Aneurysm Size Measurements Research Articles

Deep learning techniques for imaging diagnosis and treatment of aortic aneurysm.

This study aims to review the application of deep learning techniques in the imaging diagnosis and treatment of aortic aneurysm (AA), focusing on screening, diagnosis, lesion segmentation, surgical assistance, and prognosis prediction. A comprehensive literature review was conducted, analyzing studies that utilized deep learning models such as Convolutional Neural Networks (CNNs) in various aspects of AA management. The review covered applications in screening, segmentation, surgical planning, and prognosis prediction, with a focus on how these models improve diagnosis and treatment outcomes. Deep learning models demonstrated significant advancements in AA management. For screening and diagnosis, models like ResNet achieved high accuracy in identifying AA in non-contrast CT scans. In segmentation, techniques like U-Net provided precise measurements of aneurysm size and volume, crucial for surgical planning. Deep learning also assisted in surgical procedures by accurately predicting stent placement and postoperative complications. Furthermore, models were able to predict AA progression and patient prognosis with high accuracy. Deep learning technologies show remarkable potential in enhancing the diagnosis, treatment, and management of AA. These advancements could lead to more accurate and personalized patient care, improving outcomes in AA management.

RAPID aneurysm accurately measures aneurysm size on CT angiography compared to three-dimensional digital subtraction angiography.

Cerebral aneurysms are often identified and characterized on non-invasive CT Angiography (CTA) images, but digital subtraction angiography (DSA) is the gold standard for aneurysm evaluation. We compared cerebral aneurysm size measurements as measured from CTA processed by a semi-automated artificial intelligence software program (RAPID Aneurysm) and three-dimensional rotational DSA (3D-DSA). We performed a retrospective cohort study of consecutive patients with a cerebral aneurysm who underwent CTA and DSA with 3D reformations. CTA images were processed by RAPID Aneurysm to determine aneurysm height, width, and neck width. The reference standard was aneurysm measurements on 3D-DSA as measured by two neurointerventionalists. Both readers were blinded to RAPID Aneurysm measurements. Correlation and bias between these measurements were determined. Results from 50 patients with 50 aneurysms were compared. 32 patients (64%) were female. Median age was 65 (IQR: 56.25-71.75). 37 patients (74%) presented with ruptured aneurysms. The aneurysms represented a range of aneurysm sizes (1.9-33.3 mm; IQR 3.6-7.2 mm). RAPID Aneurysm size measurements showed excellent correlation and low bias (correlation, mean difference) when compared to the reference standard for aneurysm height (0.98, -0.9 mm), width (0.98, 0.1 mm), and neck width (0.94, 1.1 mm). The inter-reader comparison between the two neurointerventionalists was similarly excellent for aneurysm height (0.97, -0.4 mm), width (0.98, -0.2 mm), and neck width (0.89, 0.8 mm). RAPID Aneurysm measurement of cerebral aneurysm height, width, and neck width on CTA is strongly correlated to expert neurointerventionalist measurements on 3D-DSA.

Correlating cerebral aneurysm size measurements based on virtual reality versus standard 2D DSA measurements; a randomised comparative study

Correlating cerebral aneurysm size measurements based on virtual reality versus standard 2D DSA measurements; a randomised comparative study

Neural operator learning of heterogeneous mechanobiological insults contributing to aortic aneurysms.

Thoracic aortic aneurysm (TAA) is a localized dilatation of the aorta that can lead to life-threatening dissection or rupture. In vivo assessments of TAA progression are largely limited to measurements of aneurysm size and growth rate. There is promise, however, that computational modelling of the evolving biomechanics of the aorta could predict future geometry and properties from initiating mechanobiological insults. We present an integrated framework to train a deep operator network (DeepONet)-based surrogate model to identify TAA contributing factors using synthetic finite-element-based datasets. For training, we employ a constrained mixture model of aortic growth and remodelling to generate maps of local aortic dilatation and distensibility for multiple TAA risk factors. We evaluate the performance of the surrogate model for insult distributions varying from fusiform (analytically defined) to complex (randomly generated). We propose two frameworks, one trained on sparse information and one on full-field greyscale images, to gain insight into a preferred neural operator-based approach. We show that this continuous learning approach can predict the patient-specific insult profile associated with any given dilatation and distensibility map with high accuracy, particularly when based on full-field images. Our findings demonstrate the feasibility of applying DeepONet to support transfer learning of patient-specific inputs to predict TAA progression.

A comparison between the CS-TOF and the CTA/DSA for WEB device management.

There is no study on the role of three-dimensional compressed sensing time of flight MR angiography (3D-CS-TOF) in the management of the WEB device. We evaluated the efficacy of 3-tesla 3D-CS-TOF for the management and follow-up of the WEB device implantations. Seventy-three aneurysms of 69 patients treated with the WEB device were retrospectively examined. Morphological parameters and embolization results of the aneurysms were assessed and compared on 3D-CS-TOF, CTA, and DSA images. Occluded, neck remnant, and recurrent aneurysms were observed in 61 (83.6%), 7 (9.6%), and 5 (6.8%) aneurysms, respectively. Inter- and intra-reader agreement values related to aneurysm size measurements were perfect. Aneurysms size, age, and proximal vessel tortuosity were negatively correlated with the visibility of the aneurysms and parent vessels on 3D-CS-TOF images (p = 0.043; p = 0.032; p < 0.001, respectively). Subarachnoid hemorrhage and age are associated with 3D-CS-TOF artifacts (p = 0.031; p = 0.005, respectively). 3D-CS-TOF findings are in perfect agreement with DSA or CT angiography (CTA) results (p < 0.001). According to our results, 3D-CS-TOF can be an easy, fast, and reliable alternative for the management or follow-up of WEB assisted embolization.

Volume-based sizing of the Woven EndoBridge (WEB) device: A preliminary assessment of a novel method for device size selection.

Accurate sizing of the Woven EndoBridge (WEB) device is of critical importance as it determines procedural safety and successful occlusion of wide neck bifurcation aneurysms. The aim of this study was to assess the ability of aneurysm volume to assist in accurate WEB size selection. All patients with an intracranial aneurysm treated with the WEB SL or WEB SLS device between March 2019 and October 2019 were identified for this retrospective study. Aneurysm volumes were calculated with auto-segmentation using a three-dimensional volume rendering program on an independent Syngo workstation (Siemens Healthineers AG). Pearson correlation coefficients were calculated for aneurysm auto-segmented volumes and WEB volumes, as well as for aneurysm height × width and WEB height × width. Follow-up angiographic outcomes were collected at 6-9 months post-procedure. Twenty-nine aneurysms were evaluated by 3D rotational angiography. The correlation coefficient with WEB size was larger for auto-segmented aneurysm volumes (r = 0.979) compared to height × width measurements (r = 0.867). Using Fisher r-to-z transformations, we found the difference between the two correlations to be statistically significant (p = 0.0007). Follow-up angiography available in 13 subjects demonstrated an 85% complete aneurysm occlusion rate. Aneurysm volumes are highly correlated with WEB volumes, with auto-segmentation volumes displaying statistically significant difference against conventional height by width measurements. These results suggest that volumetric measurements of aneurysm size provide a useful adjuvant measure to assist in appropriate size selection of the WEB device.

Scoring of Growth of Unruptured Intracranial Aneurysms.

The purpose was to obtain a reliable scoring for growth of unruptured intracranial aneurysms (UIAs) in a long-term follow-up study from variables known at baseline and to compare it with the ELAPSS (Earlier subarachnoid hemorrhage, Location of the aneurysm, Age > 60 years, Population, Size of the aneurysm, and Shape of the aneurysm) score obtained from an individual-based meta-analysis. The series consists of 87 patients with 111 UIAs and 1669 person-years of follow-up between aneurysm size measurements (median follow-up time per patient 21.7, range 1.2 to 51.0 years). These were initially diagnosed between 1956 and 1978, when UIAs were not treated in our country. ELAPSS scores at baseline did not differ between those with and those without aneurysm growth. The area under the curve (AUC) for the receiver operating curve (ROC) of the ELAPSS score for predicting long-term growth was fail (0.474, 95% CI 0.345–0.603), and the optimal cut-off point was obtained at ≥7 vs. <7 points for sensitivity (0.829) and specificity (0.217). In the present series UIA growth was best predicted by female sex (4 points), smoking at baseline (3 points), and age <40 years (2 points). The AUC for the ROC of the new scoring was fair (0.662, 95% CI 0.546–0.779), which was significantly better than that of ELAPSS score (p < 0.05). The optimal cut-off point was obtained at ≥4 vs. <4 points for sensitivity (0.971) and specificity (0.304). A new simple scoring consisting of only female sex, cigarette smoking and age <40 years predicted growth of an intracranial aneurysm in long-term follow-up, significantly better than the ELAPSS score.

7T versus 3T MR Angiography to Assess Unruptured Intracranial Aneurysms.

ABSTRACTBACKGROUND AND PURPOSEAneurysm size and neck measurements are important for treatment decisions. The introduction of 7T magnetic resonance angiography (MRA) led to new possibilities assessing aneurysm morphology and flow due to the higher signal‐to‐noise ratio. However, it is unknown if the size measurements on 7T MRA are similar to those on the standard 3T MRA. This study aimed to compare aneurysm size measurements between 7T and 3T MRA.METHODSWe included 18 patients with 22 aneurysms who underwent both 3T and 7T MRA. Three acquisition protocols were compared: 3T time of flight (TOF), 7T TOF, and 7T contrast‐enhanced MRA. Each aneurysm on each protocol was measured by at least two experienced neuroradiologists. Subsequently, the differences were evaluated using scatterplots and the intraclass correlation coefficients (ICC) of agreement.RESULTSThere was a good agreement among the neuroradiologists for the height and width measurements (mean ICC: .78‐.93); the neck measurements showed a moderate agreement with a mean ICC of .57‐.72. Between the MR acquisition protocols, there was a high agreement for all measurements with a mean ICC of .81‐.96. Measurement differences between acquisition protocols (0‐2.9 mm) were in the range of the differences between the neuroradiologists (0‐3.6 mm).CONCLUSIONOur study showed that 7T MRA, both nonenhanced and contrast‐enhanced, has a high agreement in aneurysm size measurements compared to 3T. This suggests that 7T is useful for reliable aneurysm size assessment.

Differential Subsampling with Cartesian Ordering for Ultrafast High-Resolution MRA in the Assessment of Intracranial Aneurysms.

We aimed to evaluate the feasibility of an ultrafast whole head contrast-enhanced MRA (CE-MRA) in morphometric assessment of intracranial aneurysms in comparison to routinely used time-of-flight (TOF)-MRA. In this prospective single institutional study, patients with known untreated intracranial aneurysm underwent MRA. Routine multislab TOF-MRA was obtained with a 3D voxel sizes of .6 × .6 × 1 (6-minute acquisition time). CE-MRA of whole head was obtained using Differential Subsampling with Cartesian Ordering (DISCO) and 2D Auto-calibrating Reconstruction for Cartesian imaging with a 3D voxel-sizes of .75 × .75 × 1 mm3 during a 6-second temporal resolution. Morphometric features of intracranial aneurysms, including size, aneurysm sac morphology, and the presence of intraluminal thrombosis, were assessed on both techniques. Statistical analysis was performed using a combination of Kappa test, Bland-Altman, and correlation coefficient analysis. A total of 34 aneurysms in 28 patients were included. Aneurysm size measurements (mean ± SD) were similar between DISCO-MRA (4.1 ± 2.3 mm) and TOF-MRA (4.3 ± 2.8 mm) (P = .27). Bland-Altman analysis showed a mean difference of .4 mm and there was excellent correlation r = .91 (95% CI: .87-.96). In six aneurysms (17.6%), TOF-MRA was nonconfidant to exclude intraluminal thrombosis. In seven aneurysms (20%), TOF-MRA was unable or nonconfidant in depicting aneurysm sac morphology. Described ultrafast high spatial-resolution MRA is superior to routinely used TOF-MRA in assessment of morphometric features of intracranial aneurysms, such as intraluminal thrombosis and aneurysm morphology, and is obtained in a fraction of the time (6 seconds).

Multi-modality molecular imaging of aortic aneurysms

Aneurysms of the thoracic and abdominal aorta are common and can be associated with significant morbidity and mortality when complications, including dissection, rupture, or thrombosis, occur. Current approaches to diagnosis and risk stratification rely on measurements of aneurysm size and rate of growth, often using various imaging modalities, which may be suboptimal in identifying patients at the highest and lowest risk of complications. Targeting the biological processes underlying aneurysm formation and expansion with molecular imaging offers an exciting opportunity to characterize aortic aneurysms beyond size and address current gaps in our approach to diagnosis and treatment. In this review, we summarize the epidemiology and biology of aortic aneurysms and highlight the role of molecular imaging in furthering our understanding of aneurysm pathogenesis and its potential future role in guiding management.

Comparing Accuracy of Cerebral Aneurysm Size Measurements From Three Routine Investigations: Computed Tomography, Magnetic Resonance Imaging, and Digital Subtraction Angiography

Modern imaging technologies, such as computed tomography (CT) angiography, magnetic resonance (MR) angiography, and digital subtraction (DS) angiography are widely used for pretreatment evaluation of cerebral aneurysms, but the relative accuracies of these modalities are unclear. This study compared the measurements of aneurysm neck and dome height and width on CT angiography, time-of-flight (TOF)-MR angiography, and DS angiography using a three-dimensional workstation. An elastic model of a side-wall aneurysm was connected to an artificial heart pulsatile circuit system. The aneurysm model was prepared using a silicone membrane of 0.6-mm thickness under normal physiological circulation parameters. Using this aneurysm model, three-dimensional TOF-MR angiography, contrast-enhanced CT angiography, and DS angiography were performed. Source images were post-processed on a dedicated workstation to calculate the aneurysm size. DS angiography measurements were found to be the most accurate. In contrast, aneurysm neck sizes measured on CT angiography were significantly wider than actual values (p < 0.05) and aneurysm heights measured using TOF-MR angiography were significantly lower than actual values (p < 0.01). In this in-vitro model, at least one aneurysm dimension measured with CT angiography and with TOF-MR angiography differed significantly from actual values. Aneurysm neck width markedly affects therapeutic planning, as a wide neck requires craniotomy or endovascular treatment using an adjunctive device, so inaccuracies should be considered when aneurysm treatment is planned using modern methods of visualization.

Risk of growth in unruptured intracranial aneurysms: A retrospective analysis

This study sought to define the growth of unruptured intracranial aneurysms, in particular the frequency of growth and the characteristic factors predictive of growth. Two hundred and eight patients with 285 unruptured aneurysms were followed. Electronic records and angiographic films were obtained for measurements of aneurysm size. The mean follow-up duration was 21.8 months (range 1.1–137.3 months). Growth was identified in 95 of the 285 aneurysms (33.3%). The cumulative incidence of growth predicted using the Kaplan-Meier method was 22.7% at 1 year, 35.2% at 2 years, and 47.7% at 3 years. Aneurysm growth was significantly associated with a patient history of excessive alcohol consumption ( p = 0.04). A high incidence of growth can be seen in conservatively managed aneurysms with time. Consequently, continual follow-up is recommended to monitor for aneurysmal growth.

Abdominal aortic aneurysm diameter: A comparison of ultrasound measurements with those from standard and three-dimensional computed tomography reconstruction

Aortic aneurysm size is a critical determinant of the need for intervention, yet the maximal diameter will often vary depending on the modality and method of measurement. We aimed to define the relationship between commonly used computed tomography (CT) measurement techniques and those based on current reporting standards and to compare the values obtained with diameter measured using ultrasound (US). CT scans from patients with US-detected aneurysms were analyzed using three-dimensional reconstruction software. Maximal aortic diameter was recorded in the anteroposterior (CT-AP) plane, along the maximal ellipse (CT-ME), perpendicular to the maximal ellipse (CT-PME), or perpendicular to the centerline of flow (CT-PCLF). Diameter measurements were compared with each other and with maximal AP diameter according to US (US-AP). Analysis was performed according to the principles of Bland and Altman. Results are expressed as mean +/- standard deviation. CT and US scans from 109 patients (92 men, 17 women), with a mean age of 72 +/- 8 years, were included. The mean of each series of readings on CT was significantly larger than the mean US-AP measurement (P < .001), and they also differed significantly from each other (P < .001). The CT-PCLF diameter was larger than CT-AP and CT-PME by mean values of 3.0 +/- 6.6 and 5.9 +/- 6.0 mm, respectively. The CT-ME diameter was larger than CT-PCLF by a mean of 2.4 +/- 5 mm. The US-AP diameter was smaller than CT-AP diameter by 4.2 +/- 4.9 mm, CT-ME by 9.6 +/- 8.0 mm, CT-PME by 1.3 +/- 5 mm, and smaller than CT-PCLF by 7.3 +/- 7.0 mm. Aneurysm size did not significantly affect these differences. Seventy-eight percent of 120 pairs of intraobserver CT measurements and 65% of interobserver CT measurements differed by <2 mm. CT-based measurements of aneurysm size tend to be larger than the US-AP measurement. CT-PCLF diameters are consistently larger than CT-PME as well as CT-AP measurements. These differences should be considered when applying evidence from previous trials to clinical decisions.

Inter- and intraobserver variability of CT measurements obtained after endovascular repair of abdominal aortic aneurysms.

Important decisions are made on the basis of CT angiographic measurements of aneurysm size obtained after endovascular abdominal aortic aneurysm repair; however, little is known about the variability of these measurements. We evaluated the variability of CT angiographic measurements of aneurysm size obtained after endovascular abdominal aortic aneurysm repair. Thirty CT angiographic data sets were randomly chosen from 91 sets, including preoperative, postoperative, and follow-up CT images. All images were obtained according to a standardized acquisition protocol. On a workstation, three parameters were measured: maximum aneurysm diameter, maximum aneurysm cross-sectional area, and aneurysm volume. All data sets were measured twice by two investigators in a random order. The difference of each pair of measurements was plotted against the mean value. The mean difference and its standard deviation were calculated with a repeatability coefficient. The intraobserver repeatability coefficient for observer 1 was 3.8 mm for diameter, 201.7 mm(2) for cross-sectional area, and 5.6 mL for volume. For observer 2, these figures were 3.0 mm, 219.0 mm(2), and 8.1 mL, respectively. The interobserver repeatability coefficients were 3.9 mm, 236.2 mm(2), and 10.3 mL. Determination of the repeatability coefficient of aneurysm size measurements obtained after endovascular abdominal aortic aneurysm repair provides a good description of precision.

Transcranial power mode Doppler duplex sonography of intracranial aneurysms.

The application of different color-coding techniques in transcranial color-coded duplex sonography (TCCD) was assessed for detection and measurement of the size of intracranial aneurysms. Thirty-two consecutively examined patients with 36 angiographically verified cerebral aneurysms underwent TCCD with color Doppler flow imaging (CDFI), power Doppler imaging (PDI), and both methods with contrast enhancement. The diameters of the aneurysms were measured in comparable planes by means of angiography and TCCD-PD with and without 400 mg/ml of the monosaccharide microparticle contrast agent Levovist. TCCD with CFD enabled detection of 27 of 36 aneurysms (75%), and PD depicted 29 aneurysms (80%). After administration of Levovist, an additional two aneurysms were detected with CFD and three with PD color coding. Measurements of aneurysm size obtained by means of PD with contrast enhancement corresponded more highly with angiographic findings than did measurements obtained with PD alone. Use of alternative color-coding techniques with the addition of contrast agents increases the number of intracranial nonthrombosed aneurysms detectable with TCCD.

Retroperitoneal nonresective staple exclusion of abdominal aortic aneurysms: clinical outcome and fate of the excluded abdominal aortic aneurysms.

The purpose of this article was to prospectively study analyses outcome after staple exclusion of abdominal aneurysms with specific follow-up of the excluded aneurysm. Whether these data may predict behavior of aneurysms excluded from the circulation by transluminal grafting procedures is also addressed. Staple exclusion of abdominal aneurysms with bypass via retroperitoneal incisions was performed in 100 consecutive patients undergoing elective procedures. Risk factors, clamp time, operative time, transfusions, length of stay, complications, platelets, fibrinogen, and fibrin split products were documented. Duplex imaging was performed quarterly for 1 year after exclusion and at least annually thereafter. Serial measurements of aneurysm size and evaluation for thrombosis was obtained. Aneurysm size averaged 5.5 cm. Risk factors included history of smoking (54%), history of heart disease (51%), hypertension (41%), hyperlipidemia (34%), and chronic obstructive pulmonary disease (25%). Clamp time averaged 51 minutes. Forty-eight required no intraoperative transfusion, and 19 needed only autologous blood; the average 24-hour transfusion was 313 cc. Length of stay averaged 11 days, with a median of 8 days, and correlated with age, aneurysm size, and risk factors. The 30-day mortality rate was 4%. Death was associated with longer operative and anesthesia times and with age and risk factors. As calculated by life-table analysis to 5 years, 96.8% of aneurysms thrombosed. No aneurysm expanded, became symptomatic, nor ruptured. Perioperative platelet, fibrinogen, and fibrin split product assays show no evidence of disseminated intravascular coagulation or consumptive coagulopathy. Staple exclusion and bypass of abdominal aneurysms as described in this study is safe and effective. There has been neither aneurysm expansion nor rupture, and the technique reliably leads to thrombosis of aneurysms without coagulopathy.