI had significantly lower ADC than grade 1 EC and EC without LVSI, respectively (p = 0.005, p = 0.020). There were no differences in the MRI metrics in EC with or without CSI. Micro-averaged ROC of the three models had an area under the curve of 0.83.

CONCLUSIONS

Synthetic MRI provided quantitative metrics to characterize EC with one single acquisition. Low T2, PD and ADC were associated with aggressive histopathologic features of EC, offering excellent performance in determining aggressive histopathologic features of EC.

Time-saving synthetic magnetic resonance imaging protocols for pediatric neuroimaging: impact of echo train length and bandwidth on image quality

BACKGROUND

Synthetic MRI is a time-efficient imaging technique that provides both quantitative MRI and contrast-weighted images simultaneously. However, a rather long single scan time can be challenging for children.

OBJECTIVE

To evaluate the clinical feasibility of time-saving synthetic MRI protocols adjusted for echo train length and receiver bandwidth in pediatric neuroimaging based on image quality assessment and quantitative data analysis.

MATERIALS AND METHODS

In total, we included 33 children ages 1.6-17.4 years who underwent synthetic MRI using three sets of echo train length and receiver bandwidth combinations (echo train length [E]12-bandwidth [B in KHz]22, E16-B22 and E16-B83) at 3 T. The image quality and lesion conspicuity of synthetic contrast-weighted images were compared between the suggested protocol (E12-B22) and adjusted protocols (E16-B22 and E16-B83). We also compared tissue values (T1, T2, proton-density values) and brain volumetry.

RESULTS

For the E16-B83 combination, image quality was sufficient except for 15.2% of T1-W and 3% of T2-W fluid-attenuated inversion recovery (FLAIR) images, with remarkable scan time reduction (up to 35%). The E16-B22 combination demonstrated a comparable image quality to E12-B22 (P&gt;0.05) with a scan time reduction of up to 8%. There were no significant differences in lesion conspicuity among the three protocols (P&gt;0.05). Tissue value measurements and brain tissue volumes obtained with the E12-B22 protocol and adjusted protocols showed excellent agreement and strong correlations except for gray matter volume and non-white matter/gray matter/cerebrospinal fluid volume in E12-B22 vs. E16-B83.

CONCLUSION

The adjusted synthetic protocols produced image quality sufficient or comparable to that of the suggested protocol while maintaining lesion conspicuity with reduced scan time. The quantitative values were generally consistent with the suggested MRI-protocol-derived values, which supports the clinical application of adjusted protocols in pediatric neuroimaging.

Synthetic double inversion recovery imaging in brain MRI: quantitative evaluation and feasibility of synthetic MRI and a comparison with conventional double inversion recovery and fluid-attenuated inversion recovery sequences

Background and purpose

Synthetic MR imaging (SyMRI) allows the reconstruction of various contrast images, including double inversion recovery (DIR), from a single scan. This study aimed to investigate the advantages of SyMRI by comparing synthetic DIR images with synthetic T2-weighted fluid-attenuated inversion recovery (T2W-FLAIR) and conventional DIR images.

Materials and methods

We retrospectively reviewed the imaging data of 100 consecutive patients who underwent brain MRI between December 2018 and March 2019. Synthetic DIR, T2W-FLAIR, T1-weighted, and phase-sensitive inversion recovery (PSIR) images were generated from SyMRI data. For synthetic DIR, the two inversion times required to suppress white matter and cerebrospinal fluid (CSF) were manually determined by two radiologists. Quantitative analysis was performed by manually tracing the region of interest (ROI) at the sites of the lesion, white matter, and CSF. Synthetic DIR, synthetic T2W-FLAIR, and conventional DIR images were compared on the basis of using the gray matter-to-white matter, lesion-to-white matter, and lesion-to-CSF contrast-to-noise ratios.

Results

The two radiologists showed no differences in setting inversion time (TI) values, and their evaluations showed excellent interobserver agreement. The mean signal intensities obtained with synthetic DIR were significantly higher than those obtained with synthetic T2W-FLAIR and conventional DIR.

Conclusion

Synthetic DIR images showed a higher contrast than synthetic T2WFLAIR and conventional DIR images.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12880-022-00877-4.

Improving Image Quality and Reducing Scan Time for Synthetic MRI of Breast by Using Deep Learning Reconstruction

Objectives. To investigate a deep learning reconstruction algorithm to reduce the time of synthetic MRI (SynMRI) scanning on the breast and improve the image quality. Materials and Methods. A total of 192 healthy female volunteers (mean age: 48.1 years) underwent the breast MR examination at 3.0 T from September 2020 to June 2021. Standard SynMRI and fast SynMRI scans were collected simultaneously on the same volunteer. Deep learning technology with a generative adversarial network (GAN) was used to generate high-quality fast SynMRI images by end-to-end training. Peak signal-to-noise ratio (PSNR), mean squared error (MSE), and structural similarity index measure (SSIM) were used to compare the image quality of generated images from fast SynMRI by deep learning algorithms. Results. Fast SynMRI acquisition time is half of the standard SynMRI scan, and the generated images of the GAN model show that PSNR and SSIM are improved and MSE is reduced. Conclusion. The application of deep learning algorithms with GAN model in breast MAGiC MRI improves the image quality and reduces the scanning time.

Synthetic MRI for stroke: a qualitative and quantitative pilot study

Synthetic MR provides qualitative and quantitative multi-parametric data about tissue properties in a single acquisition. Its use in stroke imaging is not yet established. We compared synthetic and conventional image quality and studied synthetic relaxometry of acute and chronic ischemic lesions to investigate its interest for stroke imaging. We prospectively acquired synthetic and conventional brain MR of 43 consecutive adult patients with suspected stroke. We studied a total of 136 lesions, of which 46 DWI-positive with restricted ADC (DWI + /rADC), 90 white matter T2/FLAIR hyperintensities (WMH) showing no diffusion restriction, and 430 normal brain regions (NBR). We assessed image quality for lesion definition according to a 3-level score by two readers of different experiences. We compared relaxometry of lesions and regions of interest. Synthetic images were superior to their paired conventional images for lesion definition except for sFLAIR (sT1 or sPSIR vs. cT1 and sT2 vs. cT2 for DWI + /rADC and WMH definition; p values < .001) with substantial to almost perfect inter-rater reliability (κ ranging from 0.711 to 0.932, p values < .001). We found significant differences in relaxometry between lesions and NBR and between acute and chronic lesions (T1, T2, and PD of DWI + /rADC or WMH vs. mirror NBR; p values < .001; T1 and PD of DWI + /rADC vs. WMH; p values of 0.034 and 0.008). Synthetic MR may contribute to stroke imaging by fast generating accessible weighted images for visual inspection derived from rapidly acquired relaxometry data. Moreover, this synthetic relaxometry could differentiate acute and chronic ischemic lesions.

Assessment of 2D conventional and synthetic MRI in multiple sclerosis

PURPOSE

To qualitatively and quantitatively compare synthetic and conventional MRI sequences acquired on a 1.5-T system for patients with multiple sclerosis (MS).

METHODS

Prospective study that involved twenty-seven consecutive relapsing-remitting MS patients scanned on a 1.5-T MRI scanner. The MRI protocol included 2D transverse conventional spin-echo sequences: proton density-weighted (PD), T2-weighted, T2-FLAIR, and T1-weighted. Synthetic images were generated using 2D transverse QRAPMASTER and SyMRI software with the same voxel size, repetition, echo, and inversion times as the conventional sequences. Four raters performed a crosstab qualitative analysis that involved evaluating global image quality, contrast, flow artefacts, and confidence in lesion assessment introducing the concepts of predominance, agreement, and disagreement. A quantitative analysis was also performed and included evaluating the number of lesions (periventricular, juxtacortical, brainstem, and cerebellum) and the contrast-to-noise ratio between regions (CSF, white matter, grey matter, lesions).

RESULTS

The global image quality assessment showed predominance for better scores for conventional sequences over synthetic sequences, whereas contrast, confidence in lesion assessment, and flow artefacts showed predominance for agreement between sequences. There was predominance for disagreement between all pairs of raters in most of the evaluated qualitative parameters. Synthetic PD and T2-FLAIR images showed higher contrast-to-noise ratios than the corresponding conventional images for most comparison between regions. There were no significant differences in the number of lesions detected for most of the study regions between conventional and synthetic images.

CONCLUSION

Synthetic MRI can be potentially used as an alternative to conventional brain MRI sequences in the assessment of MS.

The effect of scan parameters on T1, T2 relaxation times measured with multi-dynamic multi-echo sequence: a phantom study

Multi-Dynamic Multi-Echo (MDME) Sequence is a new method which can acquire various contrast-weighted images using quantitative relaxometric parameters measured from multicontrast images. The purpose of our study was to investigate the effect of scan parameters of MDME Sequence on measured T1, T2 values of phantoms at 3.0 T MRI scanner. Gray matter, white matter and cerebrospinal fluid simulation phantoms with different relaxation times (named GM, WM, CSF, respectively) were used in our study. All the phantoms were scanned 9 times on different days using MDME sequence with variations of echo train length, matrix, and acceleration factor. The T1, T2 measurements were acquired after each acquisition. The repeatability was characterized as the intragroup coefficient of variation (CV) of measured values over 9 times, and the discrepancies of measurements across different groups were characterized as intergroup CVs. The highest intragroup CVs of T1-GM, T2-GM, T1-WM, T2-WM, T1-CSF, T2-SCF were 1.36%, 1.75%, 0.74%, 1.41%, 1.70%, 7.79%, respectively. The highest intergroup CVs of T1-GM, T2-GM, T1-WM, T2-WM, T1-CSF, T2-SCF were 0.54%, 1.86%, 1.70%, 0.94%, 1.00%, 2.17%, respectively. Quantitative T1, T2 measurements of gray matter, white matter and cerebrospinal fluid simulation phantoms derived from the MDME sequence were not obviously affected by variations of scanning parameters, such as echo train length, matrix, and acceleration factor on 3T scanner.

Synthetic MR: Physical principles, clinical implementation, and new developments

Current clinical MR imaging practices rely on the qualitative assessment of images for diagnosis and treatment planning. While contrast in MR images is dependent on the spin parameters of the imaged tissue, pixel values on MR images are relative and are not scaled to represent any tissue properties. Synthetic MR is a fully featured imaging workflow consisting of efficient multiparameter mapping acquisition, synthetic image generation, and volume quantitation of brain tissues. As the application becomes more widely available on multiple vendors and scanner platforms, it has also gained widespread adoption as clinicians begin to recognize the benefits of rapid quantitation. This review will provide details about the sequence with a focus on the physical principles behind its relaxometry mechanisms. It will present an overview of the products in their current form and some potential issues when implementing it in the clinic. It will conclude by highlighting some recent advances of the technique, including a 3D mapping method and its associated applications. This article is protected by copyright. All rights reserved.

Synthetic magnetic resonance imaging for primary prostate cancer evaluation: Diagnostic potential of a non-contrast-enhanced bi-parametric approach enhanced with relaxometry measurements

Purpose

Bi-parametric magnetic resonance imaging (bpMRI) with diffusion-weighted images has wide utility in diagnosing clinically significant prostate cancer (csPCa). However, bpMRI yields more false-negatives for PI-RADS category 3 lesions than multiparametric (mp)MRI with dynamic-contrast-enhanced (DCE)-MRI. We investigated the utility of synthetic MRI with relaxometry maps for bpMRI-based diagnosis of csPCa.

Methods

One hundred and five treatment-naïve patients who underwent mpMRI and synthetic MRI before prostate biopsy for suspected PCa between August 2019 and December 2020 were prospectively included. Three experts and three basic prostate radiologists evaluated the diagnostic performance of conventional bpMRI and synthetic bpMRI for csPCa. PI-RADS version 2.1 category 3 lesions were identified by consensus, and relaxometry measurements (T1-value, T2-value, and proton density [PD]) were performed. The diagnostic performance of relaxometry measurements for PI-RADS category 3 lesions in peripheral zone was compared with that of DCE-MRI. Histopathological evaluation results were used as the reference standard. Statistical analysis was performed using the areas under the receiver operating characteristic curve (AUC) and McNemar test.

Results

In 102 patients without significant MRI artefacts, the diagnostic performance of conventional bpMRI was not significantly different from that of synthetic bpMRI for all readers (p = 0.11–0.79). The AUCs of the combination of T1-value, T2-value, and PD (T1 + T2 + PD) for csPCa in peripheral zone for PI-RADS category 3 lesions were 0.85 for expert and 0.86 for basic radiologists, with no significant difference between T1 + T2 + PD and DCE-MRI for both expert and basic radiologists (p = 0.29–0.45).

Conclusion

Synthetic MRI with relaxometry maps shows promise for contrast media-free evaluation of csPCa.

•

Diagnostic performances of synthetic bpMRI and conventional bpMRI are comparable for primary PCa

•

Diagnostic performance of synthetic MRI variables are similar to that of DCE-MRI for csPCa in PZ

•

Synthetic bpMRI shows potential as a contrast agent-free method for primary PCa

Generation of quantification maps and weighted images from synthetic magnetic resonance imaging using deep learning network

OBJECTIVE

The generation of quantification maps and weighted images in synthetic MRI techniques is based on complex fitting equations. This process requires longer image generation times. The objective of this study is to evaluate the feasibility of deep learning method for fast reconstruction of synthetic MRI.

APPROACH

A total of 44 healthy subjects were recruited and random divided into a training set (30 subjects) and a testing set (14 subjects). A multiple-dynamic, multiple-echo (MDME) sequence was used to acquire synthetic MRI images. Quantification maps (T1, T2, and proton density (PD) maps) and weighted (T1W, T2W, and T2W FLAIR) images were created with MAGiC software and then used as the ground truth images in the deep learning (DL) model. An improved multichannel U-Net structure network was trained to generate quantification maps and weighted images from raw synthetic MRI imaging data (8 module images). Quantitative evaluation was performed on quantification maps. Quantitative evaluation metrics, as well as qualitative evaluation were used in weighted image evaluation. Nonparametric Wilcoxon signed-rank tests were performed in this study.

MAIN RESULTS

The results of quantitative evaluation show that the error between the generated quantification images and the reference images is small. For weighted images, no significant difference in overall image quality or SNR was identified between DL images and synthetic images. Notably, the DL images achieved improved image contrast with T2W images, and fewer artifacts were present on DL images than synthetic images acquired by T2W FLAIR.

SIGNIFICANCE

The DL algorithm provides a promising method for image generation in synthetic MRI techniques, in which every step of the calculation can be optimized and faster, thereby simplifying the workflow of synthetic MRI techniques.

Application of MAGnetic resonance imaging compilation in acute ischemic stroke

BACKGROUND

Synthetic magnetic resonance imaging (MRI) MAGnetic resonance imaging compilation (MAGiC) is a new MRI technology. Conventional T1, T2, T2-fluid-attenuated inversion recovery (FLAIR) contrast images, quantitative images of T1 and T2 mapping, and MAGiC phase sensitive inversion recovery (PSIR) Vessel cerebrovascular images can be obtained simultaneously through post-processing at the same time after completing a scan. In recent years, studies have reported that MAGiC can be applied to patients with acute ischemic stroke. We hypothesized that the synthetic MRI vascular screening scheme can evaluate the degree of cerebral artery stenosis in patients with acute ischemic stroke.

AIM

To explore the application value of vascular images obtained by synthetic MRI in diagnosing acute ischemic stroke.

METHODS

A total of 64 patients with acute ischemic stroke were selected and examined by MRI in the current retrospective cohort study. The scanning sequences included traditional T1, T2, and T2-FLAIR, three-dimensional time-of-flight magnetic resonance angiography (3D TOF MRA), diffusion-weighted imaging (DWI), and synthetic MRI. Conventional contrast images (T1, T2, and T2-FLAIR) and intracranial vessel images (MAGiC PSIR Vessel] were automatically reconstructed using synthetic MRI raw data. The contrast-to-noise ratio (CNR) values of traditional T1, T2, and T2-FLAIR images and MAGiC reconstructed T1, T2, and T2-FLAIR images in DWI diffusion restriction areas were measured and compared. MAGiC PSIR Vessel and TOF MRA images were used to measure and calculate the stenosis degree of bilateral middle cerebral artery stenosis areas. The consistency of MAGiC PSIR Vessel and TOF MRA in displaying the degree of vascular stenosis with computed tomography angiography (CTA) was compared.

RESULTS

Among the 64 patients with acute ischemic stroke, 79 vascular stenosis areas showed that the correlation between MAGiC PSIR Vessel and CTA (r = 0.90, P < 0.01) was higher than that between TOF MRA and CTA (r = 0.84, P < 0.01). With a degree of vascular stenosis > 50% assessed by CTA as a reference, the area under the receiver operating characteristic (ROC) curve of MAGiC PSIR Vessel [area under the curve (AUC) = 0.906, P < 0.01] was higher than that of TOF MRA (AUC = 0.790, P < 0.01). Among the 64 patients with acute ischemic stroke, 39 were scanned for traditional T1, T2, and T2-FLAIR images and MAGiC images simultaneously, and CNR values in DWI diffusion restriction areas were measured, which were: Traditional T2 = 21.2, traditional T1 = -6.7, and traditional T2-FLAIR = 11.9; and MAGiC T2 = 7.1, MAGiC T1 = -3.9, and MAGiC T2-FLAIR = 4.5.

CONCLUSION

The synthetic MRI vascular screening scheme for patients with acute ischemic stroke can accurately evaluate the degree of bilateral middle cerebral artery stenosis, which is of great significance to early thrombolytic interventional therapy and improving patients’ quality of life.

A pilot study of the association between leukoaraiosis and cerebral atherosclerosis using synthetic magnetic resonance imaging

BACKGROUND

Leukoaraiosis is a type of lesion characterized by tissue rarefaction or myelin pallor resulting from axons loss and gliosis. Synthetic magnetic resonance imaging (MRI) could yield quantitative T1, T2, proton density (PD) values of leukoaraiosis in addition to information on the volume of the lesion.

PURPOSE

To investigate the feasibility of quantifying leukoaraiosis using synthetic MRI and to explore the association between leukoaraiosis and cerebral small vascular diseases and cerebral atherosclerosis.

MATERIAL AND METHODS

Patients with acute ischemic stroke were enrolled in this study. All participants underwent a conventional T2-weighted image, brain volume, CUBE fluid attenuated inversion recovery, and synthetic MRI acquisition using a 3.0-T MR system. A time-of-flight magnetic resonance angiography was also obtained. We evaluated the T1, T2, PD values and leukoaraiosis volume.

RESULTS

Analysis of the leukoaraiosis volume ratios demonstrated a positive association with T2 values, a negative association with T1 values, and no association with PD values. Leukoaraiosis volume ratios were independently correlated with age (P < 0.001), lacunes (P = 0.022), and cerebral microbleeds (P = 0.010). A statistical association was found between both age (P < 0.001) and lacunes (P = 0.047) and leukoaraiosis T2 values.

CONCLUSION

Synthetic MRI may enhance the evaluation of leukoaraiosis, in addition to providing information on its volume. Leukoaraiosis may represent a type of cerebral small vascular disease rather than cerebral atherosclerosis and may share the same pathological mechanism as lacunes and cerebral microbleeds.

Synthetic MRI with T2-based Water Suppression to Reduce Hyperintense Artifacts due to CSF-Partial Volume Effects in the Brain

Purpose:

Our purpose was to assess our proposed new synthetic MRI (synMRI) technique, combined with T₂-based water suppression (T₂wsup), to reduce cerebral spinal fluid (CSF)–partial volume effects (PVEs). These PVEs are problematic in the T₂-weighted fluid-attenuation inversion recovery (FLAIR) images obtained by conventional synMRI techniques.

Methods:

Our T₂wsup was achieved by subtracting additionally acquired long TE spin echo (SE) images of water signals dominant from the originally acquired images after T₂ decay correction and a masking on the long TE image using the water volume (V_w) map to preserve tissue SNR, followed by quantitative mapping and then calculation of the synthetic images. A simulation study based on a two-compartment model including tissue and water in a voxel and a volunteer MR study were performed to assess our proposed method. Parameters of long TE and a threshold value in the masking were assessed and optimized experimentally. Quantitative parameter maps of standard and with T₂wsup were generated, then wsup-synthetic FLAIR and SE images were calculated using those suitable combinations and compared.

Results:

Our simulation clarified that the CSF–PVE artifacts in the standard synthetic FLAIR increase T₂ as the water volume increases in a voxel, and the volunteer MR brain study demonstrated that the hyperintense artifacts on synthetic images were reduced to < 10% of V_w in those with the standard synMRI while keeping the tissue SNR by selecting optimal masking parameters on additional long TE images of TE = 300 ms. In addition, the wsup-synthetic SE provided better gray-white matter contrasts compared with the wsup-synthetic FLAIR while keeping CSF suppression.

Conclusion:

Our proposed T₂wsup-synMRI technique makes it easy to reduce the CSF–PVE artifacts problematic in the synthetic FLAIR images using the current synMRI technique by adding long TE images and simple processing. Although further optimizations in data acquisition and processing techniques are required before actual clinical use, we expect our technique to become clinically useful.

Quad-Contrast Imaging: Simultaneous Acquisition of Four Contrast-Weighted Images (PD-Weighted, T₂-Weighted, PD-FLAIR and T₂-FLAIR Images) With Synthetic T₁-Weighted Image, T₁- and T₂-Maps

Magnetic resonance imaging (MRI) can provide multiple contrast-weighted images using different pulse sequences and protocols. However, a long acquisition time of the images is a major challenge. To address this limitation, a new pulse sequence referred to as quad-contrast imaging is presented. The quad-contrast sequence enables the simultaneous acquisition of four contrast-weighted images (proton density (PD)-weighted, T₂-weighted, PD-fluid attenuated inversion recovery (FLAIR), and T₂-FLAIR), and the synthesis of T₁-weighted images and T₁- and T₂-maps in a single scan. The scan time is less than 6 min and is further reduced to 2 min 50 s using a deep learning-based parallel imaging reconstruction. The natively acquired quad contrasts demonstrate high quality images, comparable to those from the conventional scans. The deep learning-based reconstruction successfully reconstructed highly accelerated data (acceleration factor 6), reporting smaller normalized root mean squared errors (NRMSEs) and higher structural similarities (SSIMs) than those from conventional generalized autocalibrating partially parallel acquisitions (GRAPPA)-reconstruction (mean NRMSE of 4.36% vs. 10.54% and mean SSIM of 0.990 vs. 0.953). In particular, the FLAIR contrast is natively acquired and does not suffer from lesion-like artifacts at the boundary of tissue and cerebrospinal fluid, differentiating the proposed method from synthetic imaging methods. The quad-contrast imaging method may have the potentials to be used in a clinical routine as a rapid diagnostic tool.

Reduced myelin in patients with isolated hippocampal sclerosis as assessed by SyMRI

Purpose

Synthetic MRI (SyMRI) enables to quantify brain tissue and morphometry. We aimed to investigate the WM and myelin alterations in patients with unilateral hippocampal sclerosis (HS) with SyMRI.

Methods

Adult patients with isolated unilateral HS and age-matched control subjects (CSs) were included in this study. The SyMRI sequence QRAPMASTER in the coronal plane perpendicular to the hippocampi was obtained from the whole brain. Automatic segmentation of the whole brain was processed by SyMRI Diagnostic software (Version 11.2). Two neuroradiologists also performed quantitative analyses independently from symmetrical 14 ROIs placed in temporal and extratemporal WM, hippocampi, and amygdalae in both hemispheres.

Results

Sixteen patients (F/M = 6/10, mean age = 32.5 ± 11.3 years; right/left HS: 8/8) and 10 CSs (F/M = 5/5, mean age = 30.7 ± 7 years) were included. Left HS patients had significantly lower myelin and WM volumes than CSs (p < .05). Myelin was reduced significantly in the ipsilateral temporal lobe of patients than CSs, greater in left HS (p < .05). Histopathological examination including luxol fast blue stain also revealed myelin pallor in all of 6 patients who were operated. Ipsilateral temporal pole and sub-insular WM had significantly reduced myelin than the corresponding contralateral regions in patients (p < .05). No significant difference was found in WM values. GM values were significantly lower in hippocampi in patients than CSs (p < .05).

Conclusion

SyMRI revealed myelin reduction in the ipsilateral temporal lobe and sub-insular WM of patients with HS. Whether this finding correlates with electrophysiological features and SyMRI could serve as lateralization of temporal lobe epilepsy need to be investigated.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00234-021-02824-6.

Current Perspectives of Artificial Intelligence in Pediatric Neuroradiology: An Overview

Artificial Intelligence, Machine Learning, and myriad related techniques are becoming ever more commonplace throughout industry and society, and radiology is by no means an exception. It is essential for every radiologists of every subspecialty to gain familiarity and confidence with these techniques as they become increasingly incorporated into the routine practice in both academic and private practice settings. In this article, we provide a brief review of several definitions and techniques that are commonly used in AI, and in particular machine vision, and examples of how they are currently being applied to the setting of clinical neuroradiology. We then review the unique challenges that the adoption and application of faces within the subspecialty of pediatric neuroradiology, and how these obstacles may be overcome. We conclude by presenting specific examples of how AI is currently being applied within the field of pediatric neuroradiology and the potential opportunities that are available for future applications.

Exploratory Radiomic Analysis of Conventional vs. Quantitative Brain MRI: Toward Automatic Diagnosis of Early Multiple Sclerosis

Conventional magnetic resonance imaging (cMRI) is poorly sensitive to pathological changes related to multiple sclerosis (MS) in normal-appearing white matter (NAWM) and gray matter (GM), with the added difficulty of not being very reproducible. Quantitative MRI (qMRI), on the other hand, attempts to represent the physical properties of tissues, making it an ideal candidate for quantitative medical image analysis or radiomics. We therefore hypothesized that qMRI-based radiomic features have added diagnostic value in MS compared to cMRI. This study investigated the ability of cMRI (T1w) and qMRI features extracted from white matter (WM), NAWM, and GM to distinguish between MS patients (MSP) and healthy control subjects (HCS). We developed exploratory radiomic classification models on a dataset comprising 36 MSP and 36 HCS recruited in CHU Liege, Belgium, acquired with cMRI and qMRI. For each image type and region of interest, qMRI radiomic models for MS diagnosis were developed on a training subset and validated on a testing subset. Radiomic models based on cMRI were developed on the entire training dataset and externally validated on open-source datasets with 167 HCS and 10 MSP. Ranked by region of interest, the best diagnostic performance was achieved in the whole WM. Here the model based on magnetization transfer imaging (a type of qMRI) features yielded a median area under the receiver operating characteristic curve (AUC) of 1.00 in the testing sub-cohort. Ranked by image type, the best performance was achieved by the magnetization transfer models, with median AUCs of 0.79 (0.69–0.90, 90% CI) in NAWM and 0.81 (0.71–0.90) in GM. The external validation of the T1w models yielded an AUC of 0.78 (0.47–1.00) in the whole WM, demonstrating a large 95% CI and a low sensitivity of 0.30 (0.10–0.70). This exploratory study indicates that qMRI radiomics could provide efficient diagnostic information using NAWM and GM analysis in MSP. T1w radiomics could be useful for a fast and automated check of conventional MRI for WM abnormalities once acquisition and reconstruction heterogeneities have been overcome. Further prospective validation is needed, involving more data for better interpretation and generalization of the results.

Synthetic MRI in subarachnoid haemorrhage

AIM

To evaluate the reliability of synthetic magnetic resonance imaging (SyMRI) for detecting complications associated with subarachnoid haemorrhage (SAH), such as ischaemic lesions, hydrocephalus, or bleeding complications.

MATERIALS AND METHODS

Twenty patients with SAH, who underwent a conventional brain MRI and a SyMRI on a 3 T MRI machine. Comparable conventional and synthetic T2-weighted fluid attenuated inversion recovery (FLAIR) images were acquired. The presence of ischaemic lesions, hydrocephalus, extra-axial blood collections as well as the volumes of grey matter (GMv), white matter (WMv), and cerebrospinal (CSFv) were compared. The acquisition times of both sequences was also analysed.

RESULTS

The concordance between the two techniques was excellent for the detection of ischaemic lesions and extra-axial collections (kappa = 0.80 and 0.88 respectively) and good for the detection of hydrocephalus (kappa = 0.69). No significant differences were detected in the number of ischaemic lesions (p=0.31) or in the Evans index (p=0.11). The WMv and CSFv measures were also similar (p=0.18 and p=0.94, respectively), as well as the volume of ischaemic lesions (p=0.79). Compared to conventional MRI, the SyMRI acquisition time was shorter regardless of the number of sections (32% and 6% time reduction for 4 or 3 mm section thickness, respectively).

CONCLUSIONS

SyMRI allows the detection of potential complications of SAH in a similar way to conventional MRI with a shorter acquisition time.

Accelerated multicontrast reconstruction for synthetic MRI using joint parallel imaging and variable splitting networks

PURPOSE

Synthetic magnetic resonance imaging (MRI) requires the acquisition of multicontrast images to estimate quantitative parameter maps, such as T₁ , T₂ , and proton density (PD). The study aims to develop a multicontrast reconstruction method based on joint parallel imaging (JPI) and joint deep learning (JDL) to enable further acceleration of synthetic MRI.

METHODS

The JPI and JDL methods are extended and combined to improve reconstruction for better-quality, synthesized images. JPI is performed as a first step to estimate the missing k-space lines, and JDL is then performed to correct and refine the previous estimate with a trained neural network. For the JDL architecture, the original variable splitting network (VS-Net) is modified and extended to form a joint variable splitting network (JVS-Net) to apply to multicontrast reconstructions. The proposed method is designed and tested for multidynamic multiecho (MDME) images with Cartesian uniform under-sampling using acceleration factors between 4 and 8.

RESULTS

It is demonstrated that the normalized root-mean-square error (nRMSE) is lower and the structural similarity index measure (SSIM) values are higher with the proposed method compared to both the JPI and JDL methods individually. The method also demonstrates the potential to produce a set of synthesized contrast-weighted images that closely resemble those from the fully sampled acquisition without erroneous artifacts.

CONCLUSION

Combining JPI and JDL enables the reconstruction of highly accelerated synthetic MRIs.

Quantitative Analysis of Synthetic Magnetic Resonance Imaging in Alzheimer's Disease

Objectives: The purpose of this study was to evaluate the feasibility and whether synthetic MRI can benefit diagnosis of Alzheimer’s disease (AD).

Materials and Methods: Eighteen patients and eighteen age-matched normal controls (NCs) underwent MR examination. The mini-mental state examination (MMSE) scores were obtained from all patients. The whole brain volumetric characteristics, T1, T2, and proton density (PD) values of different cortical and subcortical regions were obtained. The volumetric characteristics and brain regional relaxation values between AD patients and NCs were compared using independent-samples t-test. The correlations between these quantitative parameters and MMSE score were assessed by the Pearson correlation in AD patients.

Results: Although the larger volume of cerebrospinal fluid (CSF), lower brain parenchymal volume (BPV), and the ratio of brain parenchymal volume to intracranial volume (BPV/ICV) were found in AD patients compared with NCs, there were no significant differences (p > 0.05). T1 values of right insula cortex and T2 values of left hippocampus and right insula cortex were significantly higher in AD patients than in NCs, but T1 values of left caudate showed a reverse trend (p < 0.05). As the MMSE score decreased in AD patients, the BPV and BPV/ICV decreased, while the volume of CSF and T1 values of bilateral insula cortex and bilateral hippocampus as well as T2 values of bilateral hippocampus increased (p < 0.05).

Conclusion: Synthetic MRI not only provides more information to differentiate AD patients from normal controls, but also reflects the disease severity of AD.

Histogram analysis of quantitative parameters from synthetic MRI: Correlations with prognostic factors and molecular subtypes in invasive ductal breast cancer

PURPOSE

To evaluate intra-tumoral heterogeneity through a histogram analysis of quantitative parameters obtained from synthetic MRI (magnetic resonance imaging), and determine correlations of these histogram characteristics with prognostic factors and molecular subtypes of invasive ductal carcinoma (IDC).

METHODS

A total of 122 IDC from 122 women who underwent preoperative synthetic MRI and DCE (dynamic contrast enhancement)-MRI were investigated. The synthetic MRI parameters (T1, T2, and PD (proton density)) were obtained. For each parameter, the minimum, 10th percentile, mean, median, 90th percentile, maximum, skewness, and kurtosis values of tumor were calculated, and correlations with prognostic factors and subtypes were assessed. The Mann-Whitney U test or the Student^'s t test were utilized to analyze the association between the histogram features of synthetic MRI parameters and prognostic factors. The Kruskal-Wallis test followed by the post-hoc test was used to analyze differences of synthetic MRI parameters among molecular subtypes.

RESULTS

IDC with high histopathologic grade showed statistically higher PD_maxium, T1_mean and T1_median values than those with low grade (p = 0.003, p = 0.007, p = 0.003). The T1_10th were significantly higher in cancers with PR (progesterone receptor) negativity than those with PR positivity (p = 0.005). ER-negative cancers had significant higher values of T2_10th, T2_mean, and T2_median than ER-positive cancers (p = 0.006, 0.002, and 0.006, respectively). The values of PD_median were significantly higher in IDC with HER2 (human epidermal growth factor receptor 2) positivity than those with HER2 negativity (p = 0.001). When discriminating molecular subtypes of IDC, the T2_mean achieved the highest performance. The T2_mean values of TN (triple-negative), luminal B and luminal A types are arranged in descending order (p <  0.0001).

CONCLUSIONS

Histogram features derived from synthetic MRI quantifies the distributions of tissue relaxation time and proton density, and may serve as a potential biomarker for discriminating histopathological grade, hormone receptor status, HER2 expression status and breast cancer subtypes.

Investigating the Image Quality and Utility of Synthetic MRI in the Breast

Purpose

Synthetic MRI reconstructs multiple sequences in a single acquisition. In the present study, we aimed to compare the image quality and utility of synthetic MRI with that of conventional MRI in the breast.

Methods

We retrospectively collected the imaging data of 37 women (mean age: 55.1 years; range: 20–78 years) who had undergone both synthetic and conventional MRI of T2-weighted, T1-weighted, and fat-suppressed (FS)-T2-weighted images. Two independent breast radiologists evaluated the overall image quality, anatomical sharpness, contrast between tissues, image homogeneity, and presence of artifacts of synthetic and conventional MRI on a 5-point scale (5 = very good to 1 = very poor). The interobserver agreement between the radiologists was evaluated using weighted kappa.

Results

For synthetic MRI, the acquisition time was 3 min 28 s. On the 5-point scale evaluation of overall image quality, although the scores of synthetic FS-T2-weighted images (4.01 ± 0.56) were lower than that of conventional images (4.95 ± 0.23; P < 0.001), the scores of synthetic T1- and T2-weighted images (4.95 ± 0.23 and 4.97 ± 0.16) were comparable with those of conventional images (4.92 ± 0.27 and 4.97 ± 0.16; P = 0.484 and 1.000, respectively). The kappa coefficient of conventional MRI was fair (0.53; P < 0.001), and that of conventional MRI was fair (0.46; P < 0.001).

Conclusion

The image quality of synthetic T1- and T2-weighted images was similar to that of conventional images and diagnostically acceptable, whereas the quality of synthetic T2-weighted FS images was inferior to conventional images. Although synthetic MRI images of the breast have the potential to provide efficient image diagnosis, further validation and improvement are required for clinical application.

3D Quantitative Synthetic MRI in the Evaluation of Multiple Sclerosis Lesions

BACKGROUND AND PURPOSE

Synthetic MR imaging creates multiple contrast-weighted images based on a single time-efficient quantitative scan, which has been mostly performed for 2D acquisition. We assessed the utility of 3D synthetic MR imaging in patients with MS by comparing its diagnostic image quality and lesion volumetry with conventional MR imaging.

MATERIALS AND METHODS

Twenty-four patients with MS prospectively underwent 3D quantitative synthetic MR imaging and conventional T1-weighted, T2-weighted, FLAIR, and double inversion recovery imaging, with acquisition times of 9 minutes 3 seconds and 18 minutes 27 seconds for the synthetic MR imaging and conventional MR imaging sequences, respectively. Synthetic phase-sensitive inversion recovery images and those corresponding to conventional MR imaging contrasts were created for synthetic MR imaging. Two neuroradiologists independently assessed the image quality on a 5-point Likert scale. The numbers of cortical lesions and lesion volumes were quantified using both synthetic and conventional image sets.

RESULTS

The overall diagnostic image quality of synthetic T1WI and double inversion recovery images was noninferior to that of conventional images (P = .23 and .20, respectively), whereas that of synthetic T2WI and FLAIR was inferior to that of conventional images (both Ps < .001). There were no significant differences in the number of cortical lesions (P = .17 and .53 for each rater) or segmented lesion volumes (P = .61) between the synthetic and conventional image sets.

CONCLUSIONS

Three-dimensional synthetic MR imaging could serve as an alternative to conventional MR imaging in evaluating MS with a reduced scan time.

Deep Learning Approach for Generating MRA Images From 3D Quantitative Synthetic MRI Without Additional Scans

OBJECTIVES

Quantitative synthetic magnetic resonance imaging (MRI) enables synthesis of various contrast-weighted images as well as simultaneous quantification of T1 and T2 relaxation times and proton density. However, to date, it has been challenging to generate magnetic resonance angiography (MRA) images with synthetic MRI. The purpose of this study was to develop a deep learning algorithm to generate MRA images based on 3D synthetic MRI raw data.

MATERIALS AND METHODS

Eleven healthy volunteers and 4 patients with intracranial aneurysms were included in this study. All participants underwent a time-of-flight (TOF) MRA sequence and a 3D-QALAS synthetic MRI sequence. The 3D-QALAS sequence acquires 5 raw images, which were used as the input for a deep learning network. The input was converted to its corresponding MRA images by a combination of a single-convolution and a U-net model with a 5-fold cross-validation, which were then compared with a simple linear combination model. Image quality was evaluated by calculating the peak signal-to-noise ratio (PSNR), structural similarity index measurements (SSIMs), and high frequency error norm (HFEN). These calculations were performed for deep learning MRA (DL-MRA) and linear combination MRA (linear-MR), relative to TOF-MRA, and compared with each other using a nonparametric Wilcoxon signed-rank test. Overall image quality and branch visualization, each scored on a 5-point Likert scale, were blindly and independently rated by 2 board-certified radiologists.

RESULTS

Deep learning MRA was successfully obtained in all subjects. The mean PSNR, SSIM, and HFEN of the DL-MRA were significantly higher, higher, and lower, respectively, than those of the linear-MRA (PSNR, 35.3 ± 0.5 vs 34.0 ± 0.5, P < 0.001; SSIM, 0.93 ± 0.02 vs 0.82 ± 0.02, P < 0.001; HFEN, 0.61 ± 0.08 vs 0.86 ± 0.05, P < 0.001). The overall image quality of the DL-MRA was comparable to that of TOF-MRA (4.2 ± 0.7 vs 4.4 ± 0.7, P = 0.99), and both types of images were superior to that of linear-MRA (1.5 ± 0.6, for both P < 0.001). No significant differences were identified between DL-MRA and TOF-MRA in the branch visibility of intracranial arteries, except for ophthalmic artery (1.2 ± 0.5 vs 2.3 ± 1.2, P < 0.001).

CONCLUSIONS

Magnetic resonance angiography generated by deep learning from 3D synthetic MRI data visualized major intracranial arteries as effectively as TOF-MRA, with inherently aligned quantitative maps and multiple contrast-weighted images. Our proposed algorithm may be useful as a screening tool for intracranial aneurysms without requiring additional scanning time.

The Utility of a Convolutional Neural Network for Generating a Myelin Volume Index Map from Rapid Simultaneous Relaxometry Imaging

Purpose:

A current algorithm to obtain a synthetic myelin volume fraction map (SyMVF) from rapid simultaneous relaxometry imaging (RSRI) has a potential problem, that it does not incorporate information from surrounding pixels. The purpose of this study was to develop a method that utilizes a convolutional neural network (CNN) to overcome this problem.

Methods:

RSRI and magnetization transfer images from 20 healthy volunteers were included. A CNN was trained to reconstruct RSRI-related metric maps into a myelin volume-related index (generated myelin volume index: GenMVI) map using the MVI map calculated from magnetization transfer images (MTMVI) as reference. The SyMVF and GenMVI maps were statistically compared by testing how well they correlated with the MTMVI map. The correlations were evaluated based on: (i) averaged values obtained from 164 atlas-based ROIs, and (ii) pixel-based comparison for ROIs defined in four different tissue types (cortical and subcortical gray matter, white matter, and whole brain).

Results:

For atlas-based ROIs, the overall correlation with the MTMVI map was higher for the GenMVI map than for the SyMVF map. In the pixel-based comparison, correlation with the MTMVI map was stronger for the GenMVI map than for the SyMVF map, and the difference in the distribution for the volunteers was significant (Wilcoxon sign-rank test, P < 0.001) in all tissue types.

Conclusion:

The proposed method is useful, as it can incorporate more specific information about local tissue properties than the existing method. However, clinical validation is necessary.

Investigation of the feasibility of synthetic MRI in the differential diagnosis of non-keratinising nasopharyngeal carcinoma and benign hyperplasia using different contoured methods for delineation of the region of interest

AIM

To assess the feasibility and preliminary diagnostic performances of relaxation times derived from synthetic magnetic resonance imaging (syMRI) for differentiating nasopharyngeal carcinoma from nasopharyngeal benign lymphoid hyperplasia, and to assess the influence of tissue segmentation method on relaxation estimates.

MATERIALS AND METHODS

Fifty participants with nasopharyngeal carcinoma (NPC) and 40 participants with benign hyperplasia (NPH) who underwent syMRI examination were enrolled prospectively. T1, T2, and proton density (PD) values were obtained from four different regions of interest (ROIs), namely, partial-section, single-section, three-sections, and whole-lesion. The metrics between NPC and NPH or among different ROIs were compared using Student's t-test or one-way ANOVA. The area under curve (AUC) was calculated to assess the performance of metrics obtained from different ROIs to differentiate NPC and NPH.

RESULTS

The T1, T2, and PD values for NPH were significantly higher than those for NPC, regardless of the type of ROI used, except for the PD value obtained from the whole-lesion ROI. The T2 values obtained from the single-section ROI showed the highest diagnostic accuracy in distinguishing NPC from NPH, with an AUC of 0.894, sensitivity of 0.900, and specificity of 0.800. Additionally, the T1, T2, and PD values for nasopharyngeal lesions showed no statistical difference among different kinds of ROI, except for the difference in T1 value between partial-section and other methods.

CONCLUSION

Quantitative analysis of syMRI has the potential to distinguish NPC from NPH. Moreover, different types of ROI showed limited influence on the relaxation time estimation for nasopharyngeal lesions.

Synthetic MRI: Technologies and Applications in Neuroradiology

Synthetic MRI is a technique that synthesizes contrast-weighted images from multicontrast MRI data. There have been advances in synthetic MRI since the technique was introduced. Although a number of synthetic MRI methods have been developed for quantifying one or more relaxometric parameters and for generating multiple contrast-weighted images, this review focuses on several methods that quantify all three relaxometric parameters (T₁ , T₂ , and proton density) and produce multiple contrast-weighted images. Acquisition, quantification, and image synthesis techniques are discussed for each method. We discuss the image quality and diagnostic accuracy of synthetic MRI methods and their clinical applications in neuroradiology. Based on this analysis, we highlight areas that need to be addressed for synthetic MRI to be widely implemented in the clinic. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY STAGE: 1.

Synthetic MRI of the lumbar spine at 3.0 T: feasibility and image quality comparison with conventional MRI

Background

Synthetic magnetic resonance imaging (MRI), which can generate multiple morphologic MR images as well as quantitative maps from a single sequence, is not widely used in the spine at 3.0 T.

Purpose

To investigate the feasibility of synthetic MRI of the lumbar spine in clinical practice at 3.0 T.

Material and Methods

Eighty-four patients with lumbar diseases underwent conventional T1-weighted images, T2-weighted images, short-tau inversion recovery (STIR) images, and synthetic MRI of the lumbar spine at 3.0 T. The quantitative and qualitative image quality and agreement for detection of spinal lesions between conventional and synthetic MRI were compared by two radiologists.

Results

The signal-to-noise ratios of synthetic MRI showed an inferior image quality in the vertebrae and disc, whereas were higher for spinal canal and fat on the synthetic T1-weighted, T2-weighted, and STIR images. The contrast-to-noise ratios of the synthetic MRI was superior to conventional sequences, except for the vertebrae–disc contrast-to-noise ratio on T1-weighted imaging ( P =  0.005). Image quality assessments showed that synthetic MRI had greater STIR fat suppression ( P <  0.001) and fluid brightness ( P =  0.014), as well as higher degree of artifacts ( P <  0.001) and worse spatial resolution ( P =  0.002). The inter-method agreements for detection of spinal lesions were substantial to perfect (kappa, 0.614–0.925).

Conclusion

Synthetic MRI is a feasible method for lumbar spine imaging in a clinical setting at 3.0-T MR. It provides morphologic sequences with acceptable image quality, good agreement with conventional MRI for detection of spinal lesions and quantitative image maps with a slightly shorter acquisition time compared with conventional MRI.

Signal Intensity within Cerebral Venous Sinuses on Synthetic MRI

Purpose:

Flowing blood sometimes appears bright on synthetic T₁-weighted images, which could be misdiagnosed as a thrombus. This study aimed to investigate the frequency of hyperintensity within cerebral venous sinuses on synthetic MR images and to evaluate the influence of increasing flow rates on signal intensity using a flow phantom.

Materials and Methods:

Imaging data, including synthetic and conventional MRI scans, from 22 patients were retrospectively analyzed. Signal intensities at eight locations of cerebral venous sinuses on synthetic images were graded using the following three-point scale: 0, “dark vessel”; 1, “hyperintensity within the walls”; and 2, “hyperintensity within the lumen.” A phantom with gadolinium solution inside a U-shaped tube was acquired without flow and then with increasing flow rates (60, 100, 200, 300, 400 ml/min).

Results:

Considering all sinus locations, the venous signal intensity on synthetic T₁-weighted images was graded as 2 in 79.8% of the patients. On synthetic T₂-weighted images, all sinuses were graded as 0. On fluid-attenuated inversion recovery (FLAIR) images, sinuses were almost always graded as 0 (99.4%). In the phantom study, the signal initially became brighter on synthetic T₁-weighted images as the flow rate increased. Above a certain flow rate, the signal started to decrease.

Conclusion:

High signal intensity within the cerebral venous sinuses is a frequent finding on synthetic T₁-weighted images. This corresponds to the hyperintensity noted at certain flow rates in the phantom experiment.

Myelin Measurement Using Quantitative Magnetic Resonance Imaging: A Correlation Study Comparing Various Imaging Techniques in Patients with Multiple Sclerosis

Evaluation of myelin by magnetic resonance imaging (MRI) is a difficult challenge, but holds promise in demyelinating diseases, such as multiple sclerosis (MS). Although multiple techniques have been developed, no gold standard has been established. This study aims to evaluate the correlation between synthetic MRI myelin volume fraction (SyMRI_MVF) and myelin fraction estimated by other techniques, i.e., magnetization transfer saturation (MTsat), T1-weighted images divided by T2-weighted images (T1w/T2w), and radial diffusivity (RD) in patients with MS. We also compared the sensitivities of these techniques for detecting MS-related myelin damage. SyMRI_MVF, MTsat, T1w/T2w, and RD were averaged on plaque, periplaque white matter, and normal-appearing white matter (NAWM). Pairwise correlation was calculated using Spearman’s correlation analysis. For all segmented regions, strong correlations were found between SyMRI_MVF and T1w/T2w (Rho = 0.89), MTsat (Rho = 0.82), or RD (Rho = −0.75). For each technique, the average estimated myelin differed significantly among regions, but the percentage change of NAWM from both periplaque white matter and plaque were highest in SyMRI_MVF. SyMRI_MVF might be suitable for myelin evaluation in MS patients, with relevant results as compared to other well-studied techniques. Moreover, it presented better sensitivity for the detection of the difference between plaque or periplaque white matter and NAWM.

Diagnosis and Grading of Prostate Cancer by Relaxation Maps From Synthetic MRI

BACKGROUND

The interpretation system for prostate MRI is largely based on qualitative image contrast of different tissue types. Therefore, a fast, standardized, and robust quantitative technique is necessary. Synthetic MRI is capable of quantifying multiple relaxation parameters, which might have potential applications in prostate cancer (PCa).

PURPOSE

To investigate the use of quantitative relaxation maps derived from synthetic MRI for the diagnosis and grading of PCa.

STUDY TYPE

Prospective.

SUBJECTS

In all, 94 men with pathologically confirmed PCa or benign pathological changes.

FIELD STRENGTH/SEQUENCE

T₁ -weighted imaging, T₂ -weighted imaging, diffusion-weighted imaging, and synthetic MRI at 3.0T.

ASSESSMENT

Four kinds of tissue types were identified on pathology, including PCa, stromal hyperplasia (SH), glandular hyperplasia (GH), and noncancerous peripheral zone (PZ). PCa foci were grouped as low-grade (LG, Gleason score ≤6) and intermediate/high-grade (HG, Gleason score ≥7). Regions of interest were manually drawn by two radiologists in consensus on parametric maps according to the pathological results.

STATISTICAL TESTS

Independent sample t-test, Mann-Whitney U-test, and receiver operating characteristic curve analysis.

RESULTS

T₁ and T₂ values of PCa were significantly lower than SH (P = 0.015 and 0.002). The differences of T₁ and T₂ values between PCa and noncancerous PZ were also significant (P ≤ 0.006). The area under the curve (AUC) of the apparent diffusion coefficient (ADC) value was significantly higher than T₁ , T₂ , and proton density (PD) values in discriminating PCa from SH and noncancerous PZ (P ≤ 0.025). T₂ , PD, and ADC values demonstrated similar diagnostic performance in discriminating LG from HG PCa (AUC = 0.806 [0.640-0.918], 0.717 [0.542-0.854], and 0.817 [0.652-0.925], respectively; P ≥ 0.535).

DATA CONCLUSION

Relaxation maps derived from synthetic MRI were helpful for discriminating PCa from other benign pathologies. But the overall diagnostic performance was inferior to the ADC values. T₂ , PD, and ADC values performed similarly in discriminating LG from HG PCa lesions.

LEVEL OF EVIDENCE

2 Technical Efficacy Stage: 2 J. Magn. Reson. Imaging 2020;52:552-564.

Validation of Deep Learning-Based Artifact Correction on Synthetic FLAIR Images in a Different Scanning Environment

We investigated the capability of a trained deep learning (DL) model with a convolutional neural network (CNN) in a different scanning environment in terms of ameliorating the quality of synthetic fluid-attenuated inversion recovery (FLAIR) images. The acquired data of 319 patients obtained from the retrospective review were used as test sets for the already trained DL model to correct the synthetic FLAIR images. Quantitative analyses were performed for native synthetic FLAIR and DL-FLAIR images against conventional FLAIR images. Two neuroradiologists assessed the quality and artifact degree of the native synthetic FLAIR and DL-FLAIR images. The quantitative parameters showed significant improvement on DL-FLAIR in all individual tissue segments and total intracranial tissues than on the native synthetic FLAIR (p < 0.0001). DL-FLAIR images showed improved image quality with fewer artifacts than the native synthetic FLAIR images (p < 0.0001). There was no significant difference in the preservation of the periventricular white matter hyperintensities and lesion conspicuity between the two FLAIR image sets (p = 0.217). The quality of synthetic FLAIR images was improved through artifact correction using the trained DL model on a different scan environment. DL-based correction can be a promising solution for ameliorating the quality of synthetic FLAIR images to broaden the clinical use of synthetic magnetic resonance imaging (MRI).

Comparison between synthetic and conventional magnetic resonance imaging in patients with multiple sclerosis and controls

OBJECTIVES

Synthetic magnetic resonance imaging (SyMRI) allows to obtain different weighted-images using the multiple-dynamic multiple-echo sequence lasting 6 min. The aim is to compare quantitatively and qualitatively synthetic- and conventional MRI in patients with multiple sclerosis (MS) and controls assessing the contrast (C), the signal to noise ratio (SNR), and the contrast to noise ratio (CNR). We evaluated the lesion count and lesion-to-white matter contrast ([Formula: see text] in the MS patients.

METHODS AND METHODS

51 patients underwent synthetic- and conventional MRI. Qualitative analysis was evaluated by assigning scores to all synthetic- and conventional MRI sequences by two neuroradiologists. Lesions were counted in MS patients both in the conventional- and synthetic T2-FLAIR. Regions of interest were placed in the cerebrospinal fluid, in the white- and grey matter. For the sequences were evaluated: C, CNR, and SNR.

RESULTS

Synthetic T2-FLAIR images are qualitatively inferior. C and CNR were significantly higher in synthetic T1W and T2W images compared to conventional images, but not for T2-FLAIR. The SNR value was always lower in synthetic images than in conventional ones.

CONCLUSIONS

SyMRI can be used in clinical practice because it has a similar diagnostic accuracy which reduces the scanning time compared to the conventional one. However, synthetic T2-FLAIR images need to be improved.