Artificial intelligence and machine learning in aortic disease
31
Citation
36
Reference
10
Related Paper
Citation Trend
Abstract:
Discuss foundational concepts for artificial intelligence (AI) and review recent literature on its application to aortic disease.Machine learning (ML) techniques are rapidly evolving for the evaluation of aortic disease - broadly categorized as algorithms for aortic segmentation, detection of pathology, and risk stratification. Advances in deep learning, particularly U-Net architectures, have revolutionized segmentation of the aorta and show potential for monitoring the size of aortic aneurysm and characterizing aortic dissection. These algorithms also facilitate application of more complex technologies including analysis of flow dynamics with 4D Flow magnetic resonance imaging (MRI) and computational simulation of fluid dynamics for aortic coarctation. In addition, AI algorithms have been proposed to assist in 'opportunistic' screening from routine imaging exams, including automated aortic calcification score, which has emerged as a strong predictor of cardiovascular risk. Finally, several ML algorithms are being explored for risk stratification of patients with aortic aneurysm and dissection, in addition to prediction of postprocedural complications.Multiple ML techniques have potential for characterization and risk prediction of aortic aneurysm, dissection, coarctation, and atherosclerotic disease on computed tomography and MRI. This nascent field shows considerable promise with many applications in development and in early preclinical evaluation.Keywords:
Risk Stratification
배경: SAH의 rupture aneurysm은 다양한 부위에서 다양하게 발병한다. 특히, 두개이상의 다수의 aneurysm이 존재할 경우에는 aneurysm중 먼저 rupture되는 aneurysm을 찾아 치료하는 일은 시급히 선행되어야 할 과제이다. 목적: 따라서 본 논문에서는 다수의 aneurysm이 존재하는 경우 rupture aneurysm이 주로 발병하는 위치가 어디이며, 나아가 rupture aneurysm의 모양에 대해서 알아보고자 한다. 대상 및 방법: 2011년 1월부터 2012년 12월까지 경북대학교병원에서 subarachnoid hemorrhage로 내원한 환자를 대상으로 Angio, CT angio 영상을 기준으로 aneurysm의 개수가 2개 이상인 환자를 대상으로 aneurysm의 rupture 유무, 크기, 모양에 대해서 알아보았다. Aneurysm의 모양은 각각의 특성에 따라 S a , S w , L a , L d , F a 로 나누어 분류하였다. Aneurysm의 rupture 유무는 Neuro intervention 영상의학전문의에 자문으로 이루어졌다. 결과: 2011년 1월부터 2012년 12월까지 SAH로 내원한 환자 모두는 281명이었으며 그 중 두 개이상의 aneurysm이 발견된 환자는 모두 58명이었다. 이 58명의 환자 중 aneurysm이 rupture된 부위는 A-com에서 16명 (27.4%), Rt.P-com에서 10명 (17.1%), Lt.P-com 7명 (11.9%), Rt.MCA bifurcation부위에서 10명 (17.1%), Lt.MCA bifurcation부위에서 5명 (8.5%)으로 나타났다. Rupture aneurysm 평균 size는 6.71mm이었으며, rupture aneurysm의 모양은 제각각이었으나, La, Ld 분류에 포함되는 aneurysm이 대부분이었다. 결론: 두개 이상의 rupture aneurysm이 발견된 환자들 중 가장 많은 rupture가 발병된 부위는 A-com, Rt.P-com, Rt.MCA bifurcation, Lt.P-com, Lt.MCA bifurcation 순이었으며, rupture된 모양은 대부분 lobulating이거나 daughter sac을 가지고 있었음을 알 수 있었다.
Cite
Citations (0)
Objective To discuss the DSA imaging characteristic and classification of the false aneurysm and true aneurysm complex at the rupture position after intracranial aneurysmal subarachnoid hemorrhage. Methods CT scan and DSA imaging were performed in 50 patients (50 ruptured aneurysm). Results 50 ruptured aneurysm showed SAH by different amount of hemorrhage. DSA test all showed the forming of false aneurysm at the rupture position, tiny, round or near round irregular false aneurysm cavity can be found outside the true aneurysm cavity. According to the DSA imaging presentation we can divide them into three types: 11 cases were type A (near teapot), 27 cases were type B (near gourd), 12 cases were type C (near dumbbell). Conclusion The false aneurysm can form around the rupture position after intracranial rupture, the false aneurysm cavity and true aneurysm cavity together form a special aneurysm complex, it's imaging characteristic under DSA can be divided into three types.
Cite
Citations (0)
BACKGROUND: Smoking is a well-known independent risk factor for both aneurysm formation and rupture. There is mounting evidence that aneurysm morphology beyond size can have a significant role in aneurysm formation and rupture risk by its effects on aneurysmal hemodynamics. OBJECTIVE: To study the variation in aneurysm morphology between smokers and nonsmokers and delineate how changes in these factors might affect aneurysm formation and rupture. METHODS: We generated 3-dimensional models of aneurysms and their surrounding vasculature by analyzing preoperative computed tomography angiograms with Slicer software. We then examined the association between smoking status and intrinsic, transitional, and extrinsic aspects of aneurysm morphology in both univariate and multivariate statistical analyses. RESULTS: From 2005 to 2013, 199 cerebral aneurysms in never smokers and current smokers were evaluated/treated at a single institution with available computed tomography angiograms (102 in never smokers and 97 in current smokers). Multivariate analysis of current smokers vs never smokers demonstrated that aneurysms in current smokers were significantly associated with multiple aneurysms (odds ratio [OR]: 2.15, P = .03), larger daughter vessel diameters (OR: 3.13, P = .01), larger size ratio (OR: 1.78, P = .01), and location at the basilar apex (OR: 6.26, P = .02). CONCLUSION: The differences in aneurysm morphology between smoking and nonsmoking patient populations may elucidate the effects of smoking on aneurysm formation and eventual rupture. We identified several aspects of aneurysm morphology significantly associated with smoking status that may provide the morphological basis for how smoking leads to increased aneurysm rupture. ABBREVIATIONS: ACoA, anterior communicating artery PCoA, posterior communicating artery MCA, middle cerebral artery
Cite
Citations (48)
Atheroma
Cite
Citations (2)
Introduction
About 85% of the non-traumatic SAH are caused by ruptured aneurysms1. Identifying those aneurysms as the bleeding cause is essential for further therapy.Aim of study
The study evaluates the detection of cerebral aneurysm in unenhanced CT images of patients with subarachnoid hemorrhage by a relative hypodense structure in the hyperdense bleeding, the sparing aneurysm sign (SAS).Methods
Three neuroradiologic experienced radiologists rated the aneurysm location and size by applying the SAS in 50 CT-examinations of patients with aneurysmal SAH who underwent an initial CT scan followed by a DSA. The results were analyzed for correlations between aneurysm location, aneurysm size, Fisher-score and the detectability of a SAS. Further a quantitative analysis of the average HU of the aneurysm and the SAH was performed.Results
In 75% of the cases the aneurysm was identified correctly just using the SAS, influenced significant by aneurysm location (p=0.019), Fisher-Score (p=0.008) and aneurysm size (p=0.017). The highest rate of aneurysm detection was given for MCA- (90%) and BA-aneurysms (90%), followed by ACOM- (80%) and ACA-aneurysm (80%). The measured aneurysm size in the correctly identified aneurysm significantly corelates to the size measured in the DSA (p<0.001) and a cut point of 51 HU discriminates aneurysm from SAH with a specificity of 92% and a sensitivity of 86% (Youden´s index 0.78).Conclusions
The aneurysm location and size can be determined in unenhanced CT images in many cases using the new SAS (sparing aneurysm sign). Whereas quantitative measurements of HU can support the aneurysm detection.References
Connolly ES, Rabinstein AA, Carhuapoma JR, et al. Guidelines for the Management of Aneurysmal Subarachnoid Hemorrhage. Stroke. 2012;43. Do you have any conflict of interest to declare?: NoCite
Citations (1)
Angiotensin II-infused ApoE-/- mice are a popular model for aortic aneurysm and
dissection. We have recently demonstrated that the thoraco-abdominal lesions in these
mice start with a medial tear near the ostia of celiac and mesenteric arteries. Given the
location-specific nature of the disease, we hypothesized that the local mechanical
equilibrium may drive disease initiation [1]. In order to investigate this hypothesis we
subsequently developed a novel computational approach to evaluate the in-vivo strain
field in the abdominal aorta. Combining ex vivo synchrotron images with in vivo micro-
CT, we incorporated model features such as non-uniform aortic wall thickness, nonuniform
stretch field and the inclusion of small aortic side branches into our
computational models and showed how these often overlooked features impact the
location of hotspots in the computed strain field [2]. In our current work we validate
these simulations with image-guided histology in order to investigate whether regions
of high strain collocate with sites of micro-structural. N=10 ApoE-/- mice were infused
with Angiotensin-II for 3 days and subsequently underwent a contrast-enhanced micro-
CT scan prior to euthanasia. The aorta was imaged ex-vivo using high-resolution Phasecontrast
X-Ray Microscopy (PCXTM) at 6.5 um isotropic resolution. The same protocol
was followed for n=6 saline-infused controls. An in-house automated framework was
implemented to morph the non-pressurized non-stretched ex-vivo PCXTM geometry
onto the pressurized stretched in-vivo micro-CT geometry [2]. For each animal the
output was a mouse-specific structural finite element simulation. Contrast agent
infiltration in the aortic wall was used to detect the location of micro-ruptures in the
tunica media [1] and image-guided histology was performed to validate and quantify
the vascular damage. Preliminary results show good agreement between hotspots of
early vascular damage and hotspots of computed maximal strain. The highest strain
values occurred invariably in the vicinity of the celiac and mesenteric arteries and
collocated with intramural micro-ruptures and leukocyte infiltration. Moreover, the intersubject
variability of the maximal strain locations (cranial/caudal or right/left of the
ostium) corresponded qualitatively to the inter-subject variability of PCXTM-detected
contrast agent leakage. We conclude that strain concentrations near side branches may
play an important role in disease initiation and could partially explain the focal nature
of the disease.
Ex vivo
Abdominal aorta
Cite
Citations (0)
106 Background and Purpose: To determine the frequency of unruptured intracranial aneurysm enlargement using serial MR angiography, and to determine if there are factors predicting change in aneurysm size. Methods: We retrospectively reviewed MR angiography studies performed between January 1991 and December 1999. Fifty-seven patients had 62 unruptured, untreated saccular aneurysms. The ratio of females to males was 2.6: 1. An average of 3 measurements of the maximal dimension as measured on source images was defined as the aneurysm size. Both the mean and median aneurysm diameter was 5 mm (range 2–15 mm). An aneurysm was defined to have enlarged if it increased in size by more than 1 mm when the size of the aneurysm was less than 5 mm and more than 2 mm when the aneurysm was equal to or larger than 5 mm. The mean and median time between studies was 50 months and 47 months respectively, with a range of 17–90 months. Results: No aneurysm ruptured during the period of follow-up. Four (7%) of the aneurysms increased in size with the median time to aneurysm growth of 40 months (range 23–66 months). None of the aneurysms less than 9 mm diameter increased in size. Four of the 9 aneurysms (44%) 9 mm or larger increased in size. Factors which predicted aneurysm growth includes size (p = 0.002), and multiple lobes or daughter sacs (p = 0.02). Aneurysm location did not predict an increased risk of enlargement. Conclusions: Patients with medium or large size aneurysms and multiple lobes or daughter sacs may be at increased risk for aneurysm growth and should be considered for follow up imaging if left untreated.
Saccular aneurysm
Cite
Citations (0)
To evaluate the usefulness of a new computed tomographic (CT) sign of "draped aorta" in the diagnosis of a contained leak in an aortic aneurysm.CT scans were retrospectively evaluated in 10 patients in whom an unidentifiable aortic wall and posterior aspect of the aorta that followed the vertebral contour were seen. CT findings were compared with those at surgery.Seven patients had a deficient aortic wall and a contained leak. Two patients had a deficient wall and a mycotic aneurysm. One patient had a false aneurysm at the aortic graft anastomosis.On CT images, draping of the aorta if highly indicative of deficiency of the aortic wall and a contained leak.
Cite
Citations (90)
We report a case of unruptured “true posterior communicating artery” (Pcom) aneurysm associated with ruptured internal carotid-posterior communicating artery (IC-PC) aneurysm in a 72-year-old woman, treated successfully by direct surgery. Left internal carotid angiography and three-dimensional CT angiography revealed an IC-PC aneurysm 8 mm in maximum diameter protruding inferolaterally, with a small bulge on the Pcom side which was regarded as part of the IC-PC aneurysm. Intraoperative inspection revealed that the prominence initially thought to be part of the IC-PC aneurysm was a true Pcom aneurysm forming a kissing aneurysm pair with the IC-PC aneurysm. The 2 aneurysms were completely dissected and both were clipped. This is the first reported case of kissing aneurysms of the IC-PC aneurysm and true Pcom aneurysm. A true Pcom aneurysm forming kissing aneurysms with IC-PC aneurysm, as in the present case, may be difficult to diagnose preoperatively. Careful intraoperative observation and complete dissection are therefore important for a good outcome.
Posterior communicating artery
Cite
Citations (5)
Arachnodactyly
Cite
Citations (18)