ABSTRACT
Kidney failure is particularly common in the United States, where it affects over 700,000 individuals. It is typically treated through repeated sessions of hemodialysis to filter and clean the blood. Hemodialysis requires vascular access, in about 70% of cases through an arteriovenous fistula (AVF) surgically created by connecting an artery and vein. AVF take 6 weeks or more to mature. Mature fistulae often require intervention, most often percutaneous transluminal angioplasty (PTA), also known as fistulaplasty, to maintain the patency of the fistula. PTA is also the first-line intervention to restore blood flow and prolong the use of an AVF, and many patients undergo the procedure multiple times. Although PTA is important for AVF maturation and maintenance, research into predictive models of AVF function following PTA has been limited. Therefore, in this paper we hypothesize that based on patient-specific information collected during PTA, a predictive model can be created to help improve treatment planning. We test a set of rich, multimodal data from 28 patients that includes medical history, AVF blood flow, and interventional angiographic imaging (specifically excluding any post-PTA measurements) and build deep hybrid neural networks. A hybrid model combining a 3D convolutional neural network with a multi-layer perceptron to classify AVF was established. We found using this model that we were able to identify the association between different factors and evaluate whether the PTA procedure can maintain primary patency for more than 3 months. The testing accuracy achieved was 0.75 with a weighted F1-score of 0.75, and AUROC of 0.75. These results indicate that evaluating multimodal clinical data using artificial neural networks can predict the outcome of PTA. These initial findings suggest that the hybrid model combining clinical data, imaging and hemodynamic analysis can be useful to treatment planning for hemodialysis. Further study based on a large cohort is needed to refine the accuracy and model efficiency.
ABSTRACT
Vision-language models have become increasingly powerful for tasks that require an understanding of both visual and linguistic elements, bridging the gap between these modalities. In the context of multimodal clinical AI, there is a growing need for models that possess domain-specific knowledge, as existing models often lack the expertise required for medical applications. In this paper, we take brain abnormalities as an example to demonstrate how to automatically collect medical image-text aligned data for pretraining from public resources such as PubMed. In particular, we present a pipeline that streamlines the pre-training process by initially collecting a large brain image-text dataset from case reports and published journals and subsequently constructing a high-performance vision-language model tailored to specific medical tasks. We also investigate the unique challenge of mapping subfigures to subcaptions in the medical domain. We evaluated the resulting model with quantitative and qualitative intrinsic evaluations. The resulting dataset and our code can be found here https://github.com/masoud-monajati/MedVL_pretraining_pipeline.
ABSTRACT
Changes in cerebral blood flow are often associated with the initiation and development of different life-threatening medical conditions including aneurysm rupture and ischemic stroke. Nevertheless, it is not fully clear how haemodynamic changes in time across the Circle of Willis (CoW) are related with intracranial aneurysm (IA) growth. In this work, we introduced a novel reduced-order modelling strategy for the systematic quantification of longitudinal blood flow changes across the whole CoW in patients with stable and unstable/growing aneurysm. Magnetic Resonance Angiography (MRA) images were converted into one-dimensional (1-D) vessel networks through a semi-automated procedure, with a level of geometric reconstruction accuracy controlled by user-dependent parameters. The proposed pipeline was used to systematically analyse longitudinal haemodynamic changes in seven different clinical cases. Our preliminary simulation results indicate that growing aneurysms are not necessarily associated with significant changes in mean flow over time. A concise sensitivity analysis also shed light on which modelling aspects need to be further characterized to have reliable patient-specific predictions. This study poses the basis for investigating how time-dependent changes in the vasculature affect the haemodynamics across the whole CoW in patients with stable and growing aneurysms.
Subject(s)
Cerebrovascular Circulation , Circle of Willis , Intracranial Aneurysm , Magnetic Resonance Angiography , Circle of Willis/physiopathology , Circle of Willis/diagnostic imaging , Humans , Intracranial Aneurysm/physiopathology , Intracranial Aneurysm/diagnostic imaging , Female , Male , Middle Aged , Models, Cardiovascular , Aged , Hemodynamics , AdultABSTRACT
BACKGROUND: Abnormal intracranial aneurysm (IA) wall motion has been associated with IA growth and rupture. Recently, a new image processing algorithm called amplified Flow (aFlow) has been used to successfully track IA wall motion by combining the amplification of cine and four-dimensional (4D) Flow MRI. We sought to apply aFlow to assess wall motion as a potential marker of IA growth in a paired-wise analysis of patients with growing versus stable aneurysms. METHODS: In this retrospective case-control study, 10 patients with growing IAs and a matched cohort of 10 patients with stable IAs who had baseline 4D Flow MRI were included. The aFlow was used to amplify and extract IA wall displacements from 4D Flow MRI. The associations of aFlow parameters with commonly used risk factors and morphometric features were assessed using paired-wise univariate and multivariate analyses. RESULTS: aFlow quantitative results showed significantly (P=0.035) higher wall motion displacement depicted by mean±SD 90th% values of 2.34±0.72 in growing IAs versus 1.39±0.58 in stable IAs with an area under the curve of 0.85. There was also significantly (P<0.05) higher variability of wall deformation across IA geometry in growing versus stable IAs depicted by the dispersion variables including 121-150% larger standard deviation ([Formula: see text]) and 128-161% wider interquartile range [Formula: see text]. CONCLUSIONS: aFlow-derived quantitative assessment of IA wall motion showed greater wall motion and higher variability of wall deformation in growing versus stable IAs.
ABSTRACT
BACKGROUND AND PURPOSE: The review of clinical reports is an essential part of monitoring disease progression. Synthesizing multiple imaging reports is also important for clinical decisions. It is critical to aggregate information quickly and accurately. Machine learning natural language processing (NLP) models hold promise to address an unmet need for report summarization. MATERIALS AND METHODS: We evaluated NLP methods to summarize longitudinal aneurysm reports. A total of 137 clinical reports and 100 PubMed case reports were used in this study. Models were 1) compared against expert-generated summary using longitudinal imaging notes collected in our institute and 2) compared using publicly accessible PubMed case reports. Five AI models were used to summarize the clinical reports, and a sixth model, the online GPT3davinci NLP large language model (LLM), was added for the summarization of PubMed case reports. We assessed the summary quality through comparison with expert summaries using quantitative metrics and quality reviews by experts. RESULTS: In clinical summarization, BARTcnn had the best performance (BERTscore = 0.8371), followed by LongT5Booksum and LEDlegal. In the analysis using PubMed case reports, GPT3davinci demonstrated the best performance, followed by models BARTcnn and then LEDbooksum (BERTscore = 0.894, 0.872, and 0.867, respectively). CONCLUSIONS: AI NLP summarization models demonstrated great potential in summarizing longitudinal aneurysm reports, though none yet reached the level of quality for clinical usage. We found the online GPT LLM outperformed the others; however, the BARTcnn model is potentially more useful because it can be implemented on-site. Future work to improve summarization, address other types of neuroimaging reports, and develop structured reports may allow NLP models to ease clinical workflow.
Subject(s)
Aneurysm , Natural Language Processing , Humans , Machine Learning , Disease Progression , NeuroimagingABSTRACT
The main objective of this work was to evaluate the application of individual and ensemble machine learning models to classify malignant and benign breast masses using features from two-dimensional (2D) correlated spectroscopy spectra extracted from five-dimensional echo-planar correlated spectroscopic imaging (5D EP-COSI) and diffusion-weighted imaging (DWI). Twenty-four different metabolite and lipid ratios with respect to diagonal fat peaks (1.4 ppm, 5.4 ppm) from 2D spectra, and water and fat peaks (4.7 ppm, 1.4 ppm) from one-dimensional non-water-suppressed (NWS) spectra were used as the features. Additionally, water fraction, fat fraction and water-to-fat ratios from NWS spectra and apparent diffusion coefficients (ADC) from DWI were included. The nine most important features were identified using recursive feature elimination, sequential forward selection and correlation analysis. XGBoost (AUC: 93.0%, Accuracy: 85.7%, F1-score: 88.9%, Precision: 88.2%, Sensitivity: 90.4%, Specificity: 84.6%) and GradientBoost (AUC: 94.3%, Accuracy: 89.3%, F1-score: 90.7%, Precision: 87.9%, Sensitivity: 94.2%, Specificity: 83.4%) were the best-performing models. Conventional biomarkers like choline, myo-Inositol, and glycine were statistically significant predictors. Key features contributing to the classification were ADC, 2D diagonal peaks at 0.9 ppm, 2.1 ppm, 3.5 ppm, and 5.4 ppm, cross peaks between 1.4 and 0.9 ppm, 4.3 and 4.1 ppm, 2.3 and 1.6 ppm, and the triglyceryl-fat cross peak. The results highlight the contribution of the 2D spectral peaks to the model, and they demonstrate the potential of 5D EP-COSI for early breast cancer detection.
ABSTRACT
Background: While image-derived predictors of intracranial aneurysm (IA) rupture have been well-explored, current understanding of IA growth is limited. Pulsatility index (PI) and wall shear stress pulsatility index (WSSPI) are important metrics measuring temporal hemodynamic instability. However, they have not been investigated in IA growth research. The present study seeks to verify reliable predictors of IA growth with comparative analyses of several important morphological and hemodynamic metrics between stable and growing cases among a group of unruptured IAs. Methods: Using 3D images, vascular models of 16 stable and 20 growing cases were constructed and verified using Geodesic techniques. With an overall mean follow-up period of 25 months, cases exhibiting a 10% or higher increase in diameter were considered growing. Patient-specific, pulsatile simulations were performed, and hemodynamic calculations were computed at 5 important regions of each aneurysm (inflow artery, aneurysm neck, body, dome, and outflow artery). Index values were compared between growing and stable IAs using ANCOVA controlling for aneurysm diameter. Stepwise multiple logistic regression and ROC analyses were conducted to investigate predictive models of IA growth. Results: Compared to stable IAs, growing IAs exhibited significantly higher intrasaccular PI, intrasaccular WSSPI, intrasaccular spatial flow rate deviation, and intrasaccular spatial wall shear stress (WSS) deviation. Stepwise logistic regression analysis revealed a significant predictive model involving PI at aneurysm body, WSSPI at inflow artery, and WSSPI at aneurysm body. Conclusions: Our results showed that high degree of hemodynamic variations within IAs is linked to growth, even after controlling for morphological parameters. Further, evaluation of PI in conjunction with WSSPI yielded a highly accurate predictive model of IA growth. Upon validation in future cohorts, these metrics may aid in early identification of IA growth and current understanding of IA remodeling mechanism.
ABSTRACT
After detection, identifying which intracranial aneurysms (IAs) will rupture is imperative. We hypothesized that RNA expression in circulating blood reflects IA growth rate as a surrogate of instability and rupture risk. To this end, we performed RNA sequencing on 66 blood samples from IA patients, for which we also calculated the predicted aneurysm trajectory (PAT), a metric quantifying an IA's future growth rate. We dichotomized dataset using the median PAT score into IAs that were either more stable and more likely to grow quickly. The dataset was then randomly divided into training (n = 46) and testing cohorts (n = 20). In training, differentially expressed protein-coding genes were identified as those with expression (TPM > 0.5) in at least 50% of the samples, a q-value < 0.05 (based on modified F-statistics with Benjamini-Hochberg correction), and an absolute fold-change ≥ 1.5. Ingenuity Pathway Analysis was used to construct networks of gene associations and to perform ontology term enrichment analysis. The MATLAB Classification Learner was then employed to assess modeling capability of the differentially expressed genes, using a 5-fold cross validation in training. Finally, the model was applied to the withheld, independent testing cohort (n = 20) to assess its predictive ability. In all, we examined transcriptomes of 66 IA patients, of which 33 IAs were "growing" (PAT ≥ 4.6) and 33 were more "stable". After dividing dataset into training and testing, we identified 39 genes in training as differentially expressed (11 with decreased expression in "growing" and 28 with increased expression). Model genes largely reflected organismal injury and abnormalities and cell to cell signaling and interaction. Preliminary modeling using a subspace discriminant ensemble model achieved a training AUC of 0.85 and a testing AUC of 0.86. In conclusion, transcriptomic expression in circulating blood indeed can distinguish "growing" and "stable" IA cases. The predictive model constructed from these differentially expressed genes could be used to assess IA stability and rupture potential.
ABSTRACT
BACKGROUND: Determining stroke etiology is crucial for secondary prevention, but intensive workups fail to classify ~30% of strokes that are cryptogenic. OBJECTIVE: To examine the hypothesis that the transcriptomic profiles of clots retrieved during mechanical thrombectomy are unique to strokes of different subtypes. METHODS: We isolated RNA from the clots of 73 patients undergoing mechanical thrombectomy. Samples of sufficient quality were subjected to 100-cycle, paired-end RNAseq, and transcriptomes with less than 10 million unique reads were excluded from analysis. Significant differentially expressed genes (DEGs) between subtypes (defined by the Trial of Org 10 172 in Acute Stroke Treatment) were identified by expression analysis in edgeR. Gene ontology enrichment analysis was used to study the biologic differences between stroke etiologies. RESULTS: In all, 38 clot transcriptomes were analyzed; 6 from large artery atherosclerosis (LAA), 21 from cardioembolism (CE), 5 from strokes of other determined origin, and 6 from cryptogenic strokes. Among all comparisons, there were 816 unique DEGs, 174 of which were shared by at least two comparisons, and 20 of which were shared by all three. Gene ontology analysis showed that CE clots reflected high levels of inflammation, LAA clots had greater oxidoreduction and T-cell processes, and clots of other determined origin were enriched for aberrant platelet and hemoglobin-related processes. Principal component analysis indicated separation between these subtypes and showed cryptogenic samples clustered among several different groups. CONCLUSIONS: Expression profiles of stroke clots were identified between stroke etiologies and reflected different biologic responses. Cryptogenic thrombi may be related to multiple etiologies.
Subject(s)
Biological Products , Brain Ischemia , Ischemic Stroke , Stroke , Thrombosis , Humans , Transcriptome/genetics , Ischemic Stroke/complications , Thrombectomy/adverse effects , Thrombosis/therapy , Stroke/genetics , Stroke/surgery , Stroke/complications , Brain Ischemia/genetics , Brain Ischemia/surgery , Brain Ischemia/complicationsABSTRACT
BACKGROUND: Following detection, rupture risk assessment for intracranial aneurysms (IAs) is critical. Towards molecular prognostics, we hypothesized that circulating blood RNA expression profiles are associated with IA risk. METHODS: We performed RNA sequencing on 68 blood samples from IA patients. Here, patients were categorized as either high or low risk by assessment of aneurysm size (≥ 5 mm = high risk) and Population, Hypertension, Age, Size, Earlier subarachnoid hemorrhage, Site (PHASES) score (≥ 1 = high risk). Modified F-statistics and Benjamini-Hochberg false discovery rate correction was performed on transcripts per million-normalized gene counts. Protein-coding genes expressed in ≥ 50% of samples with a q value < 0.05 and an absolute fold-change ≥ 2 were considered significantly differentially expressed. Bioinformatics in Ingenuity Pathway Analysis was performed to understand the biology of risk-associated expression profiles. Association was assessed between gene expression and risk via Pearson correlation analysis. Linear discriminant analysis models using significant genes were created and validated for classification of high-risk cases. RESULTS: We analyzed transcriptomes of 68 IA patients. In these cases, 31 IAs were large (≥ 5 mm), while 26 IAs had a high PHASES score. Based on size, 36 genes associated with high-risk IAs, and two were correlated with the size measurement. Alternatively, based on PHASES score, 76 genes associated with high-risk cases, and nine of them showed significant correlation to the score. Similar ontological terms were associated with both gene profiles, which reflected inflammatory signaling and vascular remodeling. Prediction models based on size and PHASES stratification were able to correctly predict IA risk status, with > 80% testing accuracy for both. CONCLUSIONS: Here, we identified genes associated with IA risk, as quantified by common clinical metrics. Preliminary classification models demonstrated feasibility of assessing IA risk using whole blood expression.
Subject(s)
Aneurysm, Ruptured , Intracranial Aneurysm , Subarachnoid Hemorrhage , Humans , Intracranial Aneurysm/diagnosis , Intracranial Aneurysm/genetics , Aneurysm, Ruptured/etiology , Aneurysm, Ruptured/genetics , Subarachnoid Hemorrhage/etiology , Subarachnoid Hemorrhage/genetics , Transcriptome , Risk Assessment , Gene Expression ProfilingABSTRACT
BACKGROUND: Studying the relationship between hemodynamics and local intracranial aneurysm (IA) pathobiology can help us understand the natural history of IA. We characterized the relationship between the IA wall appearance, using intraoperative imaging, and the hemodynamics from CFD simulations. METHODS: Three-dimensional geometries of 15 IAs were constructed and used for CFD. Two-dimensional intraoperative images were subjected to wall classification using a machine learning approach, after which the wall type was mapped onto the 3D surface. IA wall regions included thick (white), normal (purple-crimson), and thin/translucent (red) regions. IA-wide and local statistical analyses were performed to assess the relationship between hemodynamics and wall type. RESULTS: Thin regions of the IA sac had significantly higher WSS, Normalized WSS, WSS Divergence and Transverse WSS, compared to both normal and thick regions. Thicker regions tended to co-locate with significantly higher RRT than thin regions. These trends were observed on a local scale as well. Regression analysis showed a significant positive correlation between WSS and thin regions and a significant negative correlation between WSSD and thick regions. CONCLUSION: Hemodynamic simulation results were associated with the intraoperatively observed IA wall type. We consistently found that elevated WSS and WSSNorm were associated with thin regions of the IA wall rather than thick and normal regions.
ABSTRACT
A comparative analysis between intravascular guidewire-obtained and computational fluid dynamic (CFD) flow velocity and pressure data using simplified carotid stenosis models was performed. This information was used to evaluate the viability of using guidewire pressure data to provide inlet conditions for CFD flow, and to study the relationship between stenotic length and hemodynamic behavior. Carotid stenosis models differing in diameter and length were prepared and connected to a vascular pulsatile flow simulator. Time-dependent flow velocity and pressure measurements were taken by microcatheter guidewires and compared with CFD data. Guidewire and CFD-generated pressure profiles matched closely in all measurement locations. The guidewire was unable to reliably measure flow velocity at areas associated with higher CFD flow velocities (r = 0.92). CFD results showed that an increased length of stenosis generated expansive regions of elevated wall shear stress (WSS) within and distal to the stenosis. Low WSS was found immediately outside the stenosis outlet. An increase in stenotic length produced higher flow velocities with minimal lengthening of the distal high velocity flow jet due to faster dissipation of translational kinetic energy through turbulence. We found the accuracy of guidewire-obtained velocity measurements is limited to regions unaffected by disturbed flow. WSS and turbulence behavior distal to the stenosis may be important markers to evaluate the severity of atherosclerotic progression as a function of stenotic length.
Subject(s)
Carotid Stenosis , Blood Flow Velocity , Computer Simulation , Constriction, Pathologic , Hemodynamics , Humans , Hydrodynamics , Models, Cardiovascular , Stress, MechanicalABSTRACT
Goal: Identifying population differences can serve as an insightful tool for diagnostic radiology. To do so, a reliable preprocessing framework and data representation are vital. Methods: We build a machine learning model to visualize gender differences in the circle of Willis (CoW), an integral part of the brain's vasculature. We start with a dataset of 570 individuals and process them for analysis using 389 for the final analysis. Results: We find statistical differences between male and female patients in one image plane and visualize where they are. We can see differences between the right and left-hand sides of the brain confirmed using Support Vector Machines (SVM). Conclusion: This process can be applied to detect population variations in the vasculature automatically. Significance: It can guide debugging and inferring complex machine learning algorithms such as SVM and deep learning models.
ABSTRACT
Background and Purpose: Since growing intracranial aneurysms (IA) are more likely to rupture, detecting growth is an important part of unruptured IA follow-up. Recent studies have consistently shown that detecting IA growth can be challenging, especially in smaller aneurysms. In this study, we present an automated computational method to assist detecting aneurysm growth. Materials and Methods: An analysis program, Aneurysm Growth Evaluation & Detection (AGED) based on IA images was developed. To verify the program can satisfactorily detect clinical aneurysm growth, we performed this comparative study using clinical determinations of growth during IA follow-up as a gold standard. Patients with unruptured, saccular IA followed by diagnostic brain CTA to monitor IA progression were reviewed. 48 IA image series from twenty longitudinally-followed ICA IA were analyzed using AGED. A set of IA morphologic features were calculated. Nonparametric statistical tests and ROC analysis were performed to evaluate the performance of each feature for growth detection. Results: The set of automatically calculated morphologic features demonstrated comparable results to standard, manual clinical IA growth evaluation. Specifically, automatically calculated HMAX was superior (AUC = 0.958) at distinguishing growing and stable IA, followed by V, and SA (AUC = 0.927 and 0.917, respectively). Conclusion: Our findings support automatic methods of detecting IA growth from sequential imaging studies as a useful adjunct to standard clinical assessment. AGED-generated growth detection shows promise for characterization and detection of IA growth and time-saving comparing with manual measurements.
ABSTRACT
Cerebrovascular diseases are among the world's top causes of death and their screening and diagnosis rely on angiographic imaging. We focused on automated anatomical labeling of cerebral arteries that enables their cross-sectional quantification and inter-subject comparisons and thereby identification of geometric risk factors correlated to the cerebrovascular diseases. We used 152 cerebral TOF-MRA angiograms from three publicly available datasets and manually created reference labeling using Slicer3D. We extracted centerlines from nnU-net based segmentations using VesselVio and labeled them according to the reference labeling. Vessel centerline coordinates, in combination with additional vessel connectivity, radius and spatial context features were used for training seven distinct PointNet++ models. Model trained solely on the vessel centerline coordinates resulted in ACC of 0.93 and across-labels average TPR was 0.88. Including vessel radius significantly improved ACC to 0.95, and average TPR to 0.91. Finally, focusing spatial context to the Circle of Willis are resulted in best ACC of 0.96 and best average TPR of 0.93. Hence, using vessel radius and spatial context greatly improved vessel labeling, with the attained perfomance opening the avenue for clinical applications of intracranial vessel labeling.
ABSTRACT
Vision-and-language (V&L) models take image and text as input and learn to capture the associations between them. These models can potentially deal with the tasks that involve understanding medical images along with their associated text. However, applying V&L models in the medical domain is challenging due to the expensiveness of data annotations and the requirements of domain knowledge. In this paper, we identify that the visual representation in general V&L models is not suitable for processing medical data. To overcome this limitation, we propose BERTHop, a transformer-based model based on PixelHop++ and VisualBERT for better capturing the associations between clinical notes and medical images. Experiments on the OpenI dataset, a commonly used thoracic disease diagnosis benchmark, show that BERTHop achieves an average Area Under the Curve (AUC) of 98.12% which is 1.62% higher than state-of-the-art while it is trained on a 9× smaller dataset.
ABSTRACT
BACKGROUND: Current in vitro models for human brain arteriovenous malformation (AVM) analyzing the efficacy of embolic materials or flow conditions are limited by a lack of realistic anatomic features of complex AVM nidus. The purpose of this study was to evaluate a newly developed in vitro AVM model for embolic material testing, preclinical training, and flow analysis. METHODS: Three-dimensional (3D) images of the AVM nidus were extracted from 3D rotational angiography from a patient. Inner vascular mold was printed using a 3D printer, coated with polydimethylsiloxanes, and then was removed by acetone, leaving a hollow AVM model. Injections of liquid embolic material and 4-dimensional (4D) flow magnetic resonance imaging (MRI) were performed using the AVM models. Additionally, computational fluid dynamics analysis was performed to examine the flow volume rate as compared with 4D flow MRI. RESULTS: The manufacture of 3D in vitro AVM models delivers a realistic representation of human nidus vasculature and complexity derived from patients. The injection of liquid embolic agents performed in the in vitro model successfully replicated real-life treatment conditions. The model simulated the plug and push technique before penetration of the liquid embolic material into the AVM nidus. The 4D flow MRI results were comparable to computational fluid dynamics analysis. CONCLUSIONS: An in vitro human brain AVM model with realistic geometric complexities of nidus was successfully created using 3D printing technology. This AVM model offers a useful tool for training of embolization techniques and analysis of hemodynamics analysis, and development of new devices and materials.
Subject(s)
Embolization, Therapeutic/methods , Endovascular Procedures/methods , Intracranial Arteriovenous Malformations/physiopathology , Intracranial Arteriovenous Malformations/surgery , Models, Neurological , Cerebral Angiography , Hemodynamics , Humans , Hydrodynamics , Imaging, Three-Dimensional , Printing, Three-DimensionalABSTRACT
OBJECTIVE: Aneurysm rupture risk can be assessed by its morphologic and hemodynamics features extracted based on angiographic images. Feature extraction entails aneurysm isolation, typically by manually positioning a cutting plane (MCP). To eliminate intra- and inter-rater variabilities, we propose automatic cutting plane (ACP) positioning based on the analysis of vascular surface mesh. METHODS: Innovative Hough-like and multi-hypothesis-based detection of aneurysm center, parent vessel inlets, and centerlines were proposed. These were used for initialization and iterative ACP positioning by geometry-inspired cost function optimization. For validation and baseline comparison, we tested MCP and manual neck curve-based isolation. Isolated aneurysm morphology was characterized by size, dome height, aspect ratio, and nonsphericity index. RESULTS: Methods were applied to 55 intracranial saccular aneurysms from two sites, involving 3-D digital subtraction angiography, computed tomography angiography, and magnetic resonance angiography modalities. Isolation based on ACP resulted in smaller average inter-curve distances (AICDs), compared to those obtained by MCP. One case had AICD higher than 1.0 mm, while 90% of cases had AICD 0.5 mm. Intra- and inter-rater AICD variability of manual neck curves was higher compared to MCP, validating its robustness for clinical purposes. CONCLUSION: The ACP method achieved high accuracy and reliability of aneurysm isolation, also confirmed by expert visual analysis. So extracted morphologic features were in good agreement with MCP-based ones, therefore, ACP has great potential for aneurysm morphology and hemodynamics quantification in clinical applications. SIGNIFICANCE: The novel method is angiographic modality agnostic; it delivers repeatable isolation important in follow-up aneurysm assessment; its performance is comparable to MCP; and re-evaluation is fast and simple.
Subject(s)
Angiography/methods , Image Interpretation, Computer-Assisted/methods , Imaging, Three-Dimensional/methods , Intracranial Aneurysm/diagnostic imaging , Algorithms , HumansABSTRACT
OBJECTIVE: As imaging technology has improved, more unruptured intracranial aneurysms (UIAs) are detected incidentally. However, there is limited information regarding how UIAs change over time to provide stratified, patient-specific UIA follow-up management. The authors sought to enrich understanding of the natural history of UIAs and identify basic UIA growth trajectories, that is, the speed at which various UIAs increase in size. METHODS: From January 2005 to December 2015, 382 patients diagnosed with UIAs (n = 520) were followed up at UCLA Medical Center through serial imaging. UIA characteristics and patient-specific variables were studied to identify risk factors associated with aneurysm growth and create a predicted aneurysm trajectory (PAT) model to differentiate aneurysm growth behavior. RESULTS: The PAT model indicated that smoking and hypothyroidism had a large effect on the growth rate of large UIAs (≥ 7 mm), while UIAs < 7 mm were less influenced by smoking and hypothyroidism. Analysis of risk factors related to growth showed that initial size and multiplicity were significant factors related to aneurysm growth and were consistent across different definitions of growth. A 1.09-fold increase in risk of growth was found for every 1-mm increase in initial size (95% CI 1.04-1.15; p = 0.001). Aneurysms in patients with multiple aneurysms were 2.43-fold more likely to grow than those in patients with single aneurysms (95% CI 1.36-4.35; p = 0.003). The growth rate (speed) for large UIAs (≥ 7 mm; 0.085 mm/month) was significantly faster than that for UIAs < 3 mm (0.030 mm/month) and for males than for females (0.089 and 0.045 mm/month, respectively; p = 0.048). CONCLUSIONS: Analyzing longitudinal UIA data as continuous data points can be useful to study the risk of growth and predict the aneurysm growth trajectory. Individual patient characteristics (demographics, behavior, medical history) may have a significant effect on the speed of UIA growth, and predictive models such as PAT may help optimize follow-up frequency for UIA management.
ABSTRACT
BACKGROUND: The neurovasculature dynamically responds to changes in cerebral blood flow by vascular remodeling processes. Serial imaging studies in mouse models could help characterize pathologic and physiologic flow-induced remodeling of the Circle of Willis (CoW). METHOD: We induced flow-driven pathologic cerebral vascular remodeling in the CoW of mice (n=3) by ligation of the left Common Carotid Artery (CCA), and the right external carotid and pterygopalatine arteries, increasing blood flow through the basilar and the right internal carotid arteries. One additional mouse was used as a wild-type control. Magnetic Resonance Imaging (MRI) at 9.4 Tesla (T) was used to serially image the mouse CoW over three months, and to obtain threedimensional images for use in Computational Fluid Dynamic (CFD) simulations. Terminal vascular corrosion casting and scanning electron microscope imaging were used to identify regions of macroscopic and microscopic arterial damage. RESULTS: We demonstrated the feasibility of detecting and serially measuring pathologic cerebral vascular changes in the mouse CoW, specifically in the anterior vasculature. These changes were characterized by bulging and increased vessel tortuosity on the anterior cerebral artery and aneurysm- like remodeling at the right olfactory artery origin. The resolution of the 9.4T system further allowed us to perform CFD simulations in the anterior CoW, which showed a correlation between elevated wall shear stress and pathological vascular changes. CONCLUSION: In the future, serial high-resolution MRI could be useful for characterizing the flow environments corresponding to other pathologic remodeling processes in the mouse CoW, such as aneurysm formation, subarachnoid hemorrhage, and ischemia.