Cerebrovascular segmentation network based on fast fourier convolution and Mamba

Objective To evaluate image quality and diagnostic performance of silent MR angiography (MRA) and discuss the feasibility of silent MRA in diagnosing intracranial aneurysms. Methods Twenty seven patients suspected with cerebrovascular disorders and 30 intracranial aneurysms in Northern Jiangsu People's Hospital, were enrolled prospectively in this study from December 2015 to December 2018. Silent and time of flight (TOF) MRA were performed on the same day prior to CTA examination. The corresponding MRA images were independently and blindly evaluated by two experienced neuroradiologists in the aspects of signal homogeneity, lesion conspicuity, venous signal/artifact and diagnostic confidence (4-point scale). The aneurysms were divided into tiny (≤ 3 mm) and non-tinyaneurysm groups(> 3 mm) according to the measured diameters of aneurysms. The differences in image quality ratings between silent MRA and TOF MRA were analyzed using Wilcoxon signed rank tests. Intra-class correlation coefficients (ICC) were used to test the consistency of measurements between MRAs (silent MRA, TOF MRA) and CTA. Results CTA revealed 32 intracranial aneurysms. For silent MRA and TOF MRA, the scores of signal homogeneity were 3.38±0.49 and 3.00±0.62, andthe scores of venous signal/artifact were 3.77±0.42 and 2.65±0.48.Significant differences were found between the two MRAs in these aspects (Z=-2.21, P=0.02; Z=-5.69, P=0.01). The scores of lesion conspicuity were 3.19±0.56 and 3.15±0.46, and the scores of diagnostic confidence were 3.27±0.44 and 3.12±0.51.There were no significant differences found in these aspects (P>0.05).The ICC coefficient was excellentfor silent MRA (0.94, 95%CI 0.82- 0.98)and was good for TOF MRA (0.72, 95%CI 0.30-0.91) in tiny aneurysm group. The ICC coefficient was excellent (silent MRA, 0.98, 95%CI 0.95-0.99; TOF MRA, 0.95, 95%CI 0.87-0.98) for both MRA in non-tiny aneurysm group. Conclusions Compared with TOF MRA, silent MRA could achieve higher image quality and higher diagnostic confidence, and higher consistency with CTA. Silent MRA can be a promising non-contrast-enhanced alternative MRA technique in clinical setting. Key words: Magnetic resonance imaging; Intracranial aneurysm; Diagnosis, differential; Comparative study

Accurate diagnosis of the degree of internal carotid artery (ICA) stenosis is needed for decisions regarding optimal stroke prevention. Noninvasive magnetic resonance angiography (MRA) is being proposed and used as a replacement for the gold standard, intra-arterial angiography. Our purpose was to perform a systematic review and diagnostic meta-analysis to determine the sensitivity and specificity of time-of-flight (TOF) MRA and contrast-enhanced (CE) MRA for the detection of (1) high-grade (> or = 70% to 99%) ICA stenoses; (2) ICA occlusions; (3) moderately severe (50% to 69%) ICA stenoses; and (4) compare the overall accuracy of the 2 MRA techniques. The medical literature on MRA and the diagnosis of ICA steno-occlusive disease was reviewed through the PubMed, EMBASE, and SCOPUS databases. All publication years were included through to November 2006. Studies were eligible for inclusion if they compared the accuracy of TOF or CE MRA for the detection of ICA disease against intra-arterial angiography and reported sufficient data. The overall sensitivity of TOF MRA for the detection of > or = 70% to 99% ICA stenoses was 91.2% (95% CI: 88.9% to 93.1%) with a specificity of 88.3% (86.7% to 89.7%), whereas the sensitivity of CE MRA was 94.6% (92.4% to 96.4%) with a specificity of 91.9% (90.3% to 93.4%). For the detection of ICA occlusions, the sensitivity of TOF MRA was 94.5% (91.2% to 96.8%) and the specificity was 99.3% (98.9% to 99.6%), whereas the sensitivity and specificity values for CE MRA were 99.4% (96.8% to 100%) and 99.6% (99.2% to 99.9%), respectively. For moderately severe (50% to 69%) stenoses, TOF MRA had a sensitivity of only 37.9% (29.3% to 47.1%) and a specificity of 92.1% (89.6% to 94.1%); for CE MRA, the pooled sensitivity value was somewhat better at 65.9% (57.0% to 74.0%), whereas the specificity was 93.5% (91.3% to 95.3%). TOF MRA and CE MRA showed high accuracy for the detection of high-grade ICA stenoses and occlusions with CE MRA having the edge over TOF MRA, but had only poor (TOF MRA) to fair (CE MRA) sensitivity for the detection of moderately severe stenoses.

Cerebrovascular segmentation from TOF-MRA based on multiple-U-net with focal loss function

Purpose To evaluate and compare the performance of acceleration-selective arterial spin labeling (AccASL) magnetic resonance (MR) angiography in the visualization of cerebral arteries and collateral vessels in patients with Moyamoya disease with that of time-of-flight (TOF) MR angiography, with digital subtraction angiography (DSA) as the reference standard. Materials and Methods Thirty-six cerebral hemispheres from 22 patients with Moyamoya disease underwent TOF and AccASL MR angiography and DSA. Qualitative evaluations included imaging of the terminal internal carotid artery (ICA), distal middle cerebral arteries (MCAs), Moyamoya vessels, and leptomeningeal anastomosis (LMA) collaterals with reference to DSA. Quantitative evaluations included assessment of contrast-to-noise ratio (CNR) and number of vessels in MCA branches. The linear mixed-effect model was used to compare the two methods. Results Mean scores for qualitative evaluation were significantly higher with AccASL angiography than with TOF angiography for imaging distal MCAs (3.9 ± 0.3 [standard deviation] vs 2.9 ± 1.1; P < .001), Moyamoya vessels (3.6 ± 0.6 vs 2.7 ± 0.9, P < .001), and LMA collaterals (3.8 ± 0.6 vs 1.8 ± 0.7, P < .001). Scores for steno-occlusive degree around the terminal ICAs were better with TOF angiography than with AccASL angiography (2.6 ± 0.5 vs 2.4 ± 0.6, P = .023). CNRs in the M4 segment were significantly higher with AccASL angiography (11.9 ± 12.9, P < .001) than with TOF angiography (4.1 ± 7.9). The number of vessels was significantly higher with AccASL angiography (18.3 ± 5.0, P < .001) than with TOF angiography (8.9 ± 4.9). The increase in the number of vessels from TOF angiography to AccASL angiography was greater in patients with severe ICA steno-occlusion (late ICA stage group, 11.4 ± 4.5; early ICA stage group, 6.8 ± 4.0; P = .007) and well-developed leptomeningeal anastomosis (mildly developed LMA group, 7.1 ± 4.3; well-developed LMA group, 11.3 ± 4.5; P = .011). Conclusion AccASL MR angiography enables better visualization of distal cerebral arteries and collateral vessels in patients with Moyamoya disease than does TOF MR angiography, while TOF MR angiography enables better visualization of stenosis of proximal arteries. Both methods work in a mutually beneficial manner in the assessment of cerebral arteries. © RSNA, 2017 Online supplemental material is available for this article.

To evaluate and compare the diagnostic accuracy of duplex ultrasound (US) and MR angiography (MRA) at 1.0 T in aortoiliac arterial disease using digital subtraction angiography (DSA) as the reference standard. In addition, a comparison of the 2D time-of-flight (TOF) and 3D contrast-enhanced MRA (CE MRA) techniques was performed. Prospectively, 39 patients with symptoms of lower-extremity arterial occlusive disease were examined using US, TOF MRA, CE MRA and DSA. Significant lesions (stenosis > or =50%) and occlusions were evaluated blindly for each method. For all segments, the sensitivity for US, TOF MRA and CE MRA with regard to significant lesions was 0.72, 0.81 and 0.81, respectively, and the specificity for each was 0.97, 0.91 and 0.92, respectively. For significant lesions above the inguinal ligament the corresponding sensitivity was 0.84, 0.89 and 0.94 and the specificity 0.93, 0.82 and 0.73, respectively. The specificity was higher when the two MRA methods were combined. TOF MRA overgraded 7 segments as occluded. In most cases, the length of the occlusions was correctly determined on CE MRA, overestimated on TOF MRA and uncertain on US. Neither US nor MRA were sufficiently accurate to fully replace angiography. MRA was preferable to US as a non-invasive test when vascular intervention was contemplated. Although CE MRA was superior to TOF MRA, the most accurate results were achieved when the two methods were combined.

Low-profile, self-expandable stents are used to treat wide-neck aneurysms located on the smaller distal intracranial arteries. This study aimed to assess the usefulness of time-of-flight (TOF) and contrast-enhanced (CE) magnetic resonance angiography (MRA) for follow-up after LEO Baby stent (LBS)-assisted coil embolization. Twenty-four aneurysms treated with LBS-assisted coil embolization were evaluated. Researchers reviewed TOF MRA and CE MRA images in terms of occlusion and stent patency. Aneurysm occlusion was graded according to Raymond-Roy classification as follows: total occlusion (grade 1), residual neck (grade 2), and residual aneurysm (grade 3). Stent patency was scored as follows: occlusion (1), stenosis (2), and normal (3). Interobserver and intermodality agreement values were determined by weighted kappa (κ) statistics. Intermodality and interobserver values of TOF MRA and CE MRA with digital subtraction angiography (DSA) were perfect (κ = 1.00, p < 0.001) in terms of aneurysm occlusion. Rate of stent occlusion and stenosis in DSA, TOF, and MRA, respectively, were as follows: 0 and 12.5%, 16.6 and 70.8%, and 0 and 62.5%. Intermodality agreement values of TOF MRA and CE MRA with DSA were insignificant in terms of stent patency (κ = 0.065, p = 0.27; κ = 0.158, p = 0.15, respectively). Interobserver agreement was substantial in both TOF MRA (κ = 0.71, p < 0.001) and CE MRA (κ = 0.64, p = 0.001). Both TOF and CE MRA techniques have strong concordance with DSA for the detection of aneurysm occlusion status. CE MRA can be used as a first-line noninvasive imaging modality due to its superiority to TOF MRA with respect to the visualization of in-stent signals.

To determine the feasibility of using ferumoxytol-enhanced magnetic resonance (MR) angiography to depict the vasculature of hemodialysis fistulas and improve image quality compared with nonenhanced time-of-flight (TOF) MR angiography. The study was institutional review board approved and was in compliance with HIPAA regulations. All participants provided written informed consent. TOF and first-pass ferumoxytol-enhanced MR angiography were performed in 10 patients with upper extremity autogenous fistulas. Ferumoxytol was administered as a bolus solution containing 430 μmol of elemental iron. A qualitative comparison was performed on maximum intensity projection images. Lumen depiction was evaluated by using a five-point scale. The uniformity of intraluminal signal intensity was measured as the ratio between the mean signal intensity of the entirety of the imaged fistula and its standard deviation. The contrast-to-noise ratio (CNR) between intraluminal signal and adjacent tissue was evaluated as a function of image acquisition time. Lumen depiction scores, luminal signal heterogeneity, and CNR efficiency were compared between TOF and ferumoxytol-enhanced MR angiography by using a Wilcoxon-Mann-Whitney test. Flow artifacts were greatly reduced by the use of ferumoxytol-enhanced MR angiography. Ferumoxytol-enhanced MR angiography had significantly better performance than TOF MR angiography as measured with the following: lumen depiction scores in all segments (mean, 4.7±0.1 [standard error of the mean]; vs 3.0±0.3 for arterial inflow, 4.1±0.3 vs 1.9±0.3 for arterial outflow, 3.7±0.3 vs 1.8±0.2 for anastomosis, and 4.5±0.2 vs 2.1±0.2 for venous outflow; P<.001), intraluminal signal homogeneity (0.3±0.02 vs 0.4±0.06, P=.005), and CNR efficiency in the venous outflow (5.1±0.6 vs 2.5±0.4, P=.01). This study demonstrates the feasibility of using ferumoxytol-enhanced MR angiography in imaging hemodialysis fistulas with consistently superior image quality compared with nonenhanced TOF MR angiography.

Evidence of intracranial venous reflux flow due to jugular venous reflux (JVR) on time of flight (TOF) MR angiography (MRA) is thought to be highly associated with transient global amnesia (TGA)-evidence that supports the venous congestion theory of TGA pathophysiology. However, recent studies indicate that intracranial JVR on TOF MRA is occasionally observed in normal elderly. Therefore, the purpose of this study was to compare the prevalence of intracranial JVR on TOF MRA in patients with TGA and two control groups. Three age- and sex-matched groups of subjects that received MRI and MRA were enrolled. The groups comprised 167 patients with TGA, 167 visitors to the emergency room (ER) and 167 visitors to a health promotion centre (HPC). Intracranial JVR was defined as abnormal venous signals in the inferior petrosal, sigmoid and/or transverse sinuses on TOF MRA. The prevalence of intracranial JVR was assessed across the three groups. Intracranial JVR was seen in seven (4.2 %) TGA patients, eight (4.8 %) ER visitors and three (1.8 %) HPC visitors, respectively. No statistically significant differences were observed among the three groups. TGA patients showed a low prevalence of intracranial JVR on TOF MRA, and no statistical differences were found in comparison with control groups.

A non-invasive, reliable imaging modality that characterizes cavernous sinus dural arteriovenous fistula (CSDAVF) is beneficial for diagnosis and to assess resolution on follow-up. To assess the utility of 3D time-of-flight (TOF) and silent magnetic resonance angiography (MRA) for evaluation of CSDAVF from an endovascular perspective. This prospective study included 37 patients with CSDAVF, who were subjected to digital subtraction angiography (DSA) and 3-T MR imaging with 3D TOF and silent MRA. The main arterial feeders, fistula site, and venous drainage pattern were evaluated, and the results were compared with DSA findings. The diagnostic confidence scores were also recorded using a 4-point Likert scale. Silent MRA correlated better for shunt site localization and angiographic classification (86% vs. 75% and 83% vs. 75%, respectively) compared to TOF MRA. The proportion of arterial feeders detected was marginally significant for silent MRA over TOF MRA sequences (92.8% vs. 89.5%; P=0.048), though for veins both were comparable. Sensitivity of silent MRA was higher for identification of cortical venous reflux (CVR) (90.9% vs. 81.8%) and deep venous drainage (82.4% vs. 64.7%), while specificity was >90% for both modalities. The overall diagnostic confidence score fared better for silent MRA for venous assessment (P < 0.001) as well as fistula point identification (P < 0.001), while no significant difference was evident with TOF MRA for arterial feeders (P=0.06). Various angiographic components of CSDAVF could be identified and delineated by 3D TOF and silent MRA, though silent MRA was superior for overall diagnostic assessment.

The purpose of this study is to evaluate feasibility, image quality (IQ), and accuracy of noncontrast hybrid arterial spin labeling (NoHASL) magnetic resonance angiography (MRA) compared with time of flight (TOF) MRA and contrast-enhanced (CE) MRA in patients with known/suspected cerebrovascular ischemia. Thirty inpatients were imaged at 1.5 T. Two neuroradiologists assessed 630 intracranial arterial segments for IQ (1, nondiagnostic; 3, satisfactory for diagnosis; and 5, excellent). Hemodynamically significant stenosis (>50%) was assessed against all combined techniques as reference. The NoHASL MRA IQ was diagnostic (3.32 ± 0.86) but affected by signal to noise ratio and spatial resolution limitations and significantly inferior to TOF (3.48 ± 0.68) and CE MRA (3.44 ± 0.78) (P < 0.0001 in both comparisons). Fourteen (2.2%) of 630 segments had hemodynamically significant stenoses at the reference standard. Sensitivity/specificity was not significantly different between techniques: NoHASL MRA, 67.9%/90.0%; TOF MRA, 67.9%/97.7%; and CE MRA, 50.0%/98.7%. The NoHASL MRA is feasible, with diagnostic quality imaging of proximal intracranial vessels. Low disease prevalence limited the assessment of technique accuracy.

Objective and background This study aimed to develop a deep convolutional neural network (DCNN) model capable of generating synthetic 4D magnetic resonance angiography (MRA) from 3D time-of-flight (TOF) images, allowing estimation of temporal changes in arterial flow. TOF MRA provides static information about arterial structures through maximum intensity projection (MIP) processing, but it does not capture the dynamic information of contrast agent circulation, which is lost during MIP processing. Considering the principles of TOF, it is hypothesized that dynamic information about arterial blood flow is latent within TOF signals. Although arterial spin labeling (ASL) can extract dynamic arterial information, ASL MRA has drawbacks, such as longer imaging times and lower spatial resolution than TOF MRA. This study's primary aim is to extend the utility of TOF MRA by training a machine-learning model on paired TOF and ASL data to extract latent dynamic information from TOF signals. Methods A DCNN combining a modified U-Net and a long-short-term memory (LSTM) network was trained on a dataset of 13 subjects (11 menand two women, aged 42-77 years) using paired 3D TOF MRA and 4D ASL MRA images. Subjects had no history of cerebral vessel occlusion or significant stenosis. The dataset was acquired using a 3T MRI system with a 32-channel head coil. Preprocessing involved resampling and intensity normalization of TOF and ASL images, followed by data augmentation and arterial mask generation. The model learned to extract flow information from TOF images and generate 8-phase 4D MRA images. The precision of flow estimation was evaluated using the coefficient of determination (R²) and Bland-Altman analysis. A board-certified neuroradiologist validated the quality of the images and the absence of significant stenosis in the major cerebral arteries. Results The generated 4D MRA images closely resembled the ground-truth ASL MRA data, with R² values of 0.92, 0.85, and 0.84 for the internal carotid artery (ICA), proximal middle cerebral artery (MCA), and distal MCA, respectively. Bland-Altman analysis revealed a systematic error of -0.06, with 95% agreement limits ranging from -0.18 to 0.12. Additionally, the model successfully identified flow abnormalities in a subject with left MCA stenosis, displaying a delayed peak and subsequent flattening distal to the stenosis, indicative of reduced blood flow. Visualization of the predicted arterial flow overlaid on the original TOF MRA images highlighted the spatial progression and dynamics of the flow. Conclusions The DCNN model effectively generated synthetic 4D MRA images from TOF images, demonstrating its potential to estimate temporal changes in arterial flow accurately. This non-invasive technique offers a promising alternative to conventional methods for visualizing and evaluating healthy and pathological flow dynamics. It has significant potential to improve the diagnosis and treatment of cerebrovascular diseases by providing detailed temporal flow information without the need for contrast agents or invasive procedures. The practical implementation of this model could enable the extraction of dynamic cerebral blood flow information from routine brain MRI examinations, contributing to the early diagnosis and management of cerebrovascular disorders.

The variability of the strength (increase or decrease) of the blood flow signals throughout the range of slices of the MRA volume is a big challenge for any segmentation approach because it introduces more inhomogenities to the MRA data and hence less accuracy. In this paper, a novel cerebral blood vessel segmentation framework using Time-Of-Flight Magnetic Resonance Angiography (TOF-MRA) is proposed to handle this challenge. The segmentation framework is based on using three dimensional convolutional neural networks (3D-CNN) to segment the cerebral blood vessels taking into account the variability of blood flow signals throughout the MRA scans. It consists of the following two steps: i) bias field correction to handle intensity inhomogeneity which are caused by magnetic settings, ii)instead of constructing one CNN model for the whole TOF-MRA brain, the TOF-MRA volume is divided into two compartments, above Circle of Willis (CoW) and at and below CoW to account for blood flow signals variability across the MRA volume‘s slices, then feed these two volumes into the three dimensional convolutional neural networks (3D-CNN). The final segmentation result is the combination of the output of each model. The proposed framework is tested on in-vivo data (30 TOF-MRA data sets). Both qualitative and quantitative validation with respect to ground truth (delineated by an MRA expert) are provided. The proposed approach achieved a high segmentation accuracy with 84.37% Dice similarity coefficient, sensitivity of 86.14%, and specificity of 99.00%.

Application and evaluation of non-invasive examination for Budd-Chiari syndrome

This trial assessed diagnostic accuracy of contrast-enhanced magnetic resonance angiography (MRA) with meglumine gadoterate (Gd-DOTA) at 3 Tesla (T) over unenhanced MRA at 3 T in non-coronary arterial diseases by comparing their accuracy with that of the gold standard, x-ray angiography. Ninety-two patients with suspected non-coronary arterial disease underwent in fixed sequence unenhanced time-of flight (TOF) MRA, contrast-enhanced MRA using a Gd-DOTA bolus (intravenous bolus 0.1 mmol/kg) and x-ray angiography. Eighty-four patients (71 male, 13 female; median age 64.5 years) were included in an intent-to-treat efficacy analysis. Targeted vascular areas were aorto-iliac, calf, carotid, femoral, popliteal and renal. Within-patient accuracy was significantly higher with contrast-enhanced MRA using Gd-DOTA than with unenhanced MRA (p = 0.0003). There was 84.4 +/- 17.5% agreement between contrast-enhanced MRA (Gd-DOTA) and x-ray angiography, compared with 76.8 +/- 20.4% between non-enhanced MRA and x-ray angiography. Sensitivity and specificity were also better with Gd-DOTA compared with non-enhanced MRA at the segment level. Duration of the MRA procedure was 3.5 times shorter with Gd-DOTA compared with non-enhanced MRA. Six patients reported six mild or moderate adverse events. No serious adverse events occurred. Contrast-enhanced MRA using Gd-DOTA at 3 T was superior to unenhanced TOF MRA in the vascular territories investigated.

BackgroundThree-dimensional time-of-flight magnetic resonance angiography (TOF-MRA) is a largely adopted non-invasive technique for assessing cerebrovascular diseases. We aimed to optimize the 7-T TOF-MRA acquisition protocol, confirm that it outperforms conventional 3-T TOF-MRA, and compare 7-T TOF-MRA with digital subtraction angiography (DSA) in patients with different vascular pathologies.MethodsSeven-tesla TOF-MRA sequences with different spatial resolutions acquired in four healthy subjects were compared with 3-T TOF-MRA for signal-to-noise and contrast-to-noise ratios as well as using a qualitative scale for vessel visibility and the quantitative Canny algorithm. Four patients with cerebrovascular disease (primary arteritis of the central nervous system, saccular aneurism, arteriovenous malformation, and dural arteriovenous fistula) underwent optimized 7-T TOF-MRA and DSA as reference. Images were compared visually and using the complex-wavelet structural similarity index.ResultsContrast-to-noise ratio was higher at 7 T (4.5 ± 0.8 (mean ± standard deviation)) than at 3 T (2.7 ± 0.9). The mean quality score for all intracranial vessels was higher at 7 T (2.89) than at 3 T (2.28). Angiogram quality demonstrated a better vessel border detection at 7 T than at 3 T (44,166 versus 28,720 pixels). Of 32 parameters used for diagnosing cerebrovascular diseases on DSA, 27 (84%) were detected on 7-T TOF-MRA; the similarity index ranged from 0.52 (dural arteriovenous fistula) to 0.90 (saccular aneurysm).ConclusionsSeven-tesla TOF-MRA outperformed conventional 3-T TOF-MRA in evaluating intracranial vessels and exhibited an excellent image quality when compared to DSA. Seven-tesla TOF-MRA might improve the non-invasive diagnostic approach to several cerebrovascular diseases.Relevance statementAn optimized TOF-MRA sequence at 7 T outperforms 3-T TOF-MRA, opening perspectives to its clinical use for noninvasive diagnosis of paradigmatic pathologies of intracranial vessels.Key points• An optimized 7-T TOF-MRA protocol was selected for comparison with clinical 3-T TOF-MRA for assessing intracranial vessels.• Seven-tesla TOF-MRA outperformed 3-T TOF-MRA in both quantitative and qualitative evaluation.• Seven-tesla TOF-MRA is comparable to DSA for the diagnosis and characterization of intracranial vascular pathologies.Graphical