A previous thoracic aortic aneurysm time course study from our laboratory determined that ascending aortic dilation was significantly increased by day 5, and reached a plateau by day 28 of angiotensin II (AngII) infusion. We also found that mice had hemorrhage localized to the ascending aortas by day 5 of AngII infusion. The purpose of these studies was to provide mechanistic insight into the development of AngII-induced ascending aortic hemorrhage. Male C57BL/6 mice fed normal diet were subcutaneously infused with either AngII (1000 ng/kg/min) or saline for 5 days. To examine cellular heterogeneity, hemorrhaged ascending aortas were collected and sectioned serially for histological staining and immunostaining. I was unable to identify an entry point for blood into the media of the aortic root and ascending aorta. However, I found incomplete intimo-medial dissection near the hemorrhaged regions that may potentially be contiguous with the blood. To investigate infiltration of immune cells during AngII infusion, immunohistochemistry of hemorrhaged ascending aortas was performed. The numbers of macrophages and neutrophils in AngII-infused aortas were increased in both medial and adventitial areas when compared with saline-infused aortas. Therefore, infiltration of immune cells at the point of dissection is associated with aortic hemorrhage during AngII infusion.

The occurrence of clinically diagnosed and/or ruptured abdominal aortic aneurysms (AAAs) in the families of 220 patients with AAAs, treated at the Surgical Clinic, University Hospital of Umeå in the northern part of Sweden during the years 1965-82, was studied. A questionnaire concerning the blood relatives was answered by 87/89 patients. 16/87 patients (18%) had blood relatives with AAAs. In 14 families one blood relative was affected, and in 2 families two blood relatives were affected. First degree relatives were affected in 9/87 cases (10%), and second degree relatives in 7/87 cases (8%). 9/468 (1.9%) of the patients' brothers and sisters but only five of all their cousins had AAAs, and 7/204 (3.4%) of the dead brothers and sisters had died of ruptured AAAs. Concerning the patients who were not included in the letter survey at least 14/133had blood relatives with AAAs. However, the great majority of these patients were dead when the study was performed and could not be asked aboutthe occurrence of AAAs in their families. The patients with AAAs had significantly higher serum concentrations of triglyceride and (YLDL + LDL)-cholesterol and a significantly lower serum concentration of HDL-cholesterol than randomly selected healthy controls of the same sex and age as the patients. We also compared the distributions of genetic markers (HLA antigens, the blood group systems ABO, Rh, MNSs, P, Kell, Lewis and Duffy and the serum protein group systems haptoglobin, transferrin, group-specific component, complement C3, properdin factor and alpha-1-antitrypsin) in patients with AAAs with the distributions in controls and in some cases with the expected distributions according to the Hardy-Weinberg law. A significantly decreased frequency of Rh-negative individuals, and significantly increased frequencies of Kell-positi ve individuals, of MN heterozygotes and of heterozygotes concerning haptoglobin type was found. Furthermore, the aneurysm walls of patients with and without AAAs in the family were compared concerning the morphology, but no differences were found. We also studied the occurrence of collagen types I and III in the aneurysm walls, and the occurrence of vimentin and desmin in the smooth muscle cells of the aneurysm walls, but all these components were present in the aneurysm walls of both the patients with and those without AAAs in the family. To summarize the results, there seems to be an increased frequency of AAAs, and especially of ruptured AAAs, among the brothers and sisters of patients with AAAs. Elevated serum concentrations of triglyceride and (VLDL + LDL)- cholesterol and a lowered serum concentration of HDL-cholesterol seems to be common in patients with AAAs. There seems to be a hereditary predisposition to the development of AAAs, because we found associations with four different genetic markers (Rh, MN, Kell, haptoglobin group). However, there is probably no specific "familial" type of AAAs, because we found no differences between the patients with and those without AAAs in the family.Key words: / <p>S. 1-42: sammanfattning, s. 43-103: 5 uppsatser</p> / digitalisering@umu

Thesis (Ph. D.)--University of Houston, 2005. / Includes bibliographical references (leaves 100-110). Also available online (PDF file) by a subscription to the set or by purchasing the individual file.

Thesis (Ph. D.)--University of Houston, 2005. / Includes bibliographical references (leaves 100-110).

abstract: Current treatment methods for cerebral aneurysms are providing life-saving measures for patients suffering from these blood vessel wall protrusions; however, the drawbacks present unfortunate circumstances in the invasive procedure or with efficient occlusion of the aneurysms. With the advancement of medical devices, liquid-to-solid gelling materials that could be delivered endovascularly have gained interest. The development of these systems stems from the need to circumvent surgical methods and the requirement for improved occlusion of aneurysms to prevent recanalization and potential complications. The work presented herein reports on a liquid-to-solid gelling material, which undergoes gelation via dual mechanisms. Using a temperature-responsive polymer, poly(N-isopropylacrylamide) (poly(NIPAAm), the gelling system can transition from a solution at low temperatures to a gel at body temperature (physical gelation). Additionally, by conjugating reactive functional groups onto the polymers, covalent cross-links can be formed via chemical reaction between the two moieties (chemical gelation). The advantage of this gelling system comprises of its water-based properties as well as the ability of the physical and chemical gelation to occur within physiological conditions. By developing the polymer gelling system in a ground-up approach via synthesis, its added benefit is the capability of modifying the properties of the system as needed for particular applications, in this case for embolization of cerebral aneurysms. The studies provided in this doctoral work highlight the synthesis, characterization and testing of these polymer gelling systems for occlusion of aneurysms. Conducted experiments include thermal, mechanical, structural and chemical characterization, as well as analysis of swelling, degradation, kinetics, cytotoxicity, in vitro glass models and in vivo swine study. Data on thermoresponsive poly(NIPAAm) indicated that the phase transition it undertakes comes as a result of the polymer chains associating as temperature is increased. Poly(NIPAAm) was functionalized with thiols and vinyls to provide for added chemical cross-linking. By combining both modes of gelation, physical and chemical, a gel with reduced creep flow and increased strength was developed. Being waterborne, the gels demonstrated excellent biocompatibility and were easily delivered via catheters and injected within aneurysms, without undergoing degradation. The dual gelling polymer systems demonstrated potential in use as embolic agents for cerebral aneurysm embolization. / Dissertation/Thesis / Ph.D. Bioengineering 2012

Les anévrysmes de l'aorte ascendante sont un problème de santé publique qui peut menacer le pronostic vital par le risque de rupture ou de dissection. Actuellement, le seul critère permettant de décider d'une intervention est le diamètre maximal de l'anévrysme mesuré par le scanner. La recherche biomécanique a pour objectif de caractériser les propriétés élastiques de l'aorte et de proposer une approche patient-spécifique de l'évaluation du risque de complication. Le but de cette thèse était double. Dans une première partie, il était de déterminer les propriétés à rupture d'anévrysmes de l'aorte ascendante fraîchement excisés à partir d'un banc d'essai de tests en gonflement mis au point dans notre laboratoire. Les résultats ont permis de déterminer un index de risque de rupture basé sur l'extensibilité de l'aorte. Dans une deuxième partie, nous avons identifié les propriétés mécaniques des anévrysmes aortiques à l'aide d'un scanner dynamique préopératoire. Cette identification reposait sur la minimisation simultanée de deux fonctions coût, qui définissaient la différence entre les prédictions d"un modèle numérique et les mesures par le scanner du volume de l'anévrysme au milieu du cycle cardiaque et à la systole. Les résultats étaient corrélés à ceux des tests mécaniques en gonflement, montrant une application prometteuse du scanner dynamique pour l'identification du patient-scpécifique des propriétés mécaniques de l'aorte. Ce travail ouvre un peu plus la voie vers une évaluation patient-spécifique du risque de complication d'un anévrysme de l'aorte ascendante et vers une sélection plus affinée des patients pour la chirurgie. / Aneurysms of the ascending aorta are a life-threatening desease by the risk of rupture or dissection. Currently, the only criterion for deciding an intervention is the maximum diameter of the aneurysm mesured from CT-scan. Biomechanical research aims to characterize the elastic properties of the aorta and to provide a patient-specific approach too assessing the risk of complications. The aim of this thesiswas twofold. In the first part, it was tocharacterize the rupture properties of freshly excised acsending aortic tissue from an inflation bench-test developed in our laboratory. The results were derived to determine a rupture risk index based on the extensibility of the aorta. In the second part, we identified the mechanical properties of aortic aneurysms using preoperative dynamic CT-scan. This identification was based on the simultaneous minimization of two cost functions, which defined the difference between the predictionsof a numerical model and the volumes of the aneurysms measured from the CT-scan in the middle of the cardiac cycle and the sytole. The results were correlated with those of the inflation tests, showing promising application of the dynamic scan for the patient-specific identification of the mechanical properties of the aorta. This work opens a little more the way for the patient-specific assessment of the risk of complications of an aneurysm of the ascending aorta and for a more refined selection of patients for surgery.

Introdução: O acesso pterional é uma das craniotomias mais utilizadas. Entretanto, apresenta algumas desvantagens, como a dissecação ampla do músculo temporal, que pode causar atrofia e deformidade do contorno facial. A craniotomia minipterional descrita em 2007 propiciou exposição anatômica semelhante a da craniotomia pterional clássica. Objetivos: Comparar os resultados clínicos, funcionais e estéticos dos dois acessos cirúrgicos destinados ao tratamento de aneurismas da circulação anterior. Métodos: Cinquenta e oito doentes, com aneurismas rotos (40) e não rotos (18) foram admitidos no estudo. No grupo A, 28 indivíduos foram submetidos à craniotomia minipterional. No grupo B, 30 doentes foram operados com a craniotomia pterional clássica. Doentes com hematomas intracranianos, aneurismas do segmento oftálmico e aneurismas gigantes foram excluídos. Os resultados estéticos foram analisados por meio de dois métodos. No primeiro, uma autoavaliação utilizava uma régua escalonada de 0 a 100, na qual o zero representou o melhor resultado e 100 o pior resultado na percepção do próprio doente. Fotografias dos doentes foram mostradas a dois observadores independentes. Os resultados foram classificados como ótimo, bom, regular e mau (de acordo com uma escala pré-determinada). A gradação da atrofia foi mensurada por meio de três métodos, utilizando a tomografia computadorizada de crânio. No primeiro, observou-se a percentagem de redução do complexo músculo temporal, tecido subcutâneo e pele. No segundo método, a percentagem de redução da espessura do músculo temporal foi analisada isoladamente. O terceiro método foi a mensuração da volumetria do músculo temporal, tecido subcutâneo e pele calculados a partir da margem superior do arco zigomático até a linha temporal superior utilizando-se o software OsiriX (Pixmeo Sarl Geneva/ Suíça OsiriX). Para os resultados clínicos e funcionais, foi utilizada a Escala de Rankin modificada. Outras variáveis, como paralisia do ramo frontal do nervo facial, hemorragia pós-operatória, fistula liquórica, hidrocefalia e mortalidade, também foram analisadas. Resultados: Em ambos os grupos, os dados demográficos e as características pré-operatórias foram similares. A satisfação com o resultado estético foi observada em 79% (19) no grupo A e 52% (13) no grupo B (p=0,07). O valor médio da régua foi 27 no grupo A e 45,8 no grupo B (p=0,03). Quando somente doentes classificados como Rankin modificado 0 ou 1 foram analisados, o valor médio da régua foi de 25,2 no grupo A e 39,4 no grupo B (p=0,11). Dois avaliadores independentes analisaram as fotografias dos doentes e o coeficiente de correlação kappa para os resultados estéticos foi de 0,73. De acordo com os mesmos ótimo e bom, foram observados em 87% (21) no grupo minipterional e 48% (12) no grupo pterional. A percentagem de redução do músculo temporal, subcutâneo e pele (método 1) foi de 14,9% no grupo A e 24,3% no grupo B (p=0,01). Quando somente o músculo temporal foi analisado (método 2), a percentagem de redução foi de 12,7% no grupo A e 22% no grupo B (p=0,005). A redução volumétrica das estruturas (método 3) foi de 14,8% no grupo A e 24,5% no grupo B (p=0,012). Na avaliação clínica no 6? mês, os valores da Escala de Rankin modificada foram similares (p=0,99). O óbito ocorreu em 4 doentes no grupo A e 5 doentes no grupo B (p=1,0). Conclusão: Os resultados clínicos demonstraram que a craniotomia minipterional é um procedimento seguro, com prognóstico similar ao da técnica convencional. Os resultados cosméticos foram melhores com menor deformidade no contorno facial, uma vez que a percentagem de redução da espessura, do volume do músculo temporal, do tecido subcutâneo e da pele foi menor com a técnica proposta. A craniotomia minipterional foi a melhor alternativa em relação à craniotomia pterional clássica para tratar aneurismas rotos e não rotos da circulação anterior / Introduction: The pterional approach is one of the most commonly used craniotomy. However it has disadvantages, such as complete dissection of the temporalis muscle. This may lead to muscular atrophy and facial deformity. The minipterional craniotomy was described in 2007 and the anatomic exposure provided by the pterional and minipterional approaches were similar in the total area of exposure and angular view. Objectives: This prospective randomized study was designed to compare the clinical, functional and aesthetic results of two surgical techniques for microsurgical clipping of anterior circulation aneurysms. Methods: Overall, 58 eligible patients admitted with ruptured and unruptured anterior circulation aneurysms were enrolled in the study. In group A, 28 patients were operated with the minipterional technique. In Group B 30 patients were operated according to the classical pterional craniotomy. Patients with intracranial haematomas, ophthalmic aneurysms and giant aneurysms were excluded. The aesthetic results were analyzed with 2 methods. In the first, the patients were showed to a rule, with a scale from 0 to 100, in which 0 mean the best result and 100 the worst result. Photos were taken and showed to two independent observers, the results were classified as excellent, good, regular or poor, according to a pre-determined scale. The degree of atrophy was measured with three methods. In the first one, the authors observed the percentage of thick reduction in the temporal muscle, subcutaneous tissue and skin. In the second method the percentage of thick reduction of the isolated temporal muscle was observed and the third the volumetric analysis of the temporal muscle, subcutaneous tissue and skin was calculated from the superior edge of zygomatic arch to superior temporal line using the OsiriX software (OsiriX - Pixmeo Sarl Geneva/Suíça). The functional results were compared using the Modified Rankin Score. Others variables such frontal facial palsy, post-operative hemorrhage, cerebrospinal fistulas, hydrocephalus and mortality were also analyzed. Results: In both groups the demographic and pre-operative characteristics were similar. The satisfaction with aesthetic results were observed in 79% (19) in group A and 52% (13) in group B (p=0,07). The mean value observed in the rule was 27 in group A and 45,8 in group B (p=0,03). When patients classified as Rankin Modified Score of 0 or 1 only were included the mean value observed in the rule was 25,2 in group A and 39,4 in group B (p=0,11). Two independent observers analyzed the patients photos and the kappa coefficient correlation for the aesthetic results was 0,73. According to them excellent and good results were observed in 87% (21) in minipterional group and 48% (12) in the pterional group. The degree of atrophy of temporal muscle, subcutaneous tissue and skin (method 1) was14,9% in group A and 24,3% in group B (p=0,01). The measurement of temporal muscle (method 2) revealed that the degree of atrophy was 12,7% in group A and 22% in group B (p=0,005). The volumetric reduction of the structures (method 3) was 14,8% in group A and 24,5% in group B (p=0,012). Rankin Modified Score was similar in both groups in the 6-month evaluation (p=0,99). Mortality occurred in 4 patients in group A and 5 patients in group B (p=1,0). Conclusion: These clinical results indicate that the minipterional is a safe procedure. We can estimate the better cosmetic results with less facial contour deformity since the percentage of thick and volumetric reduction in temporal muscle, subcutaneous tissue and skin were demonstrated. It can be an excellent and better alternative to the classical pterional approach

No description available.

BACKGROUND: Sirtuin-1 (SirT1) is a NAD+-dependent deacetylase essential for maintaining the structure and function of the vasculature. Reduced SirT1 expression and activity has been correlated with the development of vascular diseases, mainly attributed to loss of SirT1’s anti-oxidant and anti-inflammatory beneficial effects. We previously found that deletion of vascular smooth muscle (VSM) SirT1 in mice is associated with increased matrix metalloproteinases (MMPs) and the subsequent development of aortic dissections or ruptures in response to the hypertensive peptide angiotensin II. Based on these previous findings, we hypothesize that loss of SirT1 activity is involved in the pathogenesis of AA. SirT1 is a stress response gene, its deacetylase activity can be impaired by excessive oxidative stress. We postulate that mutating three cysteine residues in SirT1’s catalytic domain can prevent its inactivation by oxidative insults and protect against AA and other vascular diseases. OBJECTIVES: assess the role of SirT1 in a genetic mouse model of Marfan Syndrome that develops AA; (2) Determine design and optimize an enzyme-based colorimetric ELISA to determine SirT1 activity in mouse VSM cells and aortas; (3) Produce an adeno-associated virus (AAV) expressing an oxidant-resistant triple mutant SirT1 in VSM cells that has the potential to mitigate the downstream outcomes derived from alterations in SirT1 activity, such as MMPs activation and development of AA in mgR-/- mice. METHODS: mgR-/- and littermate mgR+/+ (WT) mice aortas and VSM cells were cultured in conditioned medium and the activity of released MMPs was determined by in-gel zymography. For the development of the SirT1 activity assay, we designed a multi-step sandwich ELISA that captures a biotin- and FLAG-tagged acetylated p53 peptide, used as SirT1 deacetylase substrate. Amounts of acetylated and total p53 peptide were sequentially detected with antibodies and colorimetric substrates as index of SirT1 deacetylase activity. AAVs expressing a control or triple mutant SirT1 (3M) were produced in HEK293T cells; VSM cells were then infected with control or 3M AAV and SirT1 protein expression levels were measured by Western Blot. RESULTS: MMPs activity is increased in aortas and VSMC of mgR-/- mice; the first stage of optimization of the SirT1 activity assay successfully defined the assay conditions and experimental design, and it is ready to be optimized with mgR-/- cell and tissue samples; our novel control and SirT1 triple mutant AAVs were produced and successfully overexpressed in VSM cells. / 2024-03-14T00:00:00Z

Intracranial Aneurysms are a prevalent vascular pathology present in 3-4% of the population with an inherent risk of rupture. The growing accessibility of angiography has led to a rising incidence of detected aneurysms. An accurate assessment of the rupture risk is of utmost importance for the very high disability and mortality rates in case of rupture and the non-negligible risk inherent to surgical treatment. However, human evaluation is rather subjective, and current treatment guidelines, such as the PHASES score, remain inefficient. Therefore we aimed to develop an automatic machine learning-based rupture prediction model. Our study utilized 686 CTA scans, comprising 844 intracranial aneurysms. Among these aneurysms, 579 were classified as ruptured, while 265 were categorized as non-ruptured. Notably, the CTAs of ruptured aneurysms were obtained within a week after rupture, during which negligible morphological changes were observed compared to the aneurysm’s pre-rupture shape, as established by previous research. Based on this observation, our rupture risk assessment focused on the models’ ability to classify between ruptured and unruptured IAs. In our investigation, we implemented an automated vessel and aneurysm segmentation, vessel labeling, and feature extraction framework. The rupture risk prediction involved the use of deep learning-based vessel and aneurysm shape features, along with a combination of demographic features (patient sex and age) and morphological features (aneurysm location, size, surface area, volume, sphericity, etc.). An ablation-type study was conducted to evaluate these features. Eight different machine learning models were trained with the objective of identifying ruptured aneurysms. The best performing model achieved an area under the receiver operating characteristic curve (AUC) of 0.833, utilizing a random forest algorithm with feature selection based on Spearman’s rank correlation thresholding, which effectively eliminated highly correlated and anti-correlated features...:1 Introduction 1.1 Intracranial aneurysms 1.1.1 Treatment strategy 1.1.2 Rupture risk assesment 1.2 Artificial Intelligence 1.3 Thesis structure 1.4 Contribution of the author 2 Theory 2.1 Rupture risk assessment guidelines 2.1.1 PHASES score 2.1.2 ELAPSS score 2.2 Literature review: Aneurysm rupture prediction 2.3 Machine learning classifiers 2.3.1 Decision Tree 2.3.2 Random Forests 2.3.3 XGBoost 2.3.4 K-Nearest-Neighbor 2.3.5 Multilayer Perceptron 2.3.6 Logistic Regression 2.3.7 Support Vector Machine 2.3.8 Naive Bayes 2.4 Latent feature vectors in deep learning 2.5 PointNet++ 3 Methodology 3.1 Data 3.2 Vessel segmentation 3.3 Feature extraction 3.3.1 Deep vessel features 3.3.2 Deep aneurysm features 3.3.3 Conventional features 3.4 Rupture classification 3.4.1 Univariate approach 3.4.2 Multivariate approach 3.4.3 Deep learning approach 3.4.4 Deep learning amplified multivariate approach 3.5 Feature selection 3.5.1 Correlation-based feature selection 3.5.2 Permutation feature importance 3.6 Implementation 3.7 Evaluation 4 Results 4.1 Univariate approach 4.2 Multivariate approach 4.3 Deep learning approach 4.3.1 Deep vessel features 4.3.2 Deep aneurysm features 4.3.3 Deep vessel and deep aneurysm features 4.4 Deep learning amplified multivariate approach 4.4.1 Conventional and deep vessel features 4.4.2 Conventional and deep aneurysm features 4.4.3 Conventional, deep vessel, and deep aneurysm features 5 Discussion and Conclusions 5.1 Overview of results 5.2 Feature selection 5.3 Feature analysis 5.3.1 Deep vessel features 5.3.2 Deep aneurysm features 5.3.3 Conventional features 5.3.4 Summary 5.4 Comparison to other methods 5.5 Outlook Bibliography / Intrakranielle Aneurysmen sind eine weit verbreitete vaskuläre Pathologie, die bei 3 bis 4% der Bevölkerung auftritt und ein inhärentes Rupturrisiko birgt. Mit der zunehmenden Verfügbarkeit von Angiographie wird eine steigende Anzahl von Aneurysmen entdeckt. Angesichts der sehr hohen permanenten Beeinträchtigungs- und Sterblichkeitsraten im Falle einer Ruptur und des nicht zu vernachlässigenden Risikos einer chirurgischen Behandlung ist eine genaue Bewertung des Rupturrisikos von größter Bedeutung. Die Beurteilung durch den Menschen ist jedoch sehr subjektiv, und die derzeitigen Behandlungsrichtlinien, wie der PHASES-Score, sind nach wie vor ineffizient. Daher wollten wir ein automatisches, auf maschinellem Lernen basierendes Modell zur Rupturvorhersage entwickeln. Für unsere Studie wurden 686 CTA-Scans von 844 intrakraniellen Aneurysmen verwendet, von denen 579 rupturiert waren und 265 nicht rupturiert waren. Dabei ist zu beachten, dass die CTAs der rupturierten Aneurysmen innerhalb einer Woche nach der Ruptur gewonnen wurden, in der im Vergleich zur Form des Aneurysmas vor der Ruptur nur geringfügige morphologische Veränderungen zu beobachten waren, wie in vorhergegangenen Studient festgestellt wurde. Im Rahmen unserer Untersuchung haben wir eine automatische Segmentierung von Adern und Aneurysmen, ein Aderlabeling und eine Merkmalsextraktion implementiert. Für die Vorhersage des Rupturrisikos wurden auf Deep Learning basierende Ader- und Aneurysmaformmerkmale zusammen mit einer Kombination aus demografischen Merkmalen (Geschlecht und Alter des Patienten) und morphologischen Merkmalen (u. A. Lage, Größe, Oberfläche, Volumen, Sphärizität des Aneurysmas) verwendet. Zur Bewertung dieser Merkmale wurde eine Ablationsstudie durchgeführt. Acht verschiedene maschinelle Lernmodelle wurden mit dem Ziel trainiert, rupturierte Aneurysmen zu erkennen...:1 Introduction 1.1 Intracranial aneurysms 1.1.1 Treatment strategy 1.1.2 Rupture risk assesment 1.2 Artificial Intelligence 1.3 Thesis structure 1.4 Contribution of the author 2 Theory 2.1 Rupture risk assessment guidelines 2.1.1 PHASES score 2.1.2 ELAPSS score 2.2 Literature review: Aneurysm rupture prediction 2.3 Machine learning classifiers 2.3.1 Decision Tree 2.3.2 Random Forests 2.3.3 XGBoost 2.3.4 K-Nearest-Neighbor 2.3.5 Multilayer Perceptron 2.3.6 Logistic Regression 2.3.7 Support Vector Machine 2.3.8 Naive Bayes 2.4 Latent feature vectors in deep learning 2.5 PointNet++ 3 Methodology 3.1 Data 3.2 Vessel segmentation 3.3 Feature extraction 3.3.1 Deep vessel features 3.3.2 Deep aneurysm features 3.3.3 Conventional features 3.4 Rupture classification 3.4.1 Univariate approach 3.4.2 Multivariate approach 3.4.3 Deep learning approach 3.4.4 Deep learning amplified multivariate approach 3.5 Feature selection 3.5.1 Correlation-based feature selection 3.5.2 Permutation feature importance 3.6 Implementation 3.7 Evaluation 4 Results 4.1 Univariate approach 4.2 Multivariate approach 4.3 Deep learning approach 4.3.1 Deep vessel features 4.3.2 Deep aneurysm features 4.3.3 Deep vessel and deep aneurysm features 4.4 Deep learning amplified multivariate approach 4.4.1 Conventional and deep vessel features 4.4.2 Conventional and deep aneurysm features 4.4.3 Conventional, deep vessel, and deep aneurysm features 5 Discussion and Conclusions 5.1 Overview of results 5.2 Feature selection 5.3 Feature analysis 5.3.1 Deep vessel features 5.3.2 Deep aneurysm features 5.3.3 Conventional features 5.3.4 Summary 5.4 Comparison to other methods 5.5 Outlook Bibliography