Journal of Digital Imaging

, Volume 32, Issue 5, pp 808–815 | Cite as

Convolutional Neural Networks for the Detection and Measurement of Cerebral Aneurysms on Magnetic Resonance Angiography

  • Joseph N. StemberEmail author
  • Peter Chang
  • Danielle M. Stember
  • Michael Liu
  • Jack Grinband
  • Christopher G. Filippi
  • Philip Meyers
  • Sachin Jambawalikar


Aneurysm size correlates with rupture risk and is important for treatment planning. User annotation of aneurysm size is slow and tedious, particularly for large data sets. Geometric shortcuts to compute size have been shown to be inaccurate, particularly for nonstandard aneurysm geometries. To develop and train a convolutional neural network (CNN) to detect and measure cerebral aneurysms from magnetic resonance angiography (MRA) automatically and without geometric shortcuts. In step 1, a CNN based on the U-net architecture was trained on 250 MRA maximum intensity projection (MIP) images, then applied to a testing set. In step 2, the trained CNN was applied to a separate set of 14 basilar tip aneurysms for size prediction. Step 1—the CNN successfully identified aneurysms in 85/86 (98.8% of) testing set cases, with a receiver operating characteristic (ROC) area-under-the-curve of 0.87. Step 2—automated basilar tip aneurysm linear size differed from radiologist-traced aneurysm size on average by 2.01 mm, or 30%. The CNN aneurysm area differed from radiologist-derived area on average by 8.1 mm2 or 27%. CNN correctly predicted the area trend for the set of aneurysms. This approach is to our knowledge the first using CNNs to derive aneurysm size. In particular, we demonstrate the clinically pertinent application of computing maximal aneurysm one-dimensional size and two-dimensional area. We propose that future work can apply this to facilitate pre-treatment planning and possibly identify previously missed aneurysms in retrospective assessment.


Deep learning Convolutional neural networks U-net Aneurysm Cerebral aneurysm MRA 


Compliance with Ethical Standards

Conflict of Interest

The authors declare that they have no conflict of interest.


  1. 1.
    Backes D, Rinkel GJ, Laban KG, Algra A, Vergouwen MD: Patient- and Aneurysm-Specific Risk Factors for Intracranial Aneurysm Growth: A Systematic Review and Meta-Analysis. Stroke 47:951–957, 2016. CrossRefGoogle Scholar
  2. 2.
    Cebral JR, Raschi M: Suggested connections between risk factors of intracranial aneurysms: a review. Ann Biomed Eng 41:1366–1383, 2013. CrossRefGoogle Scholar
  3. 3.
    Brown, Jr RD, Broderick JP: Unruptured intracranial aneurysms: epidemiology, natural history, management options, and familial screening. Lancet Neurol 13:393–404, 2014. CrossRefGoogle Scholar
  4. 4.
    Ghosh S et al.: Association of morphologic and demographic features of intracranial aneurysms with their rupture: a retrospective analysis. Acta Neurochir Suppl 115:275–278, 2013. Google Scholar
  5. 5.
    International Study of Unruptured Intracranial Aneurysms, I. Unruptured intracranial aneurysms--risk of rupture and risks of surgical intervention. N Engl J Med 339:1725–1733, 1998.
  6. 6.
    Etminan N et al.: The unruptured intracranial aneurysm treatment score: a multidisciplinary consensus. Neurology 85:881–889, 2015. CrossRefGoogle Scholar
  7. 7.
    Elmalem VI, Hudgins PA, Bruce BB, Newman NJ, Biousse V: Underdiagnosis of posterior communicating artery aneurysm in noninvasive brain vascular studies. J Neuroophthalmol 31:103–109, 2011. CrossRefGoogle Scholar
  8. 8.
    White PM, Wardlaw JM, Lindsay KW, Sloss S, Patel DK, Teasdale EM: The non-invasive detection of intracranial aneurysms: are neuroradiologists any better than other observers? Eur Radiol 13:389–396, 2003. Google Scholar
  9. 9.
    Raghavan ML, Ma B, Harbaugh RE: Quantified aneurysm shape and rupture risk. J Neurosurg 102:355–362, 2005. CrossRefGoogle Scholar
  10. 10.
    Bogunovic H et al.: Automated segmentation of cerebral vasculature with aneurysms in 3DRA and TOF-MRA using geodesic active regions: an evaluation study. Med Phys 38:210–222, 2011. CrossRefGoogle Scholar
  11. 11.
    Yang X, Blezek DJ, Cheng LTE, Ryan WJ, Kallmes DF, Erickson BJ: Computer-aided detection of intracranial aneurysms in MR angiography. J Digit Imaging 24:86–95, 2011. CrossRefGoogle Scholar
  12. 12.
    Arimura H, Li Q, Korogi Y, Hirai T, Abe H, Yamashita Y, Katsuragawa S, Ikeda R, Doi K: Automated computerized scheme for detection of unruptured intracranial aneurysms in three-dimensional magnetic resonance angiography. Acad Radiol 11:1093–1104, 2004. CrossRefGoogle Scholar
  13. 13.
    Nakao T, Hanaoka S, Nomura Y, Sato I, Nemoto M, Miki S, Maeda E, Yoshikawa T, Hayashi N, Abe O: Deep neural network-based computer-assisted detection of cerebral aneurysms in MR angiography. J Magn Reson Imaging, 2017.
  14. 14.
    Long J, Shelhamer E, Darrell T: Fully convolutional networks for semantic segmentation:3431–3440, 2015.
  15. 15.
    Ronneberger, O., Fischer, P. & Brox, T. U-Net: Convolutional Networks for Biomedical Image Segmentation. 9351, 234–241, (2015).
  16. 16.
    Venhuizen FG et al.: Robust total retina thickness segmentation in optical coherence tomography images using convolutional neural networks. Biomed Opt Express 8:3292–3316, 2017. CrossRefGoogle Scholar
  17. 17.
    Mohseni Salehi SS, Erdogmus D, Gholipour A: Auto-Context Convolutional Neural Network (Auto-Net) for Brain Extraction in Magnetic Resonance Imaging. IEEE Trans Med Imaging 36:2319–2330, 2017. CrossRefGoogle Scholar
  18. 18.
    Dalmis MU et al.: Using deep learning to segment breast and fibroglandular tissue in MRI volumes. Med Phys 44:533–546, 2017. CrossRefGoogle Scholar
  19. 19.
    Piotin M, Daghman B, Mounayer C, Spelle L, Moret J: Ellipsoid approximation versus 3D rotational angiography in the volumetric assessment of intracranial aneurysms. AJNR Am J Neuroradiol 27:839–842, 2006Google Scholar
  20. 20.
    Chan SH, Wong KS, Woo YM, Chan KY, Leung KM: Volume measurement of the intracranial aneurysm: a discussion and comparison of the alternatives to manual segmentation. J Cerebrovasc Endovasc Neurosurg 16:358–363, 2014. CrossRefGoogle Scholar
  21. 21.
    Sluzewski M, van Rooij WJ, Slob MJ, Bescós JO, Slump CH, Wijnalda D: Relation between aneurysm volume, packing, and compaction in 145 cerebral aneurysms treated with coils. Radiology 231:653–658, 2004. CrossRefGoogle Scholar
  22. 22.
    Slob MJ, Sluzewski M, van Rooij WJ: The relation between packing and reopening in coiled intracranial aneurysms: a prospective study. Neuroradiology 47:942–945, 2005. CrossRefGoogle Scholar
  23. 23.
    Kai Y, Hamada J, Morioka M, Yano S, Kuratsu J: Evaluation of the stability of small ruptured aneurysms with a small neck after embolization with Guglielmi detachable coils: correlation between coil packing ratio and coil compaction. Neurosurgery 56:785–792; discussion 785–792, 2005CrossRefGoogle Scholar
  24. 24.
    Yasumoto T, Osuga K, Yamamoto H, Ono Y, Masada M, Mikami K, Kanamori D, Nakamura M, Tanaka K, Nakazawa T, Higashihara H, Maeda N, Tomiyama N: Long-term outcomes of coil packing for visceral aneurysms: correlation between packing density and incidence of coil compaction or recanalization. J Vasc Interv Radiol 24:1798–1807, 2013. CrossRefGoogle Scholar
  25. 25.
    Austin GM, Schievink W, Williams R: Controlled pressure-volume factors in the enlargement of intracranial aneurysms. Neurosurgery 24:722–730, 1989CrossRefGoogle Scholar
  26. 26.
    Valencia A, Morales H, Rivera R, Bravo E, Galvez M: Blood flow dynamics in patient-specific cerebral aneurysm models: the relationship between wall shear stress and aneurysm area index. Med Eng Phys 30:329–340, 2008. CrossRefGoogle Scholar

Copyright information

© Society for Imaging Informatics in Medicine 2018

Authors and Affiliations

  1. 1.RadiologyColumbia University Medical CenterNew YorkUSA
  2. 2.RadiologyUniversity of California Irvine School of MedicineIrvineUSA
  3. 3.NeurologyNew York University School of MedicineNew YorkUSA
  4. 4.RadiologyNorth Shore LIJ Health SystemManhassetUSA

Personalised recommendations