Abstract
The detection of intracranial aneurysms from Magnetic Resonance Angiography images is a problem of rapidly growing clinical importance. In the last 3 years, the raise of deep convolutional neural networks has instigated a streak of methods that have shown promising performance. The major issue to address is the very severe class imbalance. Previous authors have focused their efforts on the network architecture and loss function. This paper tackles the data. A rough but fast annotation is considered: each aneurysm is approximated by a sphere defined by two points. Second, a small patch approach is taken so as to increase the number of samples. Third, samples are generated by a combination of data selection (negative patches are centered half on blood vessels and half on parenchyma) and data synthesis (patches containing an aneurysm are duplicated and deformed by a 3D spline transform). This strategy is applied to train a 3D U-net model, with a binary cross entropy loss, on a data set of 111 patients (155 aneurysms, mean size 3.86 mm ± 2.39 mm, min 1.23 mm, max 19.63 mm). A 5-fold cross-validation evaluation provides state of the art results (sensitivity 0.72, false positive count 0.14, as per ADAM challenge criteria). The study also reports a comparison with the focal loss, and Cohen’s Kappa coefficient is shown to be a better metric than Dice for this highly unbalanced detection problem.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Arimura, H., Li, Q., Korogi, Y., et al.: Computerized detection of intracranial aneurysms for three-dimensional MR angiography: feature extraction of small protrusions based on a shape-based difference image technique. Med. Phys. 33(2), 394–401 (2006)
Baumgartner, M., Jaeger, P., Isensee, F., et al.: Retina U-Net for aneurysm detection in MR images. In: Automatic Detection and SegMentation Challenge (ADAM) (2020). https://adam.isi.uu.nl/results/results-miccai-2020/participating-teams-miccai-2020/ibbm/
Çiçek, Ö., Abdulkadir, A., Lienkamp, S.S., Brox, T., Ronneberger, O.: 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 424–432. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46723-8_49
Cohen, J.: A coefficient of agreement for nominal scales. Educ. Psychol. Measur. 20(1), 37–46 (1960)
Ellis, D.: 3D U-Net convolution neural network with Keras (2017). https://github.com/ellisdg/3DUnetCNN (legacy branch, commit dc2d0604499298266e7aaf1db68603288bd34577)
Faron, A., Sichtermann, T., Teichert, N., et al.: Performance of a deep-learning neural network to detect intracranial aneurysms from 3D TOF-MRA compared to human readers. Clin. Neuroradiol. 30(3), 591–598 (2020)
Fedorov, A., Beichel, R., Kalpathy-Cramer, J., et al.: 3D Slicer as an image computing platform for the quantitative imaging network. Magn. Reson. Imaging 30(9), 1323–1341 (2012). https://slicer.org. pMID: 22770690
Jang, M., Kim, J., Park, J., et al.: Features of “false positive” unruptured intracranial aneurysms on screening magnetic resonance angiography. PloS One 15(9), e0238597 (2020)
Johnson, J.M., Khoshgoftaar, T.M.: Survey on deep learning with class imbalance. J. Big Data 6(1), 1–54 (2019). https://doi.org/10.1186/s40537-019-0192-5
Lin, T.Y., Goyal, P., Girshick, R., et al.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 2980–2988 (2017)
Ma, J., An, X.: Loss ensembles for intracranial aneurysm segmentation: an embarrassingly simple method. In: Automatic Detection and SegMentation Challenge (ADAM) (2020). https://adam.isi.uu.nl/results/results-miccai-2020/participating-teams-miccai-2020/junma-2/
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)
Shi, Z., Hu, B., Schoepf, U., et al.: Artificial intelligence in the management of intracranial aneurysms: current status and future perspectives. Am. J. Neuroradiol. 41(3), 373–379 (2020)
Sichtermann, T., Faron, A., Sijben, R., et al.: Deep learning-based detection of intracranial aneurysms in 3D TOF-MRA. Am. J. Neuroradiol. 40(1), 25–32 (2019)
Asgari Taghanaki, S., Abhishek, K., Cohen, J.P., Cohen-Adad, J., Hamarneh, G.: Deep semantic segmentation of natural and medical images: a review. Artif. Intell. Rev. 54(1), 137–178 (2020). https://doi.org/10.1007/s10462-020-09854-1
Taha, A., Hanbury, A.: Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool. BMC Med. Imaging 15(1), 1–28 (2015)
Ueda, D., Yamamoto, A., Nishimori, M., et al.: Deep learning for MR angiography: automated detection of cerebral aneurysms. Radiology 290(1), 187–194 (2018)
Yang, Y., Lin, Y., Li, Y., et al.: Automatic aneurysm segmentation via 3D U-Net ensemble. In: Automatic Detection and SegMentation Challenge (ADAM) (2020). https://adam.isi.uu.nl/results/results-miccai-2020/participating-teams-miccai-2020/joker/
Yu, H., Fan, Y., Shi, H.: Team ABC. In: Automatic Detection and SegMentation Challenge (ADAM) (2020). https://adam.isi.uu.nl/results/results-live-leaderboard/abc/
Acknowledgments
We want to thank the Grand Est region and the regional and university hospital center (CHRU) of Nancy in France for funding this work. Experiments presented in this paper were carried out using the Grid’5000 experimental testbed, being developed under the INRIA ALADDIN development action with support from CNRS, RENATER and several Universities as well as other funding bodies (see https://www.grid5000.fr).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Assis, Y., Liao, L., Pierre, F., Anxionnat, R., Kerrien, E. (2021). An Efficient Data Strategy for the Detection of Brain Aneurysms from MRA with Deep Learning. In: Engelhardt, S., et al. Deep Generative Models, and Data Augmentation, Labelling, and Imperfections. DGM4MICCAI DALI 2021 2021. Lecture Notes in Computer Science(), vol 13003. Springer, Cham. https://doi.org/10.1007/978-3-030-88210-5_22
Download citation
DOI: https://doi.org/10.1007/978-3-030-88210-5_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-88209-9
Online ISBN: 978-3-030-88210-5
eBook Packages: Computer ScienceComputer Science (R0)