Vessel Segmentation Research Articles

Transformer-Enhanced Retinal Vessel Segmentation for Diabetic Retinopathy Detection Using Attention Mechanisms and Multi-Scale Fusion

Eye health has become a significant concern in recent years, given the rising prevalence of visual impairment resulting from various eye disorders and related factors. Global surveys suggest that approximately 2.2 billion individuals are visually impaired, with at least 1 billion affected by treatable diseases or ailments. Early detection, treatment, and screening for fundus diseases are crucial in addressing these challenges. In this study, we propose a novel segmentation model for retinal vascular delineation aimed at diagnosing diabetic retinopathy. The model integrates CBAM (Channel-Attention and Spatial-Attention) for enhanced feature representation, JPU (Joint Pyramid Upsampling) for multi-scale feature fusion, and transformer blocks for contextual understanding. Leveraging deep-learning techniques, our proposed model outperforms existing approaches in retinal vascular segmentation, like achieving a Mean IOU of 0.8047, Recall of 0.7254, Precision of 0.8492, F1 Score of 0.7824, and Specificity of 0.9892 for CHASEDB1 dataset. Extensive evaluations on benchmark datasets demonstrate its efficacy, highlighting its potential for automated diabetic retinopathy screening.

Evaluating the Impact of Retinal Vessel Segmentation Metrics on Retest Reliability in a Clinical Setting: A Comparative Analysis Using AutoMorph.

Current research on artificial intelligence-based fundus photography biomarkers has demonstrated inconsistent results. Consequently, we aimed to evaluate and predict the test-retest reliability of retinal parameters extracted from fundus photography. Two groups of patients were recruited for the study: an intervisit group (n = 28) to assess retest reliability over a period of 1 to 14days and an intravisit group (n = 44) to evaluate retest reliability within a single session. Using AutoMorph, we generated test and retest vessel segmentation maps; measured segmentation map agreement via accuracy, sensitivity, F1 score and Jaccard index; and calculated 76 metrics from each fundus image. The retest reliability of each metric was analyzed in terms of the Spearman correlation coefficient, intraclass correlation coefficient (ICC), and relative percentage change. A linear model with the input variables contrast-to-noise-ratio and fractal dimension, chosen by a P-value-based backward selection process, was developed to predict the median percentage difference on retest per image based on image-quality metrics. This model was trained on the intravisit dataset and validated using the intervisit dataset. In the intervisit group, retest reliability varied between Spearman correlation coefficients of 0.34 and 0.99, ICC values of 0.31 to 0.99, and mean absolute percentage differences of 0.96% to 223.67%. Similarly, in the intravisit group, the retest reliability ranged from Spearman correlation coefficients of 0.55 and 0.96, ICC values of 0.40 to 0.97, and mean percentage differences of 0.49% to 371.23%. Segmentation map accuracy between test and retest never dropped below 97%; the mean F1 scores were 0.85 for the intravisit dataset and 0.82 for the intervisit dataset. The best retest was achieved with disc-width regarding the Spearman correlation coefficient in both datasets. In terms of the Spearman correlation coefficient, the worst retests of the intervisit and intravisit groups were tortuosity density and artery tortuosity density, respectively. The intravisit group exhibited better retest reliability than the intervisit group (P < 0.001). Our linear model, with the two independent variables contrast-to-noise ratio and fractal dimension predicted the median retest reliability per image on its validation dataset, the intervisit group, with an R2 of 0.53 (P < 0.001). Our findings highlight a considerable volatility in the reliability of some retinal biomarkers. Improving retest could allow disease progression modeling in smaller datasets or an individualized treatment approach. Image quality is moderately predictive of retest reliability, and further work is warranted to understand the reasons behind our observations better and thus ensure consistent retest results.

Development and Validation of a Flow-Dependent Endothelialized 3D Model of Intracranial Atherosclerotic Disease.

Intracranial atherosclerotic disease (ICAD) is a major cause of stroke globally, with mechanisms presumed to be shared with atherosclerosis in other vascular regions. Due to the scarcity of relevant animal models, testing biological hypotheses specific to ICAD is challenging. We developed a workflow to create patient-specific models of the middle cerebral artery (MCA) from neuroimaging studies, such as CT angiography. These models, which can be endothelialized with human endothelial cells and subjected to flow forces, provide a reproducible ICAD model. Using imaging from the SAMMPRIS clinical trial, we validated this novel model. Computational fluid dynamics flow velocities correlated strongly with particle-derived flow, regardless of stenosis degree. Post-stenotic flow disruption varied with stenosis severity. Single-cell RNA-seq identified flow-dependent endothelial gene expression and specific endothelial subclusters in diseased MCA segments, including upregulated genes linked to atherosclerosis. Confocal microscopy revealed flow-dependent changes in endothelial cell proliferation and morphology in vessel segments related to stenosis. This platform, rooted in the specific anatomy of cerebral circulation, enables detailed modeling of ICAD lesions and pathways. Given the high stroke risk associated with ICAD and the lack of effective treatments, these experimental models are crucial for developing new ICAD-related stroke therapies.

External Validation of Fully-Automated Infrarenal Maximum Aortic Aneurysm Diameter Measurements in Computed Tomography Angiography Scans Using Artificial Intelligence (PRAEVAorta 2).

This study investigates the accuracy of fully-automated maximum aortic diameter measurements in abdominal aortic aneurysm (AAA) patients using artificial intelligence software (PRAEVAorta 2, Nurea, Bordeaux, France). This is a multicenter, retrospective validation study using prospectively collected data from the Zenith alpha for aneurysm Repair Registry (ZEPHYR). Automated measurements of PRAEVAorta 2 are compared with measurements of an internationally recognized core laboratory (Syntactx, New York, New York State). The reviewers at the core laboratory were measurement technologists trained to and utilizing established measurement standards, overseen by vascular surgeons and radiologists. The data set comprised 871 computed tomography angiography scans from the ZEPHYR registry with 347 patients who underwent endovascular aneurysm repair (EVAR) with the Zenith Alpha Endovascular Abdominal Graft (Cook Medical, Bloomington, Indiana) in Germany, Belgium, and The Netherlands between 2016 and 2019. The analysis demonstrated excellent correlation of the measurements (r=0.97) with an intraclass correlation (ICC) of 0.972 (95% confidence interval [CI]=0.968-0.976) across all scans. For preoperative computed tomography (CT) scans, ICC was 0.953 (95% CI=0.941-0.963), and for postoperative scans, ICC was 0.979 (95% CI=0.975-0,983), respectively. In total, 95.4% of measurements were within the clinically acceptable range of 5 mm in absolute difference. In total, 10% of scans demonstrated obvious segmentation errors, mainly due to failure in detecting vessel segments (renal arteries, aortic bifurcation) or due to mis-detecting the outer border of the AAA (duodenum, inferior vena cava, aortic branches) and were excluded from the analysis. In this study, the maximum AAA diameter could be accurately measured fully-automatically by PRAEVAorta 2 (Nurea) in most cases demonstrating that artificial intelligence (AI) software could serve as an important adjunct for research and clinical practice. However, critical review of the generated reports by an experienced observer and cautious use is warranted to identify flawed segmentations. This multicenter, retrospective validation study assessed the accuracy of fully-automated maximum infrarenal aortic aneurysm diameter measurements. It was demonstrated, that 95.4% of measurements were within the clinically acceptable range of 5 mm in absolute difference, positioning the software as a potential adjunct for clinical practice and research. It is also highlighted however, that critical review of the measurements is obligatory, due to a 10% segmentation error rate.

Retinal artery/vein vessel segmentation and measurement for hypertension based on multi-level edge-guided network

AbstractHypertension is a primary risk factor for the onset of cardiocerebrovascular diseases, leading to increased mortality. In the early stages of hypertension, changes in the diameter of the retinal arteries and veins are closely observed. Therefore, the automatic segmentation of these arteries and veins in retinal fundus images is crucial for hypertension monitoring. However, current deep learning based methods still fail to generate semantically consistent segmentation result, especially for narrow blood vessel segments. Moreover, the pixels near the vessel edge are prone to be missclassified by current methods, struggling to obtain edge-preserving segmentation results. These critical issues severely hinder downstream applications, which require accurate measurement of artery/vein diameter. First, to alleviate the issue of lacking semantic consistency for vessel segments, we propose a long-range spatial dependency modeling module to learn to model the long-range spatial dependency. On this basis, a multi-level edge guided spatial aggregation module is further presented to enhance the ability to accurately classify the edge pixels, generating edge-preserving results. Extensive experimental results on the widely used DRIVE dataset and our constructed dataset (HFC-50) show the superiority of the proposed model over state-of-the-art methods. Our method achieves balanced accuracy of 95.7% on DRIVE dataset, outperforming all state-of-art methods. Finally, in order to directly demonstrate the benefit of more accurate retinal artery/vein vessel segmentation for the measurement of the ratio of artery and vein, we quantitatively evaluate the computed artery/vein ratio for hypertension patients, with the artery/vein segmentation results generated by our proposed method.

SFNet: Spatial and Frequency Domain Networks for Wide-Field OCT Angiography Retinal Vessel Segmentation.

Automatic segmentation of blood vessels in fundus images is important to assist ophthalmologists in diagnosis. However, automatic segmentation for Optical Coherence Tomography Angiography (OCTA) blood vessels has not been fully investigated due to various difficulties, such as vessel complexity. In addition, there are only a few publicly available OCTA image data sets for training and validating segmentation algorithms. To address these issues, we constructed a wild-field retinal OCTA segmentation data set, the Retinal Vessels Images in OCTA (REVIO) dataset. Second, we propose a new retinal vessel segmentation network based on spatial and frequency domain networks (SFNet). The proposed model are tested on three benchmark data sets including REVIO, ROSE and OCTA-500. The experimental results show superior performance on segmentation tasks compared to the representative methods.

SLOctolyzer: Fully Automatic Analysis Toolkit for Segmentation and Feature Extracting in Scanning Laser Ophthalmoscopy Images.

The purpose of this study was to introduce SLOctolyzer: an open-source analysis toolkit for en face retinal vessels in infrared reflectance scanning laser ophthalmoscopy (SLO) images. SLOctolyzer includes two main modules: segmentation and measurement. The segmentation module uses deep learning methods to delineate retinal anatomy, and detects the fovea and optic disc, whereas the measurement module quantifies the complexity, density, tortuosity, and caliber of the segmented retinal vessels. We evaluated the segmentation module using unseen data and measured its reproducibility. SLOctolyzer's segmentation module performed well against unseen internal test data (Dice for all-vessels = 0.91; arteries = 0.84; veins = 0.85; optic disc = 0.94; and fovea = 0.88). External validation against severe retinal pathology showed decreased performance (Dice for arteries = 0.72; veins = 0.75; and optic disc = 0.90). SLOctolyzer had good reproducibility (mean difference for fractal dimension = -0.001; density = -0.0003; caliber = -0.32 microns; and tortuosity density = 0.001). SLOctolyzer can process a 768 × 768 pixel macula-centered SLO image in under 20 seconds and a disc-centered SLO image in under 30 seconds using a laptop CPU. To our knowledge, SLOctolyzer is the first open-source tool to convert raw SLO images into reproducible and clinically meaningful retinal vascular parameters. It requires no specialist knowledge or proprietary software, and allows manual correction of segmentations and re-computing of vascular metrics. SLOctolyzer is freely available at https://github.com/jaburke166/SLOctolyzer. SLO images are captured simultaneous to optical coherence tomography (OCT), and we believe SLOctolyzer will be useful for extracting retinal vascular measurements from large OCT image sets and linking them to ocular or systemic diseases.

Deep learning for 3D vascular segmentation in hierarchical phase contrast tomography: a case study on kidney

Automated blood vessel segmentation is critical for biomedical image analysis, as vessel morphology changes are associated with numerous pathologies. Still, precise segmentation is difficult due to the complexity of vascular structures, anatomical variations across patients, the scarcity of annotated public datasets, and the quality of images. Our goal is to provide a foundation on the topic and identify a robust baseline model for application to vascular segmentation using a new imaging modality, Hierarchical Phase-Contrast Tomography (HiP-CT). We begin with an extensive review of current machine-learning approaches for vascular segmentation across various organs. Our work introduces a meticulously curated training dataset, verified by double annotators, consisting of vascular data from three kidneys imaged using HiP-CT as part of the Human Organ Atlas Project. HiP-CT pioneered at the European Synchrotron Radiation Facility in 2020, revolutionizes 3D organ imaging by offering a resolution of around 20 μm/voxel and enabling highly detailed localised zooms up to 1–2 μm/voxel without physical sectioning. We leverage the nnU-Net framework to evaluate model performance on this high-resolution dataset, using both known and novel samples, and implementing metrics tailored for vascular structures. Our comprehensive review and empirical analysis on HiP-CT data sets a new standard for evaluating machine learning models in high-resolution organ imaging. Our three experiments yielded Dice similarity coefficient (DSC) scores of 0.9523, 0.9410, and 0.8585, respectively. Nevertheless, DSC primarily assesses voxel-to-voxel concordance, overlooking several crucial characteristics of the vessels and should not be the sole metric for deciding the performance of vascular segmentation. Our results show that while segmentations yielded reasonably high scores-such as centerline DSC ranging from 0.82 to 0.88, certain errors persisted. Specifically, large vessels that collapsed due to the lack of hydrostatic pressure (HiP-CT is an ex vivo technique) were segmented poorly. Moreover, decreased connectivity in finer vessels and higher segmentation errors at vessel boundaries were observed. Such errors, particularly in significant vessels, obstruct the understanding of the structures by interrupting vascular tree connectivity. Our study establishes the benchmark across various evaluation metrics, for vascular segmentation of HiP-CT imaging data, an imaging technology that has the potential to substantively shift our understanding of human vascular networks.

CFFANet: category feature fusion and attention mechanism network for retinal vessel segmentation

CFFANet: category feature fusion and attention mechanism network for retinal vessel segmentation

Retinal blood vessel segmentation using density-based fuzzy C-means clustering and vessel neighborhood connected component

Retinal blood vessel segmentation using density-based fuzzy C-means clustering and vessel neighborhood connected component

FINE VESSEL SEGMENTATION WITH REFINEMENT GATE IN DEEP LEARNING ARCHITECTURES

Automated vessel segmentation is essential in diagnosing eye-related disorders and monitoring progressive retinal diseases. State-of-the-art methods have achieved excellent results in this field, but very few have considered the post-processing of feature maps. As a result, there is often a lack of small and fine vessels or discontinuities in segmented vessels. To address this issue, this study introduces a novel post-processing technique called the refinement gate, which works with a deep learning model during training. The refinement gate enhances contextual information to extract important features from feature maps better. The proposed technique is applied with U-net architecture and placed after every convolution block in the encoder path. Visual and statistical comparisons demonstrate the robustness of the proposed method using three publicly available datasets, namely: the DRIVE DB, the STARE DB, and CHASE_DB1 datasets, showing significant improvements to segment weak and tiny vessels. The reported results confirm the potential of the model to be used as a segmentation tool in the medical field. This study is the first to propose such a gating mechanism without additional trainable parameters or standalone networks as in other literature.

Enhancing Surgical Guidance: Deep Learning-Based Liver Vessel Segmentation in Real-Time Ultrasound Video Frames.

In the field of surgical medicine, the planning and execution of liver resection procedures present formidable challenges, primarily attributable to the intricate and highly individualized nature of liver vascular anatomy. In the current surgical milieu, intraoperative ultrasonography (IOUS) has become indispensable; however, traditional 2D ultrasound imaging's interpretability is hindered by noise and speckle artifacts. Accurate identification of critical structures for preservation during hepatectomy requires advanced surgical skills. An AI-based model that can help detect and recognize vessels including the inferior vena cava (IVC); the right (RHV), middle (MHV), and left (LVH) hepatic veins; the portal vein (PV) and its major first and second order branches the left portal vein (LPV), right portal vein (RPV), and right anterior (RAPV) and posterior (RPPV) portal veins, for real-time IOUS navigation can be of immense value in liver surgery. This research aims to advance the capabilities of IOUS-guided interventions by applying an innovative AI-based approach named the "2D-weigthed U-Net model" for the segmentation of multiple blood vessels in real-time IOUS video frames. Our proposed deep learning (DL) model achieved a mean Dice score of 0.92 for IVC, 0.90 for RHV, 0.89 for MHV, 0.86 for LHV, 0.95 for PV, 0.93 for LPV, 0.84 for RPV, 0.85 for RAPV, and 0.96 for RPPV. In the future, this research will be extended for real-time multi-label segmentation of extended vasculature in the liver, followed by the translation of our model into the surgical suite.

TCDDU-Net: combining transformer and convolutional dual-path decoding U-Net for retinal vessel segmentation

Accurate segmentation of retinal blood vessels is crucial for enhancing diagnostic efficiency and preventing disease progression. However, the small size and complex structure of retinal blood vessels, coupled with low contrast in corresponding fundus images, pose significant challenges for this task. We propose a novel approach for retinal vessel segmentation, which combines the transformer and convolutional dual-path decoding U-Net (TCDDU-Net). We propose the selective dense connection swin transformer block, which converts the input feature map into patches, introduces MLPs to generate probabilities, and performs selective fusion at different stages. This structure forms a dense connection framework, enabling the capture of long-distance dependencies and effective fusion of features across different stages. The subsequent stage involves the design of the background decoder, which utilizes deformable convolution to learn the background information of retinal vessels by treating them as segmentation objects. This is then combined with the foreground decoder to form a dual-path decoding U-Net. Finally, the foreground segmentation results and the processed background segmentation results are fused to obtain the final retinal vessel segmentation map. To evaluate the effectiveness of our method, we performed experiments on the DRIVE, STARE, and CHASE datasets for retinal vessel segmentation. Experimental results show that the segmentation accuracies of our algorithms are 96.98, 97.40, and 97.23, and the AUC metrics are 98.68, 98.56, and 98.50, respectively.In addition, we evaluated our methods using F1 score, specificity, and sensitivity metrics. Through a comparative analysis, we found that our proposed TCDDU-Net method effectively improves retinal vessel segmentation performance and achieves impressive results on multiple datasets compared to existing methods.

AngioPy: an open-source, deep learning-driven tool for coronary artery segmentation

Abstract Background Quantitative coronary angiography (QCA) permits the objective assessment of coronary artery disease. However, traditional edge detection algorithms often struggle with accurate vessel segmentation due to the complexity and variable quality of angiographic images. As a result, manual correction is frequently needed, which is a major limitation of current QCA systems. Purpose We developed angioPy, a deep learning-driven tool for vessel segmentation that employs user-defined ground truth points to minimise manual correction. We compared its performance without correction with an established QCA system. Methods angioPy was developed using 2455 images from the Fractional Flow Reserve versus Angiography for Multivessel Evaluation 2 (FAME 2) study. Deep learning models were constructed using the U-Net architecture with one of three popular backbones for image classification: ResNet101, DenseNet121, and InceptionResNet-v2. Critically, the model was constructed to integrate the user’s clinical expertise through the selection of a 5-10 ground-truth points along the length of the vessel of interest including the desired start and end point of vessel segmentation. These ground truth points were added to a separate channel of the input image. Five-fold cross validation was performed using proportions of 3:1:1 for training, validation, and test sets, respectively. External validation was performed on a separate dataset of 580 images not used for model development. For both datasets, ground truth segmentation masks were provided by interventional cardiologists using specialised in-house software. A separate analysis was performed in a cohort of 74 patients with mild/moderate stenoses that underwent vessel segmentation using both angioPy and an established commercial QCA package (Medis QFR®). Vessel dimensions at stenoses (proximal and distal reference, minimal luminal diameter) were extracted from both segmentation approaches and compared (609 diameters in total). Results The best performing model performed segmentation with an average F1 score of 0.927 (pixel accuracy 0.998, precision 0.925, sensitivity 0.930, specificity 0.999) with 99.2% of masks exhibiting an F1 score &amp;gt; 0.8 (Figure 1). Simliar results were achieved in the external validation set (F1 score 0.924, pixel accuracy 0.997, precision 0.921, sensitivity 0.929, specificity 0.999). Stenosis dimensions measured with angioPy (mean diameter 3.54 ±1.15 mm) exhibited excellent agreement with QCA (r=0.95 [95% CI 0.95-0.96], p&amp;lt;0.001; mean difference -0.18 mm [limits of agreement: -0.84 to 0.49]) (Figure 2). Minimal luminal diameter (mean 2.93 ±0.91 mm) also exhibited strong agreement (r=0.93 [95% CI 0.91-0.95], p&amp;lt;0.001; mean difference -0.06 mm [limits of agreement: -0.70 to 0.59]. Conclusion angioPy performs rapid and accurate coronary segmentation without the need for manual correction. Available as an open-source tool, angioPy has the potential to increase the efficiency and reliability of QCA.Figure 1.angioPy segmentationFigure 2.angioPy vs QCA (Medis)

Impact of ultra-high-resolution on cardiac CT assessment of coronary artery stenoses, plaque burden/composition, and pericoronary adipose tissue attenuation

Abstract Background Conventional coronary computed tomography angiography (CCTA) overestimates stenoses within stents and calcified arteries due to "blooming" artifacts. Ultra-high-resolution coronary CT (UHR-CT) may overcome this limitation because of higher spatial resolution. Purpose To investigate differences in coronary arterial lumen volume, stenosis severity, and plaque composition, between CCTA and UHRCT in patients with stents and/or high coronary calcium scores. Methods As part of a prospective pilot study, 14 patients referred for invasive coronary angiography for evaluation of obstructive CAD underwent UHRCT (Canon Precision, 160 x 0.25mm slices) prior to catheterization. Images of identical cardiac phases were reconstructed in two badges for comparison: 1) Ultra-high resolution using a 1,024 x 1,024 matrix, 0.25 mm, and 2) conventional resolution with a 524 x 524 matrix, 0.5 mm. All images were reconstructed using iterative reconstruction algorithm (AIDR 3D) and a sharp kernel (FC05). For the left main and three coronary arteries, an automated contour analysis using a dedicated software (QAngioCT RE 3.2, Medis, Netherlands) was performed to compare conventional CCTA vs. UHR-CT resolution images across common vascular and plaque metrics, including lumen and vessel volume, plaque burden/volume, plaque composition based upon predefined fixed intensity cut-off values of CT attenuation, minimal and maximal plaque thickness, pericoronary adipose tissue attenuation (PCAT), minimal lumen area and diameter, and diameter stenosis. All lumen and vessel contours were generated by the software, without manual editing. The segment model proposed by the SCCT was used as reference and the lesions classified as greater than 25% stenosis by visual assessment were recorded. The quality of the images was subjectively assessed using a 5-point Likert scale. Vessel segments with scores 1 (severe artifacts) and 2 (pronounced artifacts) were not included in the analysis. Results The mean patient age was 68.5 years (±6.8), 2 were female (14.3%), 6 patients had stents (11 stented segments) and the mean Agatston score was 947.6 (±449) among the 8 non-stented patients. A total of 56 vessels, 133 segments, and 57 lesions were analyzed. Eight segments (6%) were excluded from the analysis due to poor quality. Results on a per segment and per lesion basis were summarized in the table. The mean PCAT value was significantly lower for the UHRCT images compared to NR reconstruction in both segment (p&amp;lt;0.001) and lesion based (p=0.002) analyses. Plaque differentiation varied by UHRCT resulted in a lower fibrous plaque volumes but higher necrotic (low attenuation) plaque volumes. Conclusions Ultra-high-resolution CT image analysis results in significantly different coronary artery plaque volume and PCAT assessment vs. conventional resolution CCTA. These findings have implications for evaluating high-risk plaque features and perivascular inflammation in patients.Table 1

Side branch interventions late after MFM implantation

Abstract Background MFM prostheses were developed for the endovascular treatment of aortic and great vessel aneurysms. Implanted between two healthy segments of arterial vessel, they centralize blood flow and trough Bernoulli's principle. Thereby hemodynamic stress into the aneurismal sac is reduced. Meantime, the porosity along entire prosthesis length preserves all side branches (SB) patent. Results from real clinical practice confirm the high success rate (nearly 100%) of MFM prostheses regarding side branch preservation at one-year follow-up [1,2]. However, late after MFM implantation SB intervention may be required (due to atherosclerosis or others). The access to SB covered by MFM is challenging due to: impossible ostial engagement of the guiding catheter, distance between target vessel ostium and prosthesis, the necessary for all devices used to cross MFM mesh. Materials and methods For the period 2016-2020 we implanted a specific type of MFM prosthesis in order to treat aneurysm of the abdominal aorta in 34 patients. A total of 129 side branches was covered. Within a mean follow-up period of 5 years, 129 side branches were preserved and 7 affected by stenosis or occlusion (two of them asymptomatic). Intervention on the branch covered by the MFM prosthesis was necessary in 5 patients (two males, two females; mean age 68 years). One patient had endovascular celiac trunk stenosis, one patient had both celiac trunk and superior mesenteric artery stenoses, one patient had superior mesenteric artery stenosis, and one patient had left renal artery stenosis. All lesions were intervened through radial or brachial approach. Guiding 6F Judkins right catheter was navigated close to the target branch ostium and the MFM mesh was crossed with .014¨ coronary wire. When guidewire was placed into target vessel small low-profile, coronary balloon is advanced across the mesh of the multilayer stent. Anchor balloon technique was used in order for guiding catheter to cross the mesh gradually. Once the guiding catheter is engaged, the lesion was treated with balloon pre-dilation and implantation of a low-profile, high radial force stent. Results All 4 patients and 5 affected vessels were successfully endovascularly intervened. We did not observe any procedure complications. Immediate resolution of clinical symptoms was achieved. At 1 year follow-up with CT scan all treated branch arteries were patent. Conclusions In patients with previously implanted multilayer stents, the mesh can be crossed safely with readily available coronary devices together with the balloon anchor technique. As such, endovascular treatment of stent-covered visceral and renal arteries is possible without open surgery.Catheter stabilizationSMA successfully treated

Clustering of artificial intelligence derived plaque features for risk stratification for future atrial fibrillation development

Abstract Introduction We previously demonstrated that artificial intelligence (AI)-derived coronary artery plaque features are associated with future development of atrial fibrillation (AF) among patients undergoing CCTA(1). Our results suggest that phenotyping a large dataset of plaque features using data science techniques may reveal associations not visible from univariate analysis. Purpose Use data science analysis of AI-CT plaque characteristics to identify subpopulations at higher risk of AF. Methods We applied dimensionality reduction and visual cluster identification to phenotype our population of patients based on their AI-CT plaque features. We used a single center CCTA registry of patients with prior clinically-indicated CCTA (N=2700) from 2017-2020. Cases of new AF were defined by onset of AF on ECG or telemetry after CCTA via EMR search. Patients with AF prior to CCTA, history of mitral valve surgery, or postoperative AF were excluded. Controls were selected 1:1 by nearest neighbor propensity matching (R. v. 4.0.3.) based on age, sex, tobacco use, HTN, HLD, and diabetes. Atherosclerotic plaques were quantitatively analyzed using a commercially available FDA-approved AI coronary analysis software yielding stenosis area and diameter, remodeling index, volume of calcified/non-calcified/low-density plaques, and number of 2 or more high risk plaques. Uniform Manifold Approximation and Projection (UMAP) dimensionality reduction with cosine distance metric was used to reduce the plaque feature space from 80 dimensions (8 AI measurements per each of 10 anatomical vessel segments in all patients) to 2 dimensions on a scatter plot. Two non-contiguous clusters (i.e. plaque phenotypes) were identified based on visual analysis of UMAP feature reduction (Figure 1). Results 94 cases comprised the study cohort (47 cases and 47 controls). Mean age was 67±11 years. 38% were female. Mean CADRADS score was 1.8±1.52 and mean CAC was 325±622. Mean time from CT to AF was 281±300 days. The majority of AF patients (67%) fell into Cluster 1 (N=36), while Cluster 2 (N=58) contained most of the control subjects (75%). Treating Cluster 1 as a predictor of AF, the PPV and specificity of the UMAP reduction was 67% and 75% respectively, with NPV of 60% and sensitivity of 51% (Table 1). Left atrial volume index (LAVI) was significantly different between the 2 clusters, with mean 56.15±12.42 ml/m2 in Cluster 1 and 46.96±16.03 in Cluster 2 (p=0.0046). LAVI was also significantly different between control subjects in Cluster 1 vs 2, mean 54.84±11.6 vs 41.62±7.92 (p&amp;lt;0.001). Conclusions We demonstrated that UMAP-derived clustering of AI-CT plaque characteristics identifies novel phenotypes for future risk of AF among patients undergoing CCTA. Further, control patients in Cluster 1 were found to have a significantly higher LAVI compared to control subjects in Cluster 2, which supports that membership in Cluster 1 may increase risk of future development of AF.

Toward assessment of rupture risk predictors in abdominal aortic aneurysms including intraluminal thrombus based on 3D+t ultrasound images.

Image-based patient-specific rupture risk analysis for abdominal aortic aneurysms (AAAs) has shown considerable promise. However, clinical translation has been hampered by the use of invasive and costly imaging modalities. Despite being a promising alternative, ultrasound (US) makes a full analysis, including intraluminal thrombus (ILT), not trivial. This study explored the feasibility of assessing AAA rupture risk parameters, e.g., peak wall stress (PWS) and peak wall rupture index (PWRI), using US-based models of the AAA wall, finally including ILT. Three-dimensional US data were segmented from a group of AAA patients whose CT data were available within 30 days. The segmented vessel wall and ILT boundaries were converted into a mesh including and excluding ILT to evaluate the effect of adding ILT on the model output. US-based rupture risk parameters (PWS and PWRI) were compared to CT-based results. The US-based PWS and PWRI, including ILT, showed good agreement with CT-based results, and the model excluding ILT showed no significant bias in wall stress or rupture index. When including ILT, a lower US-based wall stress and rupture index of 7.2% and 3.8% were found, respectively. The intraclass correlation coefficient (ICC) of PWS was 0.60. The highest ICC was found for the PWRI (ICC = 0.86), indicating good absolute agreement. This study showed that PWRI can be estimated with US when including the ILT, yielding comparable results to CT, and good absolute agreement. Future work should focus on improving the contrast of ILT in US, since this will be essential to performing large-scale studies in AAA cohorts.

Self-supervised learning for accurately modelling hierarchical evolutionary patterns of cerebrovasculature

Cerebrovascular abnormalities are critical indicators of stroke and neurodegenerative diseases like Alzheimer’s disease (AD). Understanding the normal evolution of brain vessels is essential for detecting early deviations and enabling timely interventions. Here, for the first time, we proposed a pipeline exploring the joint evolution of cortical volumes (CVs) and arterial volumes (AVs) in a large cohort of 2841 individuals. Using advanced deep learning for vessel segmentation, we built normative models of CVs and AVs across spatially hierarchical brain regions. We found that while AVs generally decline with age, distinct trends appear in regions like the circle of Willis. Comparing healthy individuals with those affected by AD or stroke, we identified significant reductions in both CVs and AVs, wherein patients with AD showing the most severe impact. Our findings reveal gender-specific effects and provide critical insights into how these conditions alter brain structure, potentially guiding future clinical assessments and interventions.

Topology-aware mamba for crack segmentation in structures

CrackMamba, a Mamba-based model, is designed for efficient and accurate crack segmentation for monitoring the structural health of infrastructure. Traditional Convolutional Neural Network (CNN) models struggle with limited receptive fields, and while Vision Transformers (ViT) improve segmentation accuracy, they are computationally intensive. CrackMamba addresses these challenges by utilizing the VMambaV2 with pre-trained ImageNet-1 k weights as the encoder and a newly designed decoder for better performance. To handle the random and complex nature of crack development, a Snake Scan module is proposed to reshape crack feature sequences, enhancing feature extraction. Additionally, the three-branch Snake Conv VSS (SCVSS) block is proposed to target cracks more effectively. Experiments show that CrackMamba achieves state-of-the-art (SOTA) performance on the CrackSeg9k and SewerCrack datasets, and demonstrates competitive performance on the retinal vessel segmentation dataset CHASE_DB1, highlighting its generalization capability.