Aplicación de redes neuronales en tomografía computarizada por ultrasonido
DOI:
https://doi.org/10.37537/rev.elektron.9.2.223.2025Palavras-chave:
tomografía, ultrasonido, DCN, U-NetResumo
En este trabajo se desarrolló un sistema de reconstrucción de imágenes en el marco de la tomografía computarizada por ultrasonido, utilizando técnicas de aprendizaje profundo para la estimación de mapas de velocidad, asociados a la propagación de ondas acústicas. Se abordó el diseño y entrenamiento de diferentes arquitecturas de redes neuronales y se evaluó su desempeño. Para esto, se generó un conjunto de datos sintético mediante simulaciones y se realizó la adquisición de sinogramas reales mediante un sistema experimental que utiliza un transductor de inmersión.Downloads
Referências
A. C. Kak and M. Slaney, Principles of Computerized Tomographic Imaging. Philadelphia: Society for Industrial and Applied Mathematics, 2001.
C. Høilund, “The radon transform,” Master’s thesis, Aalborg University, 2007.
N. Duric, C. Li, O. Roy, and S. Schmidt, “Acoustic tomography: Promise versus reality,” in AIP Conference Proceedings, vol. 1335, no. 1, 2011, pp. 25–31.
X. Lin, H. Shi, Z. Fu, H. Lin, S. Chen, X. Chen, and M. Chen, “Dynamic speed of sound adaptive transmission/reflection ultrasound computed tomography,” Sensors, vol. 23, no. 7, p. 3694, 2023.
F. A. Duck, Physical Properties of Tissues: A Comprehensive Reference Book. London: Academic Press, 1990.
D. Carroll, L. McKay, C. Hacking et al. (2024) Attenuation (ultrasound). Radiopaedia.org. Accessed: 2025-10-31. [Online]. Available: https://radiopaedia.org/articles/attenuation-ultrasound
J. Virieux and S. Operto, “An overview of full-waveform inversion in exploration geophysics,” Geophysics, vol. 74, no. 6, pp. WCC1–WCC26, 2009.
T. C. Robins, C. Cueto, J. Cudeiro, O. Bates, O. C. Agudo, G. Strong, L. Guasch, M. Warner, and M.-X. Tang, “Dual-probe transcranial full-waveform inversion: A brain phantom feasibility study,” Ultrasound
in Medicine and Biology, vol. 49, no. 1, pp. 283–298, 2023.
W. Han, D. N. Sinha, K. N. Springer, and D. C. Lizon, “Noninvasive measurement of acoustic properties of fluids using an ultrasonic interferometry technique,” The Journal of the Acoustical Society of America, vol. 104, no. 3, pp. 1404–1411, 1998.
M. Reigada, M. G. Gonz´alez, and L. R. Vega, “Estudio y desarrollo de un sistema para tomograf´ıa ultras´onica bidimensional,” Elektron, vol. 7, no. 2, pp. 40–47, 2023.
Olympus NDT, Introduction to Ultrasonic Transducers, Olympus Corporation, 2010, accessed: 2025-10-31. [Online]. Available: https://www.olympus-ims.com/en/ndt-tutorials/transducers/
Evident. Immersion transducers: Thickness and flaw inspection solutions. Accessed: 2025-10-31. [Online]. Available: https://ims.evidentscientific.com/en/probes/single-and-dual-element/immersion-transducers
G. Huang, Z. Liu, L. van der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 4700–4708.
O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedical image segmentation,” in Medical Image Computing and Computer-Assisted Intervention (MICCAI), ser. Lecture Notes in Computer Science, vol. 9351. Springer, 2015, pp. 234–241, available at https://arxiv.org/abs/1505.04597.
D. P. Kingma and M. Welling, “Auto-encoding variational bayes,” arXiv preprint arXiv:1312.6114, 2013, available at https://arxiv.org/abs/1312.6114.
D. Bergmann and C. Stryker, “What is a variational autoencoder?” IBM Research Blog, 2021, available at https://research.ibm.com/blog/what-is-variational-autoencoder, Accessed: 2025-10-31.
A. Stanziola, S. R. Arridge, B. T. Cox, and B. E. Treeby, “j-wave: An open-source differentiable wave simulator,” arXiv preprint arXiv:2202.04633, 2022.
R. Frostig, M. J. Johnson, and C. Leary, “Compiling machine learning programs via high-level tracing,” in SysML Conference, 2018, available at https://github.com/google/jax.
A. Baker, A. Pinard, and D. Hammerling, “DSSIM: a structural similarity index for floating-point data,” arXiv preprint arXiv:2202.02616, 2022.
Downloads
Publicado
Edição
Seção
Licença
Os autores que publicam nesta revista concordam com os termos estabelecidos em Creative Commons Atribución/Reconocimiento-NoComercial-SinDerivados 4.0 Licencia Pública Internacional — CC BY-NC-ND 4.0.
