autoTICI: Automatic Brain Tissue Reperfusion Scoring on 2D DSA Images of Acute Ischemic Stroke Patients

CAVE: Cerebral artery-vein segmentation in digital subtraction angiography

Cerebral X-ray digital subtraction angiography (DSA) is a widely used imaging technique in patients with neurovascular disease, allowing for vessel and flow visualization with high spatio-temporal resolution. Automatic artery-vein segmentation in DSA plays a fundamental role in vascular analysis with quantitative biomarker extraction, facilitating a wide range of clinical applications. The widely adopted U-Net applied on static DSA frames often struggles with disentangling vessels from subtraction artifacts. Further, it falls short in effectively separating arteries and veins as it disregards the temporal perspectives inherent in DSA. To address these limitations, we propose to simultaneously leverage spatial vasculature and temporal cerebral flow characteristics to segment arteries and veins in DSA. The proposed network, coined CAVE, encodes a 2D+time DSA series using spatial modules, aggregates all the features using temporal modules, and decodes it into 2D segmentation maps. On a large multi-center clinical dataset, CAVE achieves a vessel segmentation Dice of 0.84 (±0.04) and an artery-vein segmentation Dice of 0.79 (±0.06). CAVE surpasses traditional Frangi-based k-means clustering (P < 0.001) and U-Net (P < 0.001) by a significant margin, demonstrating the advantages of harvesting spatio-temporal features. This study represents the first investigation into automatic artery-vein segmentation in DSA using deep learning. The code is publicly available at https://github.com/RuishengSu/CAVE_DSA.

DIAS: A dataset and benchmark for intracranial artery segmentation in DSA sequences

The automated segmentation of Intracranial Arteries (IA) in Digital Subtraction Angiography (DSA) plays a crucial role in the quantification of vascular morphology, significantly contributing to computer-assisted stroke research and clinical practice. Current research primarily focuses on the segmentation of single-frame DSA using proprietary datasets. However, these methods face challenges due to the inherent limitation of single-frame DSA, which only partially displays vascular contrast, thereby hindering accurate vascular structure representation. In this work, we introduce DIAS, a dataset specifically developed for IA segmentation in DSA sequences. We establish a comprehensive benchmark for evaluating DIAS, covering full, weak, and semi-supervised segmentation methods. Specifically, we propose the vessel sequence segmentation network, in which the sequence feature extraction module effectively captures spatiotemporal representations of intravascular contrast, achieving intracranial artery segmentation in 2D+Time DSA sequences. For weakly-supervised IA segmentation, we propose a novel scribble learning-based image segmentation framework, which, under the guidance of scribble labels, employs cross pseudo-supervision and consistency regularization to improve the performance of the segmentation network. Furthermore, we introduce the random patch-based self-training framework, aimed at alleviating the performance constraints encountered in IA segmentation due to the limited availability of annotated DSA data. Our extensive experiments on the DIAS dataset demonstrate the effectiveness of these methods as potential baselines for future research and clinical applications. The dataset and code are publicly available at https://doi.org/10.5281/zenodo.11401368 and https://github.com/lseventeen/DIAS.

First-in-human, real-time artificial intelligence assisted cerebral aneurysm coiling: a preliminary experience

BACKGROUND

Neuroendovascular procedures require careful and simultaneous attention to multiple devices on multiple screens. Overlooking unintended device movements can result in complications. Advancements in artificial intelligence (AI) have enabled real-time notifications of device movements during procedures. We report our preliminary experience with real-time AI-assisted cerebral aneurysm coiling in humans.

METHODS

A real-time AI-assistance software (Neuro-Vascular Assist, iMed technologies, Tokyo, Japan) was used during coil embolization procedures in nine patients with an unruptured aneurysm. The AI system provided real-time notifications for 'coil marker approaching', 'guidewire movement', and 'device entry' on biplane fluoroscopic images. The efficacy, accuracy, and safety of the notifications were evaluated using video recordings.

RESULTS

The AI system functioned properly in all cases. The mean number of notifications for coil marker approaching, guidewire movement, and device entry per procedure was 20.0, 3.0, and 18.3, respectively. The overall precision and recall were 92.7% and 97.2%, respectively. Five of 26 true positive guidewire notifications (19%) resulted in adjustment of the guidewire back toward its original position, indicating the potential effectiveness of the AI system. No adverse events occurred.

CONCLUSIONS

The software was sufficiently accurate and safe in this preliminary study, suggesting its potential usefulness. To the best of our knowledge, this is the first reported use of a real-time AI system for assisting cerebral aneurysm coiling in humans. Large scale studies are warranted to validate its effectiveness. Real-time AI assistance has significant potential for future neuroendovascular therapy.

Value of Immediate Flat Panel Perfusion Imaging after Endovascular Therapy (AFTERMATH): A Proof of Concept Study

BACKGROUND AND PURPOSE

Potential utility of flat panel CT perfusion imaging (FPCT-PI) performed immediately after mechanical thrombectomy (MT) is unknown. We aimed to assess whether FPCT-PI obtained directly post-MT could provide additional potentially relevant information on tissue reperfusion status.

MATERIALS AND METHODS

This was a single-center analysis of all patients with consecutive acute stroke admitted between June 2019 and March 2021 who underwent MT and postinterventional FPCT-PI (n = 26). A core lab blinded to technical details and clinical data performed TICI grading on postinterventional DSA images and qualitatively assessed reperfusion on time-sensitive FPCT-PI maps. According to agreement between DSA and FPCT-PI, all patients were classified into 4 groups: hypoperfusion findings perfectly matched by location (group 1), hypoperfusion findings mismatched by location (group 2), complete reperfusion on DSA with hypoperfusion on FPCT-PI (group 3), and hypoperfusion on DSA with complete reperfusion on FPCT-PI (group 4).

RESULTS

Detection of hypoperfusion (present/absent) concurred in 21/26 patients. Of these, reperfusion findings showed perfect agreement on location and size in 16 patients (group 1), while in 5 patients there was a mismatch by location (group 2). Of the remaining 5 patients with disagreement regarding the presence or absence of hypoperfusion, 3 were classified into group 3 and 2 into group 4. FPCT-PI findings could have avoided TICI overestimation in all false-positive operator-rated TICI 3 cases (10/26).

CONCLUSIONS

FPCT-PI may provide additional clinically relevant information in a considerable proportion of patients undergoing MT. Hence, FPCT-PI may complement the evaluation of reperfusion efficacy and potentially inform decision-making in the angiography suite.

Connecting the DOTs: a novel imaging sign on flat-panel detector CT indicating distal vessel occlusions after thrombectomy

BACKGROUND

Immediate non-contrast post-interventional flat-panel detector CT (FPDCT) has been suggested as an imaging tool to assess complications after endovascular therapy (EVT). We systematically investigated a new imaging finding of focal hyperdensities correlating with remaining distal vessel occlusion after EVT.

METHODS

A single-center retrospective analysis was conducted for all acute ischemic stroke patients admitted between July 2020 and December 2022 who underwent EVT and immediate post-interventional FPDCT. A blinded core lab performed reperfusion grading on post-interventional digital subtraction angiography (DSA) images and evaluated focal hyperdensities on FPDCT (here called the distal occlusion tracker (DOT) sign). DOT sign was defined as a tubular or punctiform, vessel confined, hyperdense signal within the initial occlusion target territory. We assessed sensitivity and specificity of the DOT sign when compared with DSA findings.

RESULTS

The median age of the cohort (n=215) was 74 years (IQR 63-82) and 58.6% were male. The DOT sign was positive in half of the cohort (51%, 110/215). The DOT sign had high specificity (85%, 95% CI 72% to 93%), but only moderate sensitivity (63%, 95% CI 55% to 70%) for detection of residual vessel occlusions. In comparison to the core lab, operators overestimated complete reperfusion in a quarter of the entire cohort (25%, 53/215). In more than half of these cases (53%, 28/53) there was a positive DOT sign, which could have mitigated this overestimation.

CONCLUSION

The DOT sign appears to be a frequent finding on immediate post-interventional FPDCT. It correlates strongly with incomplete reperfusion and indicates residual distal vessel occlusions. In the future, it may be used to complement grading of reperfusion success and may help mitigating overestimation of reperfusion in the acute setting.

Automated image registration of cerebral digital subtraction angiography

PURPOSE

Our aim is to automatically align digital subtraction angiography (DSA) series, recorded before and after endovascular thrombectomy. Such alignment may enable quantification of procedural success.

METHODS

Firstly, we examine the inherent limitations for image registration, caused by the projective characteristics of DSA imaging, in a representative set of image pairs from thrombectomy procedures. Secondly, we develop and assess various image registration methods (SIFT, ORB). We assess these methods using manually annotated point correspondences for thrombectomy image pairs.

RESULTS

Linear transformations that account for scale differences are effective in aligning DSA sequences. Two anatomical landmarks can be reliably identified for registration using a U-net. Point-based registration using SIFT and ORB proves to be most effective for DSA registration and are applicable to recordings for all patient sub-types. Image-based techniques are less effective and did not refine the results of the best point-based registration method.

CONCLUSION

We developed and assessed an automated image registration approach for cerebral DSA sequences, recorded before and after endovascular thrombectomy. Accurate results were obtained for approximately 85% of our image pairs.

Priorities for Advancements in Neuroimaging in the Diagnostic Workup of Acute Stroke

STAIR XII (12th Stroke Treatment Academy Industry Roundtable) included a workshop to discuss the priorities for advancements in neuroimaging in the diagnostic workup of acute ischemic stroke. The workshop brought together representatives from academia, industry, and government. The participants identified 10 critical areas of priority for the advancement of acute stroke imaging. These include enhancing imaging capabilities at primary and comprehensive stroke centers, refining the analysis and characterization of clots, establishing imaging criteria that can predict the response to reperfusion, optimizing the Thrombolysis in Cerebral Infarction scale, predicting first-pass reperfusion outcomes, improving imaging techniques post-reperfusion therapy, detecting early ischemia on noncontrast computed tomography, enhancing cone beam computed tomography, advancing mobile stroke units, and leveraging high-resolution vessel wall imaging to gain deeper insights into pathology. Imaging in acute ischemic stroke treatment has advanced significantly, but important challenges remain that need to be addressed. A combined effort from academic investigators, industry, and regulators is needed to improve imaging technologies and, ultimately, patient outcomes.

Quantifying Change in Perfusion after Genicular Artery Embolization with Parametric Analysis of Intraprocedural Digital Subtraction Angiograms

PURPOSE

To quantify perfusion changes during genicular artery embolization (GAE) with the qualitatively described "pruning" technique using parametric analysis.

MATERIALS AND METHODS

A total of 12 patients underwent unilateral GAE with a total of 36 vessels embolized. Among 34 of the 36 vessels embolized, regions of interest (ROIs) were placed on parent vessels (PVs) and hyperemic target vessels (TVs) before and after GAE. For each ROI, peak intensity (PI), time to arrival (TTA), and area under the curve (AUC) were computed and compared between PV and TV. Volume of embolic administered was correlated with adverse events.

RESULTS

No change was seen in PI, TTA, and AUC in the PV after GAE. Reduction in AUC (1,495.7 ± 521.5 vs 1,667.4 ± 574.0; P << .01) and PI (195.1 ± 43.8 vs 224.3 ± 49.2; P << .01) with increase in TTA (3.42 s ± 1.70 vs 1.92 s ± 1.45; P << .01) within the TV were observed after GAE. Median follow-up time was 89 days (range, 21-254 days). Reduction in clinical symptoms was also noted based on the Western-Ontario and McMaster Universities Arthritis Index total and pain scale at 1 month (total, 42.9% ± 23.0; pain, 54.4% ± 9.8; P << .01) and 3 months (total, 42.5% ± 14.9; pain, 57.8% ± 10.6; P << .01). Eight total mild adverse events (minor/self-limiting) were noted per Society of Interventional Radiology guidelines. A larger volume of embolic was observed in knees with skin changes (3.4 mL ± 0.4 vs 1.7 mL ± 0.4; P << .001). Furthermore, all skin changes were seen with embolic volumes >3.0 mL.

CONCLUSIONS

Quantification of intraprocedural perfusion changes with GAE demonstrated reduced flow to the TV with maintained flow in the PV and acceptable clinical outcomes. A potential relationship between embolic volume and nontarget embolization was also highlighted.

Affinity Feature Strengthening for Accurate, Complete and Robust Vessel Segmentation

Vessel segmentation is crucial in many medical image applications, such as detecting coronary stenoses, retinal vessel diseases and brain aneurysms. However, achieving high pixel-wise accuracy, complete topology structure and robustness to various contrast variations are critical and challenging, and most existing methods focus only on achieving one or two of these aspects. In this paper, we present a novel approach, the affinity feature strengthening network (AFN), which jointly models geometry and refines pixel-wise segmentation features using a contrast-insensitive, multiscale affinity approach. Specifically, we compute a multiscale affinity field for each pixel, capturing its semantic relationships with neighboring pixels in the predicted mask image. This field represents the local geometry of vessel segments of different sizes, allowing us to learn spatial- and scale-aware adaptive weights to strengthen vessel features. We evaluate our AFN on four different types of vascular datasets: X-ray angiography coronary vessel dataset (XCAD), portal vein dataset (PV), digital subtraction angiography cerebrovascular vessel dataset (DSA) and retinal vessel dataset (DRIVE). Extensive experimental results demonstrate that our AFN outperforms the state-of-the-art methods in terms of both higher accuracy and topological metrics, while also being more robust to various contrast changes.

The Impact of Standardized Health Education in Patients with Ischemic Stroke on Patient Management Satisfaction and Quality of Clinical Management Services

Aim

Ischemic stroke is a common brain disease, which seriously affects the quality of life of patients. The purpose of this study was to evaluate the impact of the application of standardized health education in ischemic stroke patients on patient management satisfaction and clinical management service quality.

Methods

220 patients with ischemic stroke were chosen for study target. The research objects were randomly divided into control group (n = 110) and education group (n = 110) by odd even number draw lots. The control group conducted conventional treatment; on the basis of the control group, the education group received standardized health education. The impact of the application of standardized health education in patients with ischemic stroke on patient management satisfaction and clinical management service quality was analyzed.

Results

The number of health error items in the two groups decreased significantly after 2 months and 3 months of treatment, contrast to before admission, and the number of health error items in the education group was lower than that in the control group, and the difference was statistically significant. After 3 months of treatment, the daily activity score increased and the neurological function score decreased in the two groups, and the daily activity score in the education group was higher than that in the control group, and the neurological function score was lower than that in the control group; the difference was statistically significant. The satisfaction scores of patients in the education group in different aspects such as staff working attitude, health management, diet management, and environmental management were higher than those in the control group, and the disparity was obvious.

Conclusion

The application of standardized health education in patients with ischemic stroke has certain clinical value.

Deep learning-based classification of DSA image sequences of patients with acute ischemic stroke

PURPOSE

Recently, a large number of patients with acute ischemic stroke benefited from the use of thrombectomy, a minimally invasive intervention technique for mechanically removing thrombi from the cerebrovasculature. During thrombectomy, 2D digital subtraction angiography (DSA) image sequences are acquired simultaneously from the posterior-anterior and the lateral view to control whether thrombus removal was successful, and to possibly detect newly occluded areas caused by thrombus fragments split from the main thrombus. However, such new occlusions, which would be treatable by thrombectomy, may be overlooked during the intervention. To prevent this, we developed a deep learning-based approach to automatic classification of DSA sequences into thrombus-free and non-thrombus-free sequences.

METHODS

We performed a retrospective study based on the single-center DSA data of thrombectomy patients. For classifying the DSA sequences, we applied Long Short-Term Memory or Gated Recurrent Unit networks and combined them with different Convolutional Neural Networks used as feature extractor. These network variants were trained on the DSA data by using five-fold cross-validation. The classification performance was determined on a test data set with respect to the Matthews correlation coefficient (MCC) and the area under the curve (AUC). Finally, we evaluated our models on patient cases, in which overlooking thrombi during thrombectomy had happened.

RESULTS

Depending on the specific model configuration used, we obtained a performance of up to 0.77[Formula: see text]0.94 for the MCC[Formula: see text]AUC, respectively. Additionally, overlooking thrombi could have been prevented in the reported patient cases, as our models would have classified the corresponding DSA sequences correctly.

CONCLUSION

Our deep learning-based approach to thrombus identification in DSA sequences yielded high accuracy on our single-center test data set. External validation is now required to investigate the generalizability of our method. As demonstrated, using this new approach may help reduce the incident risk of overlooking thrombi during thrombectomy in the future.

Prime Time for Artificial Intelligence in Interventional Radiology

Machine learning techniques, also known as artificial intelligence (AI), is about to dramatically change workflow and diagnostic capabilities in diagnostic radiology. The interest in AI in Interventional Radiology is rapidly gathering pace. With this early interest in AI in procedural medicine, IR could lead the way to AI research and clinical applications for all interventional medical fields. This review will address an overview of machine learning, radiomics and AI in the field of interventional radiology, enumerating the possible applications of such techniques, while also describing techniques to overcome the challenge of limited data when applying these techniques in interventional radiology. Lastly, this review will address common errors in research in this field and suggest pathways for those interested in learning and becoming involved about AI.