Search Results (20)

Background: Accurate detection of intracranial aneurysms, especially those smaller than 3 mm, remains a critical challenge in neurovascular imaging due to their subtle morphology and low contrast in Time-of-Flight Magnetic Resonance Angiography (TOF-MRA) scans. This study presents a Mask R-CNN-based deep learning framework designed to automatically detect and segment intracranial aneurysms, with specific architectural modifications aimed at improving sensitivity to small lesions. Method: A dataset of 447 TOF-MRA volumes (161 aneurysmal, 286 healthy) was used, with patient-level deduplication and 5-fold cross-validation to ensure robust evaluation. Bayesian hyperparameter optimization was applied using Optuna, and two key innovations were introduced: a Small Object Aware ROI Head to better capture micro-aneurysms and customized anchor configurations to improve region proposal quality. Healthy scans were incorporated as negative samples to enhance background modeling, and targeted data augmentation increased model generalization. Results: The proposed model achieved a Dice coefficient of 0.8832, precision of 0.9404, and sensitivity (recall) of 0.8677, with consistent performance across aneurysm sizes. Conclusions: These results demonstrate that the integration of architectural innovations, automated optimization, and negative-sample modeling enables a clinically viable deep learning tool that could serve as a reliable second-reader system for assisting radiologists in intracranial aneurysm detection. Full article

Accurate segmentation of brain vessels is critical for diagnosing cerebral stroke, yet existing AI-based methods struggle with challenges such as small vessel segmentation and class imbalance. To address this, our study proposes a novel 2D segmentation method based on the nnUNet framework, enhanced with MedSAM/MedSAM2 features, for arterial vessel segmentation in time-of-flight magnetic resonance angiography (TOF-MRA) brain slices. The approach first constructs a baseline segmentation network using nnUNet, then incorporates MedSAM/MedSAM2’s feature extraction module to enhance feature representation. Additionally, focal loss is introduced to address class imbalance. Experimental results on the CAS2023 dataset demonstrate that the MedSAM2-enhanced model achieves a 0.72% relative improvement in Dice coefficient and reduces HD95 (mm) and ASD (mm) from 48.20 mm to 46.30 mm and from 5.33 mm to 4.97 mm, respectively, compared to the baseline nnUNet, showing significant enhancements in boundary localization and segmentation accuracy. This approach addresses the critical challenge of small vessel segmentation in TOF-MRA, with the potential to improve cerebrovascular disease diagnosis in clinical practice. Full article

Background: Aneurysm-related subarachnoid hemorrhage is a life-threatening form of stroke. While medical image acquisition for aneurysm screening is limited to high-risk patients, advances in artificial intelligence (AI)-based image analysis suggest that AI-driven routine screening of imaging studies acquired for other clinical reasons could be valuable. Methods: A representative cohort of 1761 routine cranial magnetic resonance imaging scans [cMRIs] (with time-of-flight angiographies) from patients without previously known intracranial aneurysms was established by combining 854 general radiology 1.5T and 907 neuroradiology 3.0T cMRIs. TOF-MRAs were analyzed with a commercial AI algorithm for aneurysm detection. Neuroradiology consultants re-assessed cMRIs with AI results, providing Likert-based confidence scores (0–3) and work-up recommendations for suspicious findings. Original cMRI reports from more than 90 radiologists and neuroradiologists were reviewed, and patients with new findings were contacted for consultations including follow-up imaging (cMRI / catheter angiography [DSA]). Statistical analysis was conducted based on descriptive statistics, common diagnostic metrics, and the number needed to screen (NNS), defined as the number of cMRIs that must be analyzed with AI to achieve specific clinical endpoints. Results: Initial cMRI reporting by radiologists/neuroradiologists demonstrated a high risk of incidental aneurysm non-reporting (94.4% / 86.4%). A finding-based analysis revealed high AI algorithm sensitivities (100% [3T] / 94.1% [1.5T] for certain aneurysms of any size, well above 90% for any suspicious findings > 2 mm), associated with AI alerts triggered in 22% of cMRIs with PPVs of 7.5–25.2% (depending on the inclusion of inconclusive findings). The NNS to prompt further imaging work-/follow-up was 22, while the NNS to detect an aneurysm with a possible therapeutic impact was 221. Reference readings and patient consultations suggest that routine AI-driven cMRI screening would lead to additional imaging for 4–5% of patients, with 0.45% to 0.74% found to have previously undetected aneurysms with possibly therapeutic implications. Conclusions: AI-based second-reader screening substantially reduces incidental aneurysm non-reporting but may disproportionally increase follow-/work-up imaging demands also for minor or inconclusive findings with associated patient concern. Future research should focus on (subgroup-specific) AI optimization and cost-effectiveness analyses. Full article

Magnetic Resonance Angiography (MRA) is widely used for cerebrovascular assessment, with Time-of-Flight (TOF) MRA being a common non-contrast imaging technique. However, maximum intensity projection (MIP) images generated from TOF-MRA often include non-essential vascular structures such as external carotid branches, requiring manual editing for accurate visualization of intracranial arteries. This study proposes a deep learning-based semantic segmentation approach to automate the removal of these structures, enhancing MIP image clarity while reducing manual workload. Using DeepLab v3+, a convolutional neural network model optimized for segmentation accuracy, the method achieved an average Dice Similarity Coefficient (DSC) of 0.9615 and an Intersection over Union (IoU) of 0.9261 across five-fold cross-validation. The developed system processed MRA datasets at an average speed of 16.61 frames per second, demonstrating real-time feasibility. A dedicated software tool was implemented to apply the segmentation model directly to DICOM images, enabling fully automated MIP image generation. While the model effectively removed most external carotid structures, further refinement is needed to improve venous structure suppression. These results indicate that deep learning can provide an efficient and reliable approach for automated cerebrovascular image processing, with potential applications in clinical workflows and neurovascular disease diagnosis. Full article

Objectives: To quantify the clinical value of integrating a commercially available artificial intelligence (AI) algorithm for intracranial aneurysm detection in a screening setting that utilizes cranial magnetic resonance imaging (cMRI) scans acquired primarily for other clinical purposes. Methods: A total of 907 consecutive cMRI datasets, including time-of-flight-angiography (TOF-MRA), were retrospectively identified from patients unaware of intracranial aneurysms. cMRIs were analyzed by a commercial AI algorithm and reassessed by consultant-level neuroradiologists, who provided confidence scores and workup recommendations for suspicious findings. Patients with newly identified findings (relative to initial cMRI reports) were contacted for on-site consultations, including cMRI follow-up or catheter angiography. The number needed to screen (NNS) was defined as the cMRI quantity that must undergo AI screening to achieve various clinical endpoints. Results: The algorithm demonstrates high sensitivities (100% for findings >4 mm in diameter), a 17.8% MRA alert rate and positive predictive values of 11.5–43.8% (depending on whether inconclusive findings are considered or not). Initial cMRI reports missed 50 out of 59 suspicious findings, including 13 certain intradural aneurysms. The NNS for additionally identifying highly suspicious and therapeutically relevant (unruptured intracranial aneurysm treatment scores balanced or in favor of treatment) findings was 152. The NNS for recommending additional follow-/workup imaging (cMRI or catheter angiography) was 26, suggesting an additional up to 4% increase in imaging procedures resulting from a preceding AI screening. Conclusions: AI-powered routine screening of cMRIs clearly lowers the high risk of incidental aneurysm non-reporting but results in a substantial burden of additional imaging follow-up for minor or inconclusive findings. Full article

Purpose: The purpose of this study is to improve the qualitative and quantitative image quality of the time-resolved angiography with interleaved stochastic trajectories technique (4D-TWIST-MRA) using deep neural network (DNN)-based MR image reconstruction software. Materials and Methods: A total of 520 consecutive patients underwent 4D-TWIST-MRA for ischemic stroke or intracranial vessel stenosis evaluation. Four-dimensional DNN-reconstructed MRA (4D-DNR) was generated using commercially available software (SwiftMR v.3.0.0.0, AIRS Medical, Seoul, Republic of Korea). Among those evaluated, 397 (76.3%) patients received concurrent time-of-flight MRA (TOF-MRA) to compare the signal-to-noise ratio (SNR), image quality, noise, sharpness, vascular conspicuity, and degree of venous contamination with a 5-point Likert scale. Two radiologists independently evaluated the detection rate of intracranial aneurysm in TOF-MRA, 4D-TWIST-MRA, and 4D-DNR in separate sessions. The other 123 (23.7%) patients received 4D-TWIST-MRA due to a suspicion of acute ischemic stroke. The confidence level and decision time for large vessel occlusion were evaluated in these patients. Results: In qualitative analysis, 4D-DNR demonstrated better overall image quality, sharpness, vascular conspicuity, and noise reduction compared to 4D-TWIST-MRA. Moreover, 4D-DNR exhibited a higher SNR than 4D-TWIST-MRA. The venous contamination and aneurysm detection rates were not significantly different between the two MRA images. When compared to TOF-MRA, 4D-CE-MRA underestimated the aneurysm size (2.66 ± 0.51 vs. 1.75 ± 0.62, p = 0.029); however, 4D-DNR showed no significant difference in size compared to TOF-MRA (2.66 ± 0.51 vs. 2.10 ± 0.41, p = 0.327). In the diagnosis of large vessel occlusion, 4D-DNR showed a better confidence level and shorter decision time than 4D-TWIST-MRA. Conclusion: DNN reconstruction may improve the qualitative and quantitative image quality of 4D-TWIST-MRA, and also enhance diagnostic performance for intracranial aneurysm and large vessel occlusion. Full article

Background: Silent MRA has shown promising results in evaluating the stents used for intracranial aneurysm treatment. A deep learning-based denoising and deranging algorithm was recently introduced by GE HealthCare. The purpose of this study was to compare the performance of several MRA techniques regarding lumen visibility in silicone models with flow diverter stents. Methods: Two Surpass Evolve stents of different sizes were implanted in two silicone tubes. The tubes were placed in separate boxes in the straight position and in two different curve configurations and connected to a pulsatile pump to construct a flow loop. Using a 3.0T MRI scanner, TOF and silent MRA images were acquired, and deep learning reconstruction was applied to the silent MRA dataset. The intraluminal signal intensity in the stent (SI_in-stent), in the tube outside the stent (SI_vessel), and of the background (SI_bg) were measured for each scan. Results: The SI_in-stent/SI_bg and SI_in-stent/SI_v ratios were higher in the silent scans and DL-based reconstructions than in the TOF images. The stent tips created severe artefacts in the TOF images, which could not be observed in the silent scans. Conclusions: Our study demonstrates that the DL reconstruction algorithm improves the quality of the silent MRA technique in evaluating the flow diverter stent patency. Full article

Centerline tracking is useful in performing segmental analysis of vessel tortuosity in angiography data. However, a highly tortuous) artery can produce multiple centerlines due to over-segmentation of the artery, resulting in inaccurate path-finding results when using the shortest path-finding algorithm. In this study, the internal carotid arteries (ICAs) from three-dimensional (3D) time-of-flight magnetic resonance angiography (TOF MRA) data were used to demonstrate the effectiveness of a new path-finding method. The method is based on a series of depth-first searches (DFSs) with randomly different orders of neighborhood searches and produces an appropriate path connecting the two endpoints in the ICAs. It was compared with three existing methods which were (a) DFS with a sequential order of neighborhood search, (b) Dijkstra algorithm, and (c) A* algorithm. The path-finding accuracy was evaluated by counting the number of successful paths. The method resulted in an accuracy of 95.8%, outperforming the three existing methods. In conclusion, the proposed method has been shown to be more suitable as a path-finding procedure than the existing methods, particularly in cases where there is more than one centerline resulting from over-segmentation of a highly tortuous artery. Full article

Background: We aimed to evaluate the feasibility of a non-contrast time-of-flight magnetic resonance angiography (TOF-MRA) protocol for the pre-procedural access route assessment of transcatheter aortic valve implantation (TAVI) in comparison with contrast-enhanced cardiac dual-source computed tomography angiography (CTA). Methods and Results: In total, 51 consecutive patients (mean age: 82.69 ± 5.69 years) who had undergone a pre-TAVI cardiac CTA received TOF-MRA for a pre-procedural access route assessment. The MRA image quality was rated as very good (median of 5 [IQR 4–5] on a five-point Likert scale), with only four examinations rated as non-diagnostic. The TOF-MRA systematically underestimated the minimal effective vessel diameter in comparison with CTA (for the effective vessel diameter in mm, the right common iliac artery (CIA)/external iliac artery (EIA)/common femoral artery (CFA) MRA vs. CTA was 8.04 ± 1.46 vs. 8.37 ± 1.54 (p < 0.0001) and the left CIA/EIA/CFA MRA vs. CTA was 8.07 ± 1.32 vs. 8.28 ± 1.34 (p < 0.0001)). The absolute difference between the MRA and CTA was small (for the Bland–Altman analyses in mm, the right CIA/EIA/CFA was −0.36 ± 0.77 and the left CIA/EIA/CFA was −0.25 ± 0.61). The overall correlation between the MRA and CTA measurements was very good (with a Pearson correlation coefficient of 0.87 (p < 0.0001) for the right CIA/EIA/CFA and a Pearson correlation coefficient of 0.9 (p < 0.0001) for the left CIA/EIA/CFA). The feasibility agreement between the MRA and CTA for transfemoral access was good (the right CIA/EIA/CFA agreement was 97.9% and the left CIA/EIA/CFA agreement was 95.7%, Kohen’s kappa: 0.477 (p = 0.001)). Conclusions: The TOF-MRA protocol was feasible for the assessment of the access route in an all-comer pre-TAVI population. This protocol might be a reliable technique for patients at an increased risk of contrast-induced nephropathy. Full article

This study aimed to optimize velocity-selective magnetic resonance angiography (VS-MRA) protocols for whole-neck angiography and demonstrate its feasibility in healthy subjects with comparisons to clinical 3D time-of-flight (TOF) angiography. To help optimize VS-MRA protocols, 2D phase-contrast (PC) flow imaging and 3D B₀ and B₁ field mappings were performed on five healthy volunteers. Based on these measurements, a slab-selective (SS) inversion preparation was applied prior to a VS saturation preparation to further suppress venous blood, while the VS preparation pulse was designed with compensation for field offsets. VS-MRA and 3D TOF were performed on six healthy subjects, and relative contrast ratios (CRs) between artery and muscle signals were calculated for twenty arterial regions for comparisons. The pre-compensated VS pulse improved the visualization of the subclavian arteries and suppression of background tissues, which involved large B₀ and B₁ field errors. The combination of SS and VS preparations effectively suppressed venous blood. While the relative CR values were 0.78 ± 0.08 and 0.72 ± 0.10 for VS-MRA and 3D TOF, respectively, over the twenty segments, VS-MRA outperformed 3D TOF in visualizing arterial segments of a small size or with a horizontal orientation, such as subclavian, facial, and occipital arteries. The proposed neck VS-MRA with the field-error-compensated VS preparation combined with the SS preparation is feasible and superior to 3D TOF in visualizing small and/or horizontally oriented arterial segments. Full article

Blood vessels of the brain provide the human brain with the required nutrients and oxygen. As a vulnerable part of the cerebral blood supply, pathology of small vessels can cause serious problems such as Cerebral Small Vessel Diseases (CSVD). It has also been shown that CSVD is related to neurodegeneration, such as Alzheimer’s disease. With the advancement of 7 Tesla MRI systems, higher spatial image resolution can be achieved, enabling the depiction of very small vessels in the brain. Non-Deep Learning-based approaches for vessel segmentation, e.g., Frangi’s vessel enhancement with subsequent thresholding, are capable of segmenting medium to large vessels but often fail to segment small vessels. The sensitivity of these methods to small vessels can be increased by extensive parameter tuning or by manual corrections, albeit making them time-consuming, laborious, and not feasible for larger datasets. This paper proposes a deep learning architecture to automatically segment small vessels in 7 Tesla 3D Time-of-Flight (ToF) Magnetic Resonance Angiography (MRA) data. The algorithm was trained and evaluated on a small imperfect semi-automatically segmented dataset of only 11 subjects; using six for training, two for validation, and three for testing. The deep learning model based on U-Net Multi-Scale Supervision was trained using the training subset and was made equivariant to elastic deformations in a self-supervised manner using deformation-aware learning to improve the generalisation performance. The proposed technique was evaluated quantitatively and qualitatively against the test set and achieved a Dice score of 80.44 ± 0.83. Furthermore, the result of the proposed method was compared against a selected manually segmented region (62.07 resultant Dice) and has shown a considerable improvement (18.98%) with deformation-aware learning. Full article

The aim of our study was to compare compressed sensing (CS) time-of-flight (TOF) magnetic resonance angiography (MRA) with parallel imaging (PI) TOF MRA in the evaluation of patients with intracranial aneurysms treated with coil embolization or stent-assisted coiling. We enrolled 22 patients who underwent follow-up imaging after intracranial aneurysm coil embolization. All patients underwent both PI TOF and CS TOF MRA during the same examination. Image evaluation aimed to compare the performance of CS to PI TOF MRA in determining the degree of aneurysm occlusion, as well as the depiction of parent vessel and vessels adjacent to the aneurysm dome. The reference standard for the evaluation of aneurysm occlusion was PI TOF MRA. The inter-modality agreement between CS and PI TOF MRA in the evaluation of aneurysm occlusion was almost perfect (κ  =  0.98, p  <  0.001) and the overall inter-rater agreement was substantial (κ  =  0.70, p  <  0.001). The visualization of aneurysm parent vessel in CS TOF images compared with PI TOF images was evaluated to be better in 11.4%, equal in 86.4%, and worse in 2.3%. CS TOF MRA, with almost 70% scan time reduction with respect to PI TOF MRA, yields comparable results for assessing the occlusion status of coiled intracranial aneurysms. Short scan times increase patient comfort, reduce the risk of motion artifacts, and increase patient throughput, with a resulting reduction in costs. CS TOF MRA may therefore be a potential replacement for PI TOF MRA as a first-line follow-up examination in patients with intracranial aneurysms treated with coil embolization. Full article

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. Full article

This study aimed to develop a magnetic resonance imaging (MRI)-compatible flow delivery system and individualized models of circle of Willis (CoW), which include 50% and 100% blockage in internal carotid artery (ICA50 and ICA100), and 100% blockage in vertebral artery (VA100). Images were obtained using 3D time-of-flight and phase-contrast magnetic resonance angiography (MRA) sequences, and changes in velocity and flow direction at CoW models were analyzed. For the ICA50 and VA100 models, the flow was similar to that of the normal model. For the ICA 50 model, it was found that 50% blockage did not affect cerebral blood flow. For the VA100 model, decreased flow in the posterior cerebral artery and a change to the flow direction in the posterior communicating artery were found. For the ICA100 model, particularly, decreased flow in the ipsilateral middle and anterior cerebral arteries and a change to the flow direction in the ipsilateral anterior cerebral artery of the CoW were found. These results demonstrated that the flow system with various CoW disease models tailored to individual characteristics could be used to predict stroke onset more quickly. For the ICA50 and VA100 models, the possibility of cerebral infarction was significantly lower. On the other hand, for the ICA100 model, there was a high possibility of decreased flow, which could lead to cerebral infarction. Full article

Clinicians are often very sceptical about applying automatic image processing approaches, especially deep learning-based methods, in practice. One main reason for this is the black-box nature of these approaches and the inherent problem of missing insights of the automatically derived decisions. In order to increase trust in these methods, this paper presents approaches that help to interpret and explain the results of deep learning algorithms by depicting the anatomical areas that influence the decision of the algorithm most. Moreover, this research presents a unified framework, TorchEsegeta, for applying various interpretability and explainability techniques for deep learning models and generates visual interpretations and explanations for clinicians to corroborate their clinical findings. In addition, this will aid in gaining confidence in such methods. The framework builds on existing interpretability and explainability techniques that are currently focusing on classification models, extending them to segmentation tasks. In addition, these methods have been adapted to 3D models for volumetric analysis. The proposed framework provides methods to quantitatively compare visual explanations using infidelity and sensitivity metrics. This framework can be used by data scientists to perform post hoc interpretations and explanations of their models, develop more explainable tools, and present the findings to clinicians to increase their faith in such models. The proposed framework was evaluated based on a use case scenario of vessel segmentation models trained on Time-of-Flight (TOF) Magnetic Resonance Angiogram (MRA) images of the human brain. Quantitative and qualitative results of a comparative study of different models and interpretability methods are presented. Furthermore, this paper provides an extensive overview of several existing interpretability and explainability methods. Full article