3D convolutional neural networks for detecting intracranial aneurysms on brachiocephalic arteries CTA scans

Background: Computed tomography angiography (CTA) is the primary and minimally invasive imaging modality currently used for diagnosis and monitoring of intracranial aneurysms as well as preoperative planning of their treatment. However, its interpretation is time-consuming even for specially trained neuroradiologists. Nowadays little is known whether trained neural networks contribute to analyzing medical images and reduce the time to diagnosis, and how effective they are in detecting intracranial aneurysms according to the CTA findings.

Objective: To assess the diagnostic value of a convolutional neural network prototype in the intracranial aneurysm detection according to the brachiocephalic arteries CTA findings.

Materials and methods: We analyzed the 3D convolutional neural network prototype based at Kuban State University (Krasnodar, Russian Federation).This prototype was to determine the probability of intracranial aneurysms according to the brachiocephalic arteries CTA findings, obtained in the Radiology Department of Scientific Research Institute – Ochapovsky Regional Clinical Hospital No. 1. The study included 451 CTA scans of 205 patients with confirmed intracranial aneurysms and 246 patients without aneurysms.

Results: The sensitivity of the 3D convolutional neural network prototype in the aneurysms detection according to the brachiocephalic arteries CTA findings was 85.1%, the specificity was 95.1%, and the overall accuracy was 91%.

Conclusions: The 3D convolutional systems may predict aneurysms with a high accuracy as well as localize them with an accuracy of more than 90%. Such results require a larger dataset.

1. Zyablova EI, Achmiz NZ, Tkachev VV, Porhanov VA. Cerebrovascular CT-angiography in the emergency diagnostics of ruptured cerebral aneurysms. Russian Electronic Journal of Radiology. 2022;12(2):65–73. (In Russ.). https://doi.org/10.21569/2222-7415-2022-12-2-65-73

2. Turan N, Heider RA, Roy AK, et al. Current perspectives in imaging modalities for the assessment of unruptured intracranial aneurysms: a comparative analysis and review. World Neurosurg. 2018;113:280–292. PMID: 29360591. https://doi.org/10.1016/j.wneu.2018.01.054

3. Yoon NK, McNally S, Taussky P, Park MS. Imaging of cerebral aneurysms: a clinical perspective. Neurovasc Imaging. 2016;2(1). https://doi.org/10.1186/s40809-016-0016-3

4. Jayaraman MV, Mayo-Smith WW, Tung GA, et al. Detection of intracranial aneurysms: multi-detector row CT angiography compared with DSA. Radiology. 2004;230(2):510–518. PMID: 14699177. https://doi.org/10.1148/radiol.2302021465

5. Bharatha A, Yeung R, Durant D, et al. Comparison of computed tomography angiography with digital subtraction angiography in the assessment of clipped intracranial aneurysms. J Comput Assist Tomogr. 2010;34(3):440–445. PMID: 20498551. https://doi.org/10.1097/RCT.0b013e3181d27393

6. Lubicz B, Levivier M, François O, et al. Sixty-four-row multisection CT angiography for detection and evaluation of ruptured intracranial aneurysms: interobserver and intertechnique reproducibility. AJNR Am J Neuroradiol. 2007;28(10):1949–1955. PMID: 17898200. PMCID: PMC8134231. https://doi.org/10.3174/ajnr.A0699

7. White PM, Teasdale EM, Wardlaw JM, Easton V. Intracranial aneurysms: CT angiography and MR angiography for detection prospective blinded comparison in a large patient cohort. Radiology. 2001;219(3):739–749. PMID: 11376263. https://doi.org/10.1148/radiology.219.3.r01ma16739

8. Rajpurkar P, Irvin J, Ball RL, et al. Deep learning for chest radiograph diagnosis: a retrospective comparison of the CheXNeXt algorithm to practicing radiologists.PLoS Med. 2018;15(11):e1002686. PMID: 30457988. PMCID: PMC6245676. https://doi.org/10.1371/journal.pmed.1002686

9. Prikhodko IV, Erogodskii EA, Kuzmina DV, Sinitsa SG, Zyablova EI, Khalafyan AA. Algorithms for detection of intracranial aneurysms location. In: Applied Mathematics: Modern Issues of Mathematics, Informatics, and Modeling: Proceedings of III Russian Scientific and Practical Conference for Young Scientists. Vol. 1. Krasnodar Center of Scientific and Technical Information – branch of Russian Energy Agency of the Ministry of Energy of Russia; 2021:313–320. (In Russ.).

10. UCAS Japan Investigators, Morita A, Kirino T, et al. The natural course of unruptured cerebral aneurysms in a Japanese cohort. N Engl J Med. 2012;366(26):2474–2482. PMID: 22738097. https://doi.org/10.1056/NEJMoa1113260

11. Goodfellow I, Bengio Y, Courville A. Deep Learning. Slinkin AA, trans. 2nd rev ed. DMK Press; 2018. (In Russ.).

12. Nikolenko S, Kadurin A, Arkhangelskaya E. Deep Learning. Piter; 2018. (In Russ.).

13. Zyablova EI, Tkachev VV, Porhanov VA. CT angiography for detecting the cause of intracranial hemorrhage in the emergency department. Innovative Medicine of Kuban. 2021;(1):34–38. (In Russ.). https://doi.org/10.35401/2500-0268-2021-21-1-34-38

14. Tomandl BF, Hammen T, Klotz E, Ditt H, Stemper B, Lell M. Bone-subtraction CT angiography for the evaluation of intracranial aneurysms. AJNR Am J Neuroradiol. 2006;27(1):55–59. PMID: 16418356. PMCID: PMC7976055.

15. Shi WY, Li YD, Li MH, et al. 3D rotational angiography with volume rendering: the utility in the detection of intracranial aneurysms. Neurol India. 2010;58(6):908–913. PMID: 21150058. https://doi.org/10.4103/0028-3886.73743

16. Lin N, Ho A, Gross BA, et al. Differences in simple morphological variables in ruptured and unruptured middle cerebral artery aneurysms. J Neurosurg. 2012;117(5):913–919. PMID: 22957531. https://doi.org/10.3171/2012.7.JNS111766

17. Villablanca JP, Jahan R, Hooshi P, et al. Detection and characterization of very small cerebral aneurysms by using 2D and 3D helical CT angiography. AJNR Am J Neuroradiol. 2002;23(7):1187–1198. PMID: 12169479. PMCID: PMC8185733.