Development of an intelligent system for the determination of rupture-related characteristics in intracranial aneurysms detected by Computed Tomography Angiography

Petros Zampakis, Nontas Ntzanis, Vasilios Panagiotopoulos, Fotis Anagnostopoulos, Gerasimos A.T Messaris, Christina Kalogeropoulou, Constantinos Koutsojannis


Purpose: Aim of this study was the development of an intelligent system (IS) that can determine the rupture-related characteristics in intracranial aneurysms detected by computed tomography angiography.

Material and Methods: 100 intracranial aneurysms in 100 patients (74% ruptured) were analysed. An IS was developed based on machine learning (ML) algorithm (WEKA J48 software). The IS used measurements, morphological characteristics and location of the aneurysms, as well as patients’ age. 70 aneurysms were used as the training set, while 30 aneurysms were used as the test set.

Results: Using training set, our model along with Neuroradiologist interaction indicated the following: The two most important rupture-related aneurysmal characteristics were dome/neck ratio ≥1.96 and irregular shape (regardless of location). Other rupture-related characteristics included anterior circulation aneurysms that were irregular in shape (regardless of dimension) and posterior circulation aneurysms with maximum dimension ≤6.7 mm (regardless of shape). A negative-related characteristic for rupture included posterior circulation aneurysms with wide neck and maximum dimension >6.7 mm. The accuracy of the IS in our test set was 80%. Age did not influence aneurysmal risk status.

Conclusions: In the present study we developed an IS which, based on certain aneurysmal parameters, can accurately identify rupture-related characteristics. As a result of the interaction between ML algorithms and clinical expert, a number of rules were created that can be further evaluated in larger studies.


Intracranial aneurysm/risk factors; Rupture; CT angiography; Intracranial aneurysm; Rupture; Machine learning

Full Text:



Steiner T, Juvela S, Unterberg A, et al. European Stroke Organization. European Stroke Organization guidelines for the management of intracranial aneurysms and subarachnoid haemorrhage. Cerebrovasc Dis 2013; 5(2): 93-112.

Hackenberg KAM, Hänggi D, Etminan N. Unruptured intracranial aneurysms. Stroke 2018; 49(9): 2268-2275.

Thompson BG, Brown RD Jr, Amin-Hanjani S, et al. American Heart Association Stroke Council, Council on Cardiovascular and Stroke Nursing, and Council on Epidemiology and Prevention; American Heart Association; American Stroke Association. Guidelines for the management of patients with unruptured intracranial aneurysms: a guideline for healthcare professionals from the American Heart Association/American Stroke Association. Stroke 2015; 46(8): 2368-2400.

International Study of Unruptured Intracranial Aneurysms Investigators. Unruptured intracranial aneurysms-risk of rupture and risks of surgical intervention. N Engl J Med 1998; (339): 1725-1733.

Wiebers DO, Whisnant JP, Huston J 3rd, et al. International Study of Unruptured Intracranial Aneurysms Investigators. Unruptured intracranial aneurysms: natural history, clinical outcome, and risks of surgical and endovascular treatment. Lancet 2003; 362 (9378): 103-110.

UCAS Japan Investigators. Morita A, Kirino T, Hashi K, et al. The natural course of unruptured cerebral aneurysms in a Japanese cohort. N Engl J Med 2012; 366(26): 2474-2482.

Takao H, Murayama Y, Otsuka S, et al. Hemodynamic differences between unruptured and ruptured intracranial aneurysms during observation. Stroke 2012; 43(5): 1436-1439.

Xiang J, Natarajan SK, Tremmel M, et al. Hemodynamic−morphologic discriminants for intracranial aneurysm rupture. Stroke 2011; 42(1): 144-152.

Ren Y, Chen GZ, Liu Z, et al. Reproducibility of image-based computational models of intracranial aneurysm: a comparison between 3D rotational angiography, CT angiography and MR angiography. Biomed Eng Online 2016; 15(1): 50.

Riccardello GJ Jr, Shastri DN, Changa AR, et al. Influence of relative residence time on side-wall aneurysm inception. Neurosurgery 2018; 83(3): 574-581.

Greving JP, Wermer MJ, Brown RD Jr, et al. Development of the PHASES score for prediction of risk of rupture of intracranial aneurysms: a pooled analysis of six prospective cohort studies. Lancet Neurol 2014; 13(1): 59-66.

Etminan N, Brown RD Jr, Beseoglu K, et al. The unruptured intracranial aneurysm treatment score: a multidisciplinary consensus. Neurology 2015; 85(10): 881-889.

Juvela S. Treatment Scoring of Unruptured Intracranial Aneurysms. Stroke 2019; 50(9): 2344-2350.

Abu-Nasser SB. Medical Expert Systems Survey. International Journal of Engineering and Information Systems. 2017, 1 (7), pp.218-224.

Shortliffe EH. Medical expert systems--knowledge tools for physicians. West J Med 1986; 145(6): 830-839.

Kalogeropoulou C, Zampakis P, Tsimara M, et al. Intelligent System for preoperative evaluation of parathyroid gland for surgical intervention prediction. J Clin Exp Radiol 2019; 2(1).

Liu J, Chen Y, Lan L, et al. Prediction of rupture risk in anterior communicating artery aneurysms with a feed-forward artificial neural network. Eur Radiol 2018; 28(8): 3268-3275.

Kim HC, Rhim JK, Ahn JH, et al. Machine learning application for rupture risk assessment in small-sized intracranial aneurysm. J Clin Med 2019; 8(5): 683.

Liu Q, Jiang P, Jiang Y, et al. Prediction of aneurysm stability using a machine learning model based on PyRadiomics-derived morphological features. Stroke 2019; 50(9): 2314-2321.

Tanioka S, Ishida F, Yamamoto A, et al. Machine learning classification of cerebral aneurysm rupture status with morphologic variables and hemodynamic parameters. Radiology 2020: Artificial Intelligence. Published Online: Jan 15 2020.

Silva MA, Patel J, Kavouridis V, et al. Machine learning models can detect aneurysm rupture and identify clinical features associated with rupture. World Neurosurg 2019; 131: e46-e51.

Bisbal J, Engelbrecht G, Villa-Uriol MC, et al. Prediction of cerebral aneurysm rupture using hemodynamic, morphologic and clinical features: A data mining approach. Database and Expert Systems Applications: 22nd International Conference, DEXA 2011, Toulouse, France, August 29 - September 2, 2011, Proceedings, Part II (pp.59-73) DOI: 10.1007/978-3-642-23091-2_6.

Karabadji NE, Seridi-Bouchelaghem H, Khelf I, et al. Improved decision tree construction based on attribute selection and data sampling for fault diagnosis in rotating machines. Eng Appl Artif Intell 2014; 35: 71-83.

Lima C, de Assis F, Souza C. An empirical investigation of attribute selection techniques based on Shannon, Rényi and Tsallis entropies for network intrusion detection. Am J Intell Syst 2012; (2): 111-117.

Dietterich TG. Overfitting and undercomputing in machine learning. ACM Comput Surv 1995; 27: 326-327.

Hawkins DM. The problem of overfitting. J Chem Inf Comput Sci 2004; 44(1): 1-12.

Stehman S. Selecting and interpreting measures of thematic classification accuracy. Remote Sens Environ 1997; (62): 77-89.

Tharwat A. Classification assessment methods. Appl Comput Inform 2018;

Cunningham SJ. Machine Learning and Statistics: A Matter of Perspective. New Zealand J Computing. 1995, 6 (1a), pp. 69–73.

Nader-Sepahi A, Casimiro M, Sen J, et al. Is aspect ratio a reliable predictor of intracranial aneurysm rupture? Neurosurgery 2004; 54: 1343-1348.

Tateshima S, Chien A, Sayre J, et al. The effect of aneurysm geometry on the intra-aneurysmal flow condition. Neuroradiology 2010; 52: 1135-1141.

Feigin VL, Anderson CS, Rodgers A, et al. Subarachnoid haemorrhage occurrence exhibits a temporal pattern—evidence from meta-analysis. Eur J Neurol 2002; 9: 511-516.

Bhogal P, AlMatter M, Hellstern V, et al. Difference in aneurysm characteristics between ruptured and unruptured aneurysms in patients with multiple intracranial aneurysms. Surg Neurol Int 2018; 9: 1.

Kleinloog R, de Mul N, Verweij BH, et al. Risk factors for intracranial aneurysm rupture: A systematic review. Neurosurgery 2018; 82(4): 431-440.

Liu Q, Jiang P, Wu J, et al. Intracranial aneurysm rupture score may correlate to the risk of rebleeding before treatment of ruptured intracranial aneurysms. Neurol Sci 2019; 40(8): 1683-1693.

Ujiie H, Tamano Y, Sasaki K, et al. Is the aspect ratio a reliable index for predicting the rupture of a saccular aneurysm? Neurosurgery 2001; 48: 495-503.

Dhar S, Tremmel M, Mocco J, et al. Morphology parameters for intracranial aneurysm rupture risk assessment. Neurosurgery 2008; 63: 185-196, discussion: 196-187.

Ghosh S, Dey S, Tjoumakaris S, et al. Association of morphologic and demographic features of intracranial aneurysms with their rupture: a retrospective analysis. Acta Neurochir 2013; Suppl 115: 275-278.

Li M, Hu S, Yu N, et al. Association between meteorological factors and the rupture of intracranial aneurysms. J Am Heart Assoc 2019; 8(17): e012205.

Lindgren AE, Koivisto T, Björkman J, et al. Irregular shape of intracranial aneurysm indicates rupture risk irrespective of size in a population-based cohort. Stroke 2016; 47(5): 1219-1226.

Björkman J, Frösen J, Tähtinen O, et al. Irregular shape identifies ruptured intracranial aneurysm in subarachnoid hemorrhage patients with multiple aneurysms. Stroke 2017; 48(7): 1986-1989.

Abboud T, Rustom J, Bester M, et al. Morphology of ruptured and unruptured intracranial aneurysms. World Neurosurg 2017; 99: 610-617.

Brinjikji W, Zhu YQ, Lanzino G, et al. Risk factors for growth of intracranial aneurysms: A systematic review and meta-analysis. AJNR Am J Neuroradiol 2016; 37: 615-620.

Skodvin TØ, Johnsen LH, Gjertsen Ø, et al. Cerebral aneurysm morphology before and after rupture: Nationwide case series of 29 aneurysms. Stroke 2017; 48: 880-886.

Huhtakangas J, Lehecka M, Lehto H, et al. CTA analysis and assessment of morphological factors related to rupture in 413 posterior communicating artery aneurysms. Acta Neurochir (Wien) 2017; 159(9): 1643-1652.

Hostettler IC, Alg VS, Shahi N, et al. Genetics and Observational Subarachnoid Haemorrhage (GOSH) study investigators. Characteristics of unruptured compared to ruptured intracranial aneurysms: A multicenter case-control study. Neurosurgery 2018; 83(1): 43-52.

Waqas M, Rajabzadeh-Oghaz H, Tutino VM, et al. Morphologic parameters and location associated with rupture status of intracranial aneurysms in elderly patients. World Neurosurg 2019; 129: e831-e837.

de Jong GA, Aquarius R. Use of artificial neural networks to predict anterior communicating artery aneurysm rupture: possible methodological considerations. Eur Radiol 2019; 29(5): 2724-2726.

Truică CO, Leordeanu C. Classication of an imbalanced data set using decision tree algorithms. UPB Sci Bull Ser C 2017; 79: 69-84.

Ramyachitra D, Manikandan P. Imbalanced dataset classification and solutions: A review. Int J Bus Res 2014; 5: 4.



  • There are currently no refbacks.