Time-of-flight magnetic resonance angiography (TOF-MRA) is a non-contrast technique used to visualize neurovascular. However, manual reconstruction of the volume render (VR) by radiologists is time-consuming and labor-intensive. Deep learning-based (DL-based) vessel segmentation technology may provide intelligent automation workflow. To evaluate the image quality of DL vessel segmentation for automatically acquiring intracranial arteries in TOF-MRA. A total of 394 TOF-MRA scans were selected, which included cerebral vascular health, aneurysms, or stenoses. Both our proposed method and two state-of-the-art DL methods are evaluated on external datasets for generalization ability. For qualitative assessment, two experienced clinical radiologists evaluated the image quality of cerebrovascular diagnostic and visualization (scoring 0-5 as unacceptable to excellent) obtained by manual VR reconstruction or automatic convolutional neural network (CNN) segmentation. The proposed CNN outperforms the other two DL-based methods in clinical scoring on external datasets, and its visualization was evaluated by readers as having the appearance of the radiologists\' manual reconstructions. Scoring of proposed CNN and VR of intracranial arteries demonstrated good to excellent agreement with no significant differences (median, 5.0 and 5.0, P ≥ 12) at healthy-type scans. All proposed CNN image quality were considered to have adequate diagnostic quality (median scores > 2). Quantitative analysis demonstrated a superior dice similarity coefficient of cerebrovascular overlap (training sets and validation sets; 0.947 and 0.927). Automatic cerebrovascular segmentation using DL is feasible and the image quality in terms of vessel integrity, collateral circulation and lesion morphology is comparable to expert manual VR without significant differences.

OBJECTIVE: Accurate nidus segmentation and quantification have long been challenging but important tasks in the clinical management of Cerebral Arteriovenous Malformation (CAVM). However, there are still dilemmas in nidus segmentation, such as difficulty defining the demarcation of the nidus, observer-dependent variation and time consumption. The aim of this study isto develop an artificial intelligence model to automatically segment the nidus on Time-Of-Flight Magnetic Resonance Angiography (TOF-MRA) images.
METHODS: A total of 92patients with CAVM who underwent both TOF-MRA and DSA examinations were enrolled. Two neurosurgeonsmanually segmented the nidusonTOF-MRA images,which were regarded as theground-truth reference. AU-Net-basedAImodelwascreatedfor automatic nidus detectionand segmentationonTOF-MRA images.
RESULTS: The meannidus volumes of the AI segmentationmodeland the ground truthwere 5.427 ± 4.996 and 4.824 ± 4.567 mL,respectively. The meandifference in the nidus volume between the two groups was0.603 ± 1.514 mL,which wasnot statisticallysignificant (P = 0.693). The DSC,precision and recallofthe testset were 0.754 ± 0.074, 0.713 ± 0.102 and 0.816 ± 0.098, respectively. The linear correlation coefficient of the nidus volume betweenthesetwo groupswas 0.988, p < 0.001.
CONCLUSIONS: The performance of the AI segmentationmodel is moderate consistent with that of manual segmentation. This AI model has great potential in clinical settings, such as preoperative planning, treatment efficacy evaluation, riskstratification and follow-up.

To validate the correlation between the signal intensity gradient (SIG) from time-of-flight magnetic resonance angiography (TOF-MRA) and wall shear stress (WSS) determined by phase contrast magnetic resonance (PC-MR), we conducted both experimental and human studies. In the experimental study, we measured WSS in four tubes of different sizes with variable flow rates using PC-MR and TOF-MRA. The flow rates of water in the experimental study ranged from 0.06 to 12.75 mL/s, resulting in PC-WSS values between 0.1 and 1.6 dyne/cm2. The correlation between PC-WSS and SIG was statistically significant, showing a coefficient of 0.86 (P < 0.001, R2 = 0.75). The line fit provided the conversion equation as Y = 1.6287X - 1.1563 (Y = PC-WSS, X = SIG). For the human study, 28 subjects underwent TOF-MRA and PC-MR examinations of carotid and vertebral arteries. Arterial PC-WSS and SIG were determined in the same segment for each subject. The arterial PC-WSS ranged from 1.9 to 21.0 dyne/cm2. Both carotid and vertebral arteries showed significant correlations between PC-WSS and SIG, with coefficients of 0.85, 0.86, 0.91, and 0.81 in the right and left carotid and vertebral arteries, respectively. Our results show that SIG from TOF-MRA and SIG-WSS derived from the conversion equation provide concurrent in vivo hemodynamic information on arterial shear stress. This study was registered on ClinicalTrials.gov with the identifier NCT04585971 on October 14, 2020.

UNASSIGNED: Lenticulostriate infarction requires further research of arterial hemodynamic factors, as the disease is diagnosed in the absence of major arterial stenosis or cardioembolism.
UNASSIGNED: In this multicenter retrospective cohort study, we included patients who were hospitalized for lenticulostriate infarction from January 2015 to March 2021 at three stroke centers in South Korea. We obtained hemodynamic information on cerebral arteries using signal intensity gradient (SIG), an in-vivo approximated wall shear stress (WSS) derived from Time-of-Flight Magnetic Resonance Angiography (TOF-MRA). A favorable outcome was defined as a modified Rankin Scale of 0 to 2 at hospital discharge.
UNASSIGNED: A total of 294 patients were included, of whom 146 (49.7%) had an unfavorable outcome. The unfavorable outcome group showed significantly lower SIG in both middle cerebral arteries (MCAs) than the favorable group (5.2 ± 1.2 SI/mm vs. 5.9 ± 1.2, p < 0.001), and similar findings were observed in other cerebral arteries. The SIGs in both MCAs were independently associated with favorable outcome, with an odds ratio of 1.42 (95% confidence interval, 1.11-1.80; p = 0.005) for the right MCA and 1.49 (95% CI, 1.15-1.93; p = 0.003) for the left MCA, after adjusting for potential confounders. Similar findings were observed in other cerebral artery SIGs.
UNASSIGNED: Cerebral artery SIG from TOF-MRA was significantly associated with short-term functional outcomes in patients with lenticulostriate infarction. Further studies are needed to investigate the temporal relationships of SIG in patients with cerebral infarction.

The delineation of brain arteriovenous malformations (bAVMs) is crucial for subsequent treatment planning. Manual segmentation is time-consuming and labor-intensive. Applying deep learning to automatically detect and segment bAVM might help to improve clinical practice efficiency.
To develop an approach for detecting bAVM and segmenting its nidus on Time-of-flight magnetic resonance angiography using deep learning methods.
Retrospective.
221 bAVM patients aged 7-79 underwent radiosurgery from 2003 to 2020. They were split into 177 training, 22 validation, and 22 test data.
1.5 T, Time-of-flight magnetic resonance angiography based on 3D gradient echo.
The YOLOv5 and YOLOv8 algorithms were utilized to detect bAVM lesions and the U-Net and U-Net++ models to segment the nidus from the bounding boxes. The mean average precision, F1, precision, and recall were used to assess the model performance on the bAVM detection. To evaluate the model\'s performance on nidus segmentation, the Dice coefficient and balanced average Hausdorff distance (rbAHD) were employed.
The Student\'s t-test was used to test the cross-validation results (P < 0.05). The Wilcoxon rank test was applied to compare the median for the reference values and the model inference results (P < 0.05).
The detection results demonstrated that the model with pretraining and augmentation performed optimally. The U-Net++ with random dilation mechanism resulted in higher Dice and lower rbAHD, compared to that without that mechanism, across varying dilated bounding box conditions (P < 0.05). When combining detection and segmentation, the Dice and rbAHD were statistically different from the references calculated using the detected bounding boxes (P < 0.05). For the detected lesions in the test dataset, it showed the highest Dice of 0.82 and the lowest rbAHD of 5.3%.
This study showed that pretraining and data augmentation improved YOLO detection performance. Properly limiting lesion ranges allows for adequate bAVM segmentation.
4 TECHNICAL EFFICACY STAGE: 1.

OBJECTIVE: Flow re-direction endoluminal device (FRED) is a novel dual-layer flow-diverting stent to treat cerebral aneurysms with high obliteration rates, however, it induces inevitable metal-related artifacts. We compared silent magnetic resonance angiography (MRA), a new MRA method using ultra-short time of echo and arterial spin-labeling, with conventional time-of-flight (TOF)-MRA for imaging aneurysms treated using FRED.
METHODS: Between May 2020 and September 2022, 16 patients with unruptured internal carotid aneurysms treated using FRED simultaneously underwent silent MRA and TOF-MRA after treatment, with 36 follow-up sessions in total. Two observers independently graded the quality of intra-aneurysmal flow and stented parent arteries under both types of MRA from 1 (not visible) to 4 (nearly equal to digital subtraction angiography [DSA]), with reference to DSA images as a standard criterion.
RESULTS: The mean scores for intra-aneurysmal flow and stented parent arteries were significantly better for silent MRA (3.93  ±  0.21 and 3.82  ±  0.32, respectively) than for TOF-MRA (2.08  ±  0.99 and 1.92  ±  0.79, respectively) (P < 0.01). Intermodality agreements for intra-aneurysmal flow and stented parent arteries were 0.87 and 0.90, respectively.
CONCLUSIONS: Silent MRA is superior to TOF-MRA for assessing patients treated with FRED, with potential as an alternative imaging modality to DSA.

暂无摘要。

Segmenting vessels in brain images is a critical step for many medical interventions and diagnoses of illnesses. Recent advances in artificial intelligence provide better models, achieving a human-like level of expertise in many tasks. In this paper, we present a new approach to segment Time-of-Flight Magnetic Resonance Angiography (TOF-MRA) images, relying on fewer training samples than state-of-the-art methods. We propose a conditional generative adversarial network with an adapted generator based on a concatenated U-Net with a residual U-Net architecture (UUr-cGAN) to carry out blood vessel segmentation in TOF-MRA images, relying on data augmentation to diminish the drawback of having few volumes at disposal for training the model, while preventing overfitting by using regularization techniques. The proposed model achieves 89.52% precision and 87.23% in Dice score on average from the cross-validated experiment for brain blood vessel segmentation tasks, which is similar to other state-of-the-art methods while using considerably fewer training samples. UUr-cGAN extracts important features from small datasets while preventing overfitting compared to other CNN-based methods and still achieve a relatively good performance in image segmentation tasks such as brain blood vessels from TOF-MRA.

BACKGROUND: 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.
OBJECTIVE: To assess the utility of 3D time-of-flight (TOF) and silent magnetic resonance angiography (MRA) for evaluation of CSDAVF from an endovascular perspective.
METHODS: 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.
RESULTS: 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).
CONCLUSIONS: 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.

Objectives: To investigate the association between radiomics features and epilepsy in patients with unruptured brain arteriovenous malformations (bAVMs) and to develop a prediction model based on radiomics features and clinical characteristics for bAVM-related epilepsy. Methods: This retrospective study enrolled 176 patients with unruptured bAVMs. After manual lesion segmentation, a total of 858 radiomics features were extracted from time-of-flight magnetic resonance angiography (TOF-MRA). A radiomics model was constructed, and a radiomics score was calculated. Meanwhile, the demographic and angioarchitectural characteristics of patients were assessed to build a clinical model. Incorporating the radiomics score and independent clinical risk factors, a combined model was constructed. The performance of the models was assessed with respect to discrimination, calibration, and clinical usefulness. Results: The clinical model incorporating 3 clinical features had an area under the curve (AUC) of 0.71. Fifteen radiomics features were used to build the radiomics model, which had a higher AUC of 0.78. Incorporating the radiomics score and clinical risk factors, the combined model showed a favorable discrimination ability and calibration, with an AUC of 0.82. Decision curve analysis (DCA) demonstrated that the combined model outperformed the clinical model and radiomics model in terms of clinical usefulness. Conclusions: The radiomics features extracted from TOF-MRA were associated with epilepsy in patients with unruptured bAVMs. The radiomics-clinical nomogram, which was constructed based on the model incorporating the radiomics score and clinical features, showed favorable predictive efficacy for bAVM-related epilepsy.