Abstract
The paper considers the problem of silicon aberrator shape identification from 3D medical ultrasound data using convolutional neural networks.
This work demonstrates that it is possible to obtain high quality numerical 3D ultrasound images using direct numerical modeling methods. Current study models reflections from long smooth boundaries and individual large reflectors, as well as background noise from point reflectors. The synthetic computational data obtained in this way can be used to develop convolutional neural networks for 3D ultrasound data.
This work shows that 3D convolutional neural network can identify position and shape of the silicone aberrator boundary from an ultrasound data. The papers covers the cases of strong noise and significant signal distortions. It is demonstrated that 3D network can handle the distortions and correctly distinguish the boundary of materials from the responses of individual large reflectors. This possibility of the network is due to its three-dimensional architecture, which uses all spatial information from all directions.
Supported by RSF project 22-11-00142.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Dimitris, P., Manuel, V., Florian, M., Marcel, A, Jean-Philippe, T.: Single-shot CNN-based ultrasound imaging with sparse linear arrays. In: 2020 IEEE International Ultrasonics Symposium (IUS), pp. 1–4 (2020)
Stankevich, A.S., Petrov, I.B., Vasyukov, A.V.: Numerical solution of inverse problems of wave dynamics in heterogeneous media with convolutional neural networks. In: Favorskaya, M.N., Favorskaya, A.V., Petrov, I.B., Jain, L.C. (eds.) Smart Modelling for Engineering Systems. SIST, vol. 215, pp. 235–246. Springer, Singapore (2021). https://doi.org/10.1007/978-981-33-4619-2_18
Patel, D., Tibrewala, R., Vega, A., Dong, L., Hugenberg, N., Oberai, A.: Circumventing the solution of inverse problems in mechanics through deep learning: application to elasticity imaging. Comput. Methods Appl. Mech. Eng. 353, 448–466 (2019)
Lu, H., Wang, H., Zhang, Q., Yoon, S., Won, D.: A 3D convolutional neural network for volumetric image semantic segmentation. Procedia Manuf. 39, 422–428 (2019)
Potočnik, B., Šavc, M.: Deeply-supervised 3D convolutional neural networks for automated ovary and follicle detection from ultrasound volumes. Appl. Sci. 12(1246) (2022)
Brown, K., Dormer, J., Fei, B., Hoy, K.: Deep 3D convolutional neural networks for fast super-resolution ultrasound imaging. In: Proceedings of the SPIE 10955, Medical Imaging 2019: Ultrasonic Imaging and Tomography, p. 1095502 (2019)
Krönke, M., et al.: Tracked 3D ultrasound and deep neural network-based thyroid segmentation reduce interobserver variability in thyroid volumetry. PLoS ONE 17(7), Article e0268550 (2022)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. arXiv:1505.04597 (2015)
Çiçek, Ö., Abdulkadir, A., Lienkamp, S.S., Brox, T., Ronneberger, O.: 3D U-Net: learning dense volumetric segmentation from sparse annotation. arXiv:1606.06650 (2016)
Jiang, M., Spence, J.D., Chiu, B.: Segmentation of 3D ultrasound carotid vessel wall using U-Net and segmentation average network. In: 42nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 2043–2046. IEEE (2020)
Zheng, Y., Liu, D., Georgescu, B., Nguyen, H., Comaniciu, D.: 3D deep learning for efficient and robust landmark detection in volumetric data. In: Proceedings of 2015 IEEE Medical Image Computing and Computer-Assisted Intervention, pp. 565–572. IEEE (2015)
Mast, T.D., Hinkelman, L.M., Metlay, L.A., Orr, M.J., Waag, R.C.: Simulation of ultrasonic pulse propagation, distortion, and attenuation in the human chest wall. J. Acoust. Soc. Am. 6, 3665–3677 (1999)
Beklemysheva, K., et al.: Transcranial ultrasound of cerebral vessels in silico: proof of concept. Russ. J. Numer. Anal. Math. Model. 31(5), 317–328 (2016)
Madsen, E.L., Sathoff, H.J., Zagzebski, J.A.: Ultrasonic shear wave properties of soft tissues and tissuelike materials. J. Acoust. Soc. Am. 74(5), 1346–1355 (1983)
Beklemysheva, K., Grigoriev, G., Kulberg, N., Petrov, I., Vasyukov, A., Vassilevski, Y.: Numerical simulation of aberrated medical ultrasound signals. Russ. J. Numer. Anal. Math. Model. 33, 277–288 (2018)
Vassilevski, Y., Beklemysheva, K., Grigoriev, G., Kulberg, N., Petrov, I., Vasyukov, A.: Numerical modelling of medical ultrasound: phantom-based verification. Russ. J. Numer. Anal. Math. Model. 32(5), 339–346 (2017)
Stankevich, A., Nechepurenko, I., Shevchenko, A., Gremyachikh, L., Ustyuzhanin, A., Vasyukov, A.: Learning velocity model for complex media with deep convolutional neural networks. arXiv:2110.08626 (2021)
Paserin, O., Mulpuri, K., Cooper, A., Abugharbieh, R., Hodgson, A.: Improving 3D ultrasound scan adequacy classification using a three-slice convolutional neural network architecture. In: Zhan, W., Baena, F. (eds.) CAOS 2018 (EPiC Series in Health Sciences), vol. 2, pp. 152–156 (2018)
Coupeau, P., Fasquel, J.-B., Mazerand, E., Menei, P., Montero-Menei, C.N., Dinomais, M.: Patch-based 3D U-Net and transfer learning for longitudinal piglet brain segmentation on MRI. Comput. Methods Programs Biomed. 214, 106563 (2022)
Ghimire, K., Chen, Q., Feng, X.: Patch-based 3D UNet for head and neck tumor segmentation with an ensemble of conventional and dilated convolutions. In: Andrearczyk, V., Oreiller, V., Depeursinge, A. (eds.) HECKTOR 2020. LNCS, vol. 12603, pp. 78–84. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-67194-5_9
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Vasyukov, A., Stankevich, A., Beklemysheva, K., Petrov, I. (2022). Aberrator Shape Identification from 3D Ultrasound Data Using Convolutional Neural Networks and Direct Numerical Modeling. In: Balandin, D., Barkalov, K., Meyerov, I. (eds) Mathematical Modeling and Supercomputer Technologies. MMST 2022. Communications in Computer and Information Science, vol 1750. Springer, Cham. https://doi.org/10.1007/978-3-031-24145-1_2
Download citation
DOI: https://doi.org/10.1007/978-3-031-24145-1_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-24144-4
Online ISBN: 978-3-031-24145-1
eBook Packages: Computer ScienceComputer Science (R0)