European Radiology

, Volume 28, Issue 8, pp 3268–3275 | Cite as

Prediction of rupture risk in anterior communicating artery aneurysms with a feed-forward artificial neural network

  • Jinjin Liu
  • Yongchun Chen
  • Li Lan
  • Boli Lin
  • Weijian Chen
  • Meihao Wang
  • Rui Li
  • Yunjun YangEmail author
  • Bing ZhaoEmail author
  • Zilong Hu
  • Yuxia Duan
Head and Neck



Anterior communicating artery (ACOM) aneurysms are the most common intracranial aneurysms, and predicting their rupture risk is challenging. We aimed to predict this risk using a two-layer feed-forward artificial neural network (ANN).

Materials and method

594 ACOM aneurysms, 54 unruptured and 540 ruptured, were reviewed. A two-layer feed-forward ANN was designed for ACOM aneurysm rupture-risk analysis. To improve ANN efficiency, an adaptive synthetic (ADASYN) sampling approach was applied to generate more synthetic data for unruptured aneurysms. Seventeen parameters (13 morphological parameters of ACOM aneurysm measured from these patients' CT angiography (CTA) images, two demographic factors, and hypertension and smoking histories) were adopted as ANN input.


Age, vessel size, aneurysm height, perpendicular height, aneurysm neck size, aspect ratio, size ratio, aneurysm angle, vessel angle, aneurysm projection, A1 segment configuration, aneurysm lobulations and hypertension were significantly different between the ruptured and unruptured groups. Areas under the ROC curve for training, validating, testing and overall data sets were 0.953, 0.937, 0.928 and 0.950, respectively. Overall prediction accuracy for raw 594 samples was 94.8 %.


This ANN presents good performance and offers a valuable tool for prediction of rupture risk in ACOM aneurysms, which may facilitate management of unruptured ACOM aneurysms.

Key Points

• A feed-forward ANN was designed for the prediction of rupture risk in ACOM aneurysms.

• Two demographic parameters, 13 morphological aneurysm parameters, and hypertension/smoking history were acquired.

• An ADASYN sampling approach was used to improve ANN quality.

• Overall prediction accuracy of 94.8 % for the raw samples was achieved.


Aneurysm Angiography Machine learning Risk Rupture 



Anterior communicating artery


Adaptive synthetic


Artificial neural network


Computational fluid dynamics


Computed tomography angiography


Digital subtraction angiography


Receiver operating characteristic curve


Subarachnoid haemorrhage



This study received funding by Science and Technology Planning Project in Medicine and Health of Zhejiang Province, China (Grant No. 2015KYB247), Natural Science Foundation of Zhejiang Province, China (Grant No. LQ15H180002), Scientific Research Staring Foundation for the Returned Overseas Chinese Scholars of Ministry of Education of China, Science and Technology Planning Projects of Wenzhou, China (Grant No. Y20150289, Y20170210 and Y20140733), Shanghai Municipal Education Commision - Gaofeng Clinical Medicine Grant Support (20171914) Shanghai municipal commission of health and family planning grant (201740080), and Project for Creative Talents of Zhejiang Province.

Compliance with ethical standards


The scientific guarantor of this publication is Yunjun Yang.

Conflict of interest

The authors of this manuscript declare no relationships with any companies whose products or services may be related to the subject matter of the article.

Statistics and biometry

No complex statistical methods were necessary for this paper.

Informed consent

Written informed consent was waived by the Institutional Review Board.

Ethical approval

Institutional Review Board approval was obtained.

Study subjects or cohorts overlap

Some study subjects or cohorts have been previously reported in ‘Lin, B., Chen, W., Ruan, L., Chen, Y., Zhong, M., Zhuge, Q., ... & Yang, Y. (2016). Sex differences in aneurysm morphologies and clinical outcomes in ruptured anterior communicating artery aneurysms: a retrospective study. BMJ Open, 6(4), e009920.’ and ‘Xia, N., Liu, Y., Zhong, M., Zhuge, Q., Fan, L., Chen, W., ... & Zhao, B. (2016). Smoking associated with increased aneurysm sizein patients with anterior communicating artery aneurysms. World Neurosurg, 87, 155-161.’


• retrospective

• diagnostic or prognostic study

• performed at one institution

Supplementary material

330_2017_5300_MOESM1_ESM.docx (247 kb)
ESM 1 (DOCX 246 kb)


  1. 1.
    Van GJ (2007) Subarachnoid haemorrhage. Lancet 70:1264–1266Google Scholar
  2. 2.
    Rivero-Arias O, Gray A, Wolstenholme J (2010) Burden of disease and costs of aneurysmal subarachnoid haemorrhage (aSAH) in the United Kingdom. Cost Eff Resour Alloc 8:6CrossRefGoogle Scholar
  3. 3.
    Suarez JI, Tarr RW, Selman WR (2006) Aneurysmal Subarachnoid Hemorrhage. N Engl J Med 354:387–396CrossRefGoogle Scholar
  4. 4.
    Thompson BG, Jr BR, Amin-Hanjani S et al (2015) Guidelines for the Management of Patients With Unruptured Intracranial Aneurysms: A Guideline for Healthcare Professionals From the American Heart Association/American Stroke Association. Stroke 46:2368CrossRefGoogle Scholar
  5. 5.
    Etminan N, Rinkel GJ (2016) Unruptured intracranial aneurysms: development, rupture and preventive management. Nat Rev NeurolGoogle Scholar
  6. 6.
    Brisman JL, Song JK, Newell DW (2006) Cerebral Aneurysms. N Engl J Med 355:928CrossRefGoogle Scholar
  7. 7.
    Jr FT, Benitez R, Veznedaroglu E et al (2001) A review of size and location of ruptured intracranial aneurysms. Neurosurg 49:1322–1326CrossRefGoogle Scholar
  8. 8.
    Investigators UJ (2012) The natural course of unruptured cerebral aneurysms in a Japanese cohort. N Engl J Med 2012:2474–2482CrossRefGoogle Scholar
  9. 9.
    Investigators ISoUIA (1998) Unruptured intracranial aneurysms—risk of rupture and risks of surgical intervention. N Engl J Med 1998:1725-1733Google Scholar
  10. 10.
    Ujiie H, Tamano Y, Sasaki K, Hori T (2001) Is the Aspect Ratio a Reliable Index for Predicting the Rupture of a Saccular Aneurysm? Neurosurg 48:495–502 discussion 502-493CrossRefGoogle Scholar
  11. 11.
    Amenta PS, Yadla S, Campbell PG et al (2012) Analysis of nonmodifiable risk factors for intracranial aneurysm rupture in a large, retrospective cohort. Neurosurg 70:693CrossRefGoogle Scholar
  12. 12.
    Baharoglu MI, Schirmer CM, Hoit DA, Gao B-L, Malek AM (2010) Aneurysm Inflow-Angle as a Discriminant for Rupture in Sidewall Cerebral Aneurysms. Morphometric and Computational Fluid Dynamic Analysis 41:1423–1430Google Scholar
  13. 13.
    Richardson AE, Jane JA, Payne PM (1964) Assessment of the Natural History of Anterior Communicating Aneurysms. J Neurosurg 21:266–274CrossRefGoogle Scholar
  14. 14.
    Matsukawa H, Uemura A, Fujii M, Kamo M, Takahashi O, Sumiyoshi S (2013) Morphological and clinical risk factors for the rupture of anterior communicating artery aneurysms. J Neurosurg 118:978CrossRefGoogle Scholar
  15. 15.
    Velthuis BK, van Leeuwen MS, Witkamp TD, Ramos LM, Jw BVDS, Rinkel GJ (2001) Surgical anatomy of the cerebral arteries in patients with subarachnoid hemorrhage: comparison of computerized tomography angiography and digital subtraction angiography. J Neurosurg 95:206CrossRefGoogle Scholar
  16. 16.
    Tarulli E, Fox AJ (2010) Potent risk factor for aneurysm formation: termination aneurysms of the anterior communicating artery and detection of A1 vessel asymmetry by flow dilution. AJNR Am J Neuroradiol 31:1186–1191CrossRefGoogle Scholar
  17. 17.
    Kim MC, Hwang S-K (2017) The Rupture Risk of Aneurysm in the Anterior Communicating Artery: A Single Center Study. J Cerebrovasc Endovasc Neurosurg 19:36–43CrossRefGoogle Scholar
  18. 18.
    Hamdan A, Barnes J, Mitchell P (2014) Subarachnoid hemorrhage and the female sex: analysis of risk factors, aneurysm characteristics, and outcomes. J Neurosurg 121:1367–1373CrossRefGoogle Scholar
  19. 19.
    Kongable GL, Lanzino G, Germanson TP et al (1996) Gender-related differences in aneurysmal subarachnoid hemorrhage. J Neurosurg 84:43–48CrossRefGoogle Scholar
  20. 20.
    Lin B, Chen W, Lei R et al (2016) Sex differences in aneurysm morphologies and clinical outcomes in ruptured anterior communicating artery aneurysms: a retrospective study. BMJ Open 6:e009920CrossRefGoogle Scholar
  21. 21.
    Kang H, Peng T, Qian Z et al (2015) Impact of hypertension and smoking on the rupture of intracranial aneurysms and their joint effect. Neurol Neurochir Pol 49:121–125PubMedGoogle Scholar
  22. 22.
    Etminan N, Beseoglu K, Steiger HJ, Hänggi D (2011) The impact of hypertension and nicotine on the size of ruptured intracranial aneurysms. J Neurol Neurosurg Psychiatry 82:4–7CrossRefGoogle Scholar
  23. 23.
    Vlak MH, Rinkel GJ, Greebe P, Algra A (2013) Independent risk factors for intracranial aneurysms and their joint effect: a case-control study. Stroke 44:984CrossRefGoogle Scholar
  24. 24.
    Tu JV (1996) Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. J Clin Epidemiol 49:1225–1231CrossRefGoogle Scholar
  25. 25.
    Kim KG, Goo JM, Kim JH et al (2005) Computer-aided diagnosis of localized ground-glass opacity in the lung at CT: initial experience. Radiol 237:657–661CrossRefGoogle Scholar
  26. 26.
    Karssemeijer N, Otten JD, Verbeek AL et al (2003) Computer-aided detection versus independent double reading of masses on mammograms. Radiol 227:192CrossRefGoogle Scholar
  27. 27.
    Magnotta VA, Heckel D, Andreasen NC et al (1999) Measurement of brain structures with artificial neural networks: two- and three-dimensional applications. Radiol 211:781–790CrossRefGoogle Scholar
  28. 28.
    Das A, Benmenachem T, Cooper GS et al (2003) Prediction of outcome in acute lower-gastrointestinal haemorrhage based on an artificial neural network: internal and external validation of a predictive model. Lancet 362:1261–1266CrossRefGoogle Scholar
  29. 29.
    Xia N, Liu Y, Zhong M et al (2016) Smoking associated with increased aneurysm size in patients with anterior communicating artery aneurysms. World Neurosurg 87:155–161CrossRefGoogle Scholar
  30. 30.
    Lin N, Ho A, Charoenvimolphan N, Frerichs KU, Day AL, Du R (2013) Analysis of morphological parameters to differentiate rupture status in anterior communicating artery aneurysms. PLoS One 8:e79635CrossRefGoogle Scholar
  31. 31.
    Shao X, Wang H, Wang Y et al (2016) The effect of anterior projection of aneurysm dome on the rupture of anterior communicating artery aneurysms compared with posterior projection. Clin Neurol Neurosurg 143:99CrossRefGoogle Scholar
  32. 32.
    He H, Bai Y, Garcia EA, Li S (2008) ADASYN: Adaptive synthetic sampling approach for imbalanced learning. IEEE International Joint Conference on Neural Networks, pp 1322-1328Google Scholar
  33. 33.
    He H, Garcia EA (2008) Learning from Imbalanced Data. IEEE Trans Knowl Data Eng 21:1263–1284Google Scholar
  34. 34.
    Tang B, He H (2015) KernelADASYN: Kernel based adaptive synthetic data generation for imbalanced learning. IEEE Congress on Evolutionary Computation, pp 664-671Google Scholar
  35. 35.
    Wiebers DO (2003) Unruptured intracranial aneurysms: natural history, clinical outcome, and risks of surgical and endovascular treatment. Lancet 362:103–110CrossRefGoogle Scholar
  36. 36.
    Dhar S, Tremmel M, Mocco J et al (2008) Morphology parameters for intracranial aneurysm rupture risk assessment. Neurosurg 63:185–196 discussion 196-187CrossRefGoogle Scholar
  37. 37.
    Aarhus M, Helland CA, Wester K (2009) Differences in anatomical distribution, gender, and sidedness between ruptured and unruptured intracranial aneurysms in a defined patient population. Acta Neurochir 151:1569CrossRefGoogle Scholar
  38. 38.
    Greving JP, Wermer MJ, Brown RD et al (2014) Development of the PHASES score for prediction of risk of rupture of intracranial aneurysms: a pooled analysis of six prospective cohort studies. Lancet Neurol 13:59–66CrossRefGoogle Scholar
  39. 39.
    Meng H, Tutino VM, Xiang J, Siddiqui A (2014) High WSS or low WSS? Complex interactions of hemodynamics with intracranial aneurysm initiation, growth, and rupture: toward a unifying hypothesis. Am J Neuroradiol 35:1254–1262CrossRefGoogle Scholar
  40. 40.
    Xiang J, Natarajan SK, Tremmel M et al (2011) Hemodynamic–Morphologic Discriminants for Intracranial Aneurysm Rupture. Stroke; a journal of cerebral circulation 42:144–152CrossRefGoogle Scholar
  41. 41.
    Jansen IG, Schneiders JJ, Potters WV et al (2014) Generalized versus patient-specific inflow boundary conditions in computational fluid dynamics simulations of cerebral aneurysmal hemodynamics. AJNR Am J Neuroradiol 35:1543–1548CrossRefGoogle Scholar
  42. 42.
    Hademenos GJ, Massoud TF, Turjman F, Sayre JW (1998) Anatomical and morphological factors correlating with rupture of intracranial aneurysms in patients referred for endovascular treatment. Neuroradiol 40:755–760CrossRefGoogle Scholar
  43. 43.
    Prestigiacomo C, He WJ, Chung S, Kasper L, Pasupuleti L, Mittal N (2009) Predicting aneurysm rupture probabilities through the application of a computed tomography angiography-derived binary logistic regression model. J Neurosurg 110:1–6CrossRefGoogle Scholar
  44. 44.
    Lall RR, Eddleman CS, Bendok BR, Batjer HH (2009) Unruptured intracranial aneurysms and the assessment of rupture risk based on anatomical and morphological factors: sifting through the sands of data. Neurosurg Focus 26:E2CrossRefGoogle Scholar

Copyright information

© European Society of Radiology 2018

Authors and Affiliations

  • Jinjin Liu
    • 1
  • Yongchun Chen
    • 1
  • Li Lan
    • 1
  • Boli Lin
    • 1
  • Weijian Chen
    • 1
  • Meihao Wang
    • 1
  • Rui Li
    • 1
  • Yunjun Yang
    • 1
    Email author
  • Bing Zhao
    • 2
    Email author
  • Zilong Hu
    • 1
  • Yuxia Duan
    • 1
  1. 1.Department of RadiologyThe First Affiliated Hospital of Wenzhou Medical UniversityZhejiangChina
  2. 2.Department of Neurosurgery, Ren Ji Hospital, School of MedicineShanghai Jiao Tong UniversityShanghaiChina

Personalised recommendations