Abstract
Early diagnosis and treatment of cerebral aneurysms are important for reducing the risk of aneurysm rupture. Fast and accurate detection of aneurysms on blood vessels is a key step in diagnosis of aneurysm. To date, a large number of deep learning algorithms, especially the UNet network, have been developed for detection of aneurysms. However, when the amount of data for training is small, it is difficult to obtain a reliable deep learning network to effectively identify aneurysms. In order to address this issue and improve the accuracy of aneurysm detection, here we proposed to combine the deep learning approach with specially designed preprocessing and postprocessing algorithm. We first determined the rough locations of the aneurysms based on the features on the vascular skeleton before aneurysms segmentation with deep learning network, i.e. 3D Attention UNet in this work, thus reducing the missed detection rate of the UNet network. We could obtain the shape and texture related to the aneurysm. Then we used the random forest algorithm to implement the feature classification model to find out the false aneurysms incorrectly detected by the U-Net network. The experimental results show that our method can accurately identify aneurysms in the case of small data sets.
Y. Jia and W. Liao—These authors contributed equally to this work.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Drake, C.: Management of cerebral aneurysm. Stroke 12(3), 273–283 (1981)
Kato, Y., Katada, K., Hayakawa, M., et al.: Can 3D-CTA surpass DSA in diagnosis of cerebral aneurysm? Acta Neurochir. 143(3), 245–250 (2001). https://doi.org/10.1007/s007010170104
Nakao, T., Hanaoka, S., Nomura, Y., et al.: Deep neural network-based computer-assisted detection of cerebral aneurysms in MR angiography. J. Magn. Reson. Imaging 47(4), 948–953 (2018). https://doi.org/10.1002/jmri.25842
Wolterink, J.M., van Hamersvelt, R.W., Viergever, M.A., et al.: Coronary artery centerline extraction in cardiac CT angiography using a CNN-based orientation classifier. Med. Image Anal. 51, 46–60 (2019). https://doi.org/10.1016/j.media.2018.10.005
Ueda, D., Yamamoto, A., Nishimori, M., et al.: Deep learning for MR angiography: automated detection of cerebral aneurysms. Radiology 290(1), 187–194 (2018). https://doi.org/10.1148/radiol.2018180901
Zhou, Z., et al.: Models genesis: generic autodidactic models for 3D medical image analysis. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11767, pp. 384–393. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32251-9_42
van Griethuysen, J.J.M., et al.: Computational radiomics system to decode the radiographic phenotype. Can. Res. 77(21), e104–e107 (2017). https://doi.org/10.1158/0008-5472.CAN-17-0339
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Jia, Y. et al. (2021). Detect and Identify Aneurysms Based on Adjusted 3D Attention UNet. In: Hennemuth, A., Goubergrits, L., Ivantsits, M., Kuhnigk, JM. (eds) Cerebral Aneurysm Detection and Analysis. CADA 2020. Lecture Notes in Computer Science(), vol 12643. Springer, Cham. https://doi.org/10.1007/978-3-030-72862-5_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-72862-5_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-72861-8
Online ISBN: 978-3-030-72862-5
eBook Packages: Computer ScienceComputer Science (R0)