Convolutional Neural Networks for the Detection and Measurement of Cerebral Aneurysms on Magnetic Resonance Angiography
- 379 Downloads
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.
KeywordsDeep 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.
- 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. https://doi.org/10.1056/NEJM199812103392401
- 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. https://doi.org/10.1016/j.acra.2004.07.011 CrossRefGoogle Scholar
- 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. https://doi.org/10.1002/jmri.25842
- 14.Long J, Shelhamer E, Darrell T: Fully convolutional networks for semantic segmentation:3431–3440, 2015. https://doi.org/10.1109/cvpr.2015.7298965
- 15.Ronneberger, O., Fischer, P. & Brox, T. U-Net: Convolutional Networks for Biomedical Image Segmentation. 9351, 234–241, https://doi.org/10.1007/978-3-319-24574-4_28 (2015).
- 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
- 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.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. https://doi.org/10.1016/j.jvir.2013.04.030 CrossRefGoogle Scholar