Estudio de redes generativas de confrontación para generación de datos sintéticos y su aplicación a tomografía optoacústica

Alejandro Scopa Lopina, Martín Germán González, Matías Vera

Resumen


En este trabajo se propone el uso de una red generativa de confrontación (GAN) para efectuar un aumento de datos con el objetivo de mejorar la reconstrucción de imágenes en sistemas para tomografía optoacústica (TOA). Se utilizó el modelo denominado FastGAN que es una red compacta, capaz de generar imágenes de alta resolución a partir de un conjunto de datos reducidos. La calidad de los datos generados se evaluó a través de dos métodos. Por un lado, se usó la distancia de inicio de Fréchet (FID), observándose una tendencia decreciente a largo de todo el entrenamiento de la GAN. En el segundo método se entrenó una red neuronal U-Net diseñada para un sistema de TOA con y sin datos aumentados. En este caso, el modelo entrenado con los datos extras aportados por la GAN logró una mejora apreciable en las figuras de mérito asociadas a la reconstrucción.

Palabras clave


Tomografía optoacústica; Aprendizaje profundo; Redes generativas de confrontación; Datos sintéticos

Texto completo:

PDF HTML

Referencias


C. Huang, K. Wang, L. Nie, and et al., “Full-wave iterative image reconstruction in photoacoustic tomography with acoustically inhomogeneous media,” IEEE Transactions on Medical Imaging, vol. 32, pp. 1097–1110, 2013.

S. Arridge, P. Beard, M. Betcke, and et al., “Accelerated high-resolution photoacoustic tomography via compressed sensing,” Physics in medicine and biology, vol. 61, pp. 8908–8940, 2016.

Y. E. Boink, M. J. Lagerwerf, W. Steenbergen, and et al., “A framework for directional and higher-order reconstruction in photoacoustic tomography,” Physics in Medicine & Biology, vol. 63, 2018.

I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. The MIT Press, 2016.

A. Hauptmann and B. Cox, “Deep learning in photoacoustic tomography: Current approaches and future directions,” Journal of Biomedical Optics, vol. 25, 09 2020.

O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” arXiv preprint ar-Xiv:1505.04597, 2015.

S. Guan, A. A. Khan, S. Sikdar, and P. V. Chitnis, “Fully Dense UNet for 2-D Sparse Photoacoustic Tomography Artifact Removal,” IEEE Journal of Biomedical and Health Informatics, vol. 24, no. 2, pp. 568--576, 2020.

X. Ma, C. Peng, J. Yuan, Q. Cheng, G. Xu, X. Wang, and P. L. Carson, “Multiple delay and sum with enveloping beamforming algorithm for photoacoustic imaging,” IEEE Trans. on Medical Imaging, vol. 39, pp. 1812–1821, 2019.

L. Torrey and J. Shavlik, “Transfer learning,” Handbook of Research on Machine Learning Applications, 01 2009.

B. Liu, Y. Zhu, K. Song, and A. Elgammal, “Towards faster and stabilized GAN training for high-fidelity few-shot image synthesis,” arXiv preprint arXiv:2101.04775, 2021.

M. Arjovsky and L. Bottou, “Towards principled methods for training generative adversarial networks,” stat, vol. 1050, 01 2017.

D. Zhang and A. Khoreva, “PA-GAN: Improving gan training by progressive augmentation,” arXiv preprint arXiv:1901.10422, 01 2019.

H. Zhang, T. Xu, H. Li, S. Zhang, X. Wang, X. Huang, and D. N. Metaxas, “Stackgan: Text to photo-realistic image synthesis with stacked generative adversarial networks,” Proceedings of the IEEE international conference on computer vision, pp. 5907–5915, 2017.

K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770–778, 2016.

P. Isola, J.-Y. Zhu, T. Zhou, and A. Efros, “Image-to-image translation with conditional adversarial networks,” 07 2017, pp. 5967–5976.

D. Hendrycks, M. Mazeika, S. Kadavath, and D. Song, “Using self-supervised learning can improve model robustness and uncertainty,” Advances in Neural Information Processing Systems, pp. 15 663––15 674, 2019.

J. Lim and J. C. Ye, “Geometric GAN,” arXiv preprint ar-Xiv:1705.02894, 05 2017.

“DRIVE: Digital retinal images for vessel extraction,” 2020. [Online]. Available: https://drive.grand-challenge.org/

“STARE: Structured analysis of the retina,” 2000. [Online]. Available: https://cecas.clemson.edu/ ∼ ahoover/stare/

“RITE: Retinal images vessel tree extraction,” 2013. [Online]. Available: https://medicine.uiowa.edu/eye/rite-dataset

“ARIA: Automated retinal image analysis,” 2006. [Online]. Available: http://www.damianjjfarnell.com/

A. Hatamizadeh, H. Hosseini, N. Patel, J. Choi, C. Pole, C. Hoeferlin, S. Schwartz, and D. Terzopoulos, “RAVIR: A dataset and methodology for the semantic segmentation and quantitative analysis of retinal arteries and veins in infrared reflectance imaging,” IEEE Journal of Biomedical and Health Informatics, 2022.

A. Borji, “Pros and cons of gan evaluation measures,” Computer Vision and Image Understanding, vol. 1793, pp. 41–65, 2019.

M. Heusel, H. Ramsauer, T. Unterthiner, B. Nessler, and S. Hochreiter, “Gans trained by a two time-scale update rule converge to a local nash equilibrium,” Advances in neural information processing systems, pp. 6626–6637, 2017.

C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, “Rethinking the inception architecture for computer vision,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2818–2826, 2016.

A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga et al., “Pytorch: An imperative style, high-performance deep learning library,” Advances in neural information processing systems, vol. 32, 2019.

M. G. Gonzalez, M. Vera, and L. R. Vega, “Combining band-frequency separation and deep neural networks for optoacoustic imaging,” Optics and Lasers in Engineering, vol. 163, p. 107471, 2023.

L. Hirsch, M. G. Gonzalez, and L. R. Vega, “A comparative study of time domain compressed sensing techniques for optoacoustic imaging,” IEEE Latin America Transactions, vol. 20, pp. 1018–1024, 2022.

C. Tian, M. Pei, K. Shen, S. Liu, Z. Hu, and T. Feng, “Impact of system factors on the performance of photoacoustic tomography scanners,” Phys. Rev. Applied, vol. 13, p. 014001, 2020.

M. Haltmeier, M. Sandbichler, T. Berer, J. Bauer-Marschallinger, P. Burgholzer, and L. Nguyen, “A sparsification and reconstruction strategy for compressed sensing photoacoustic tomography,” Acoust. Soc. Am., vol. 143, no. 6, p. 3838–3848, 2018.

S. Guan, A. Khan, S. Sikdar, and P. Chitnis, “Fully dense unet for 2D sparse photoacoustic tomography artifact removal,” IEEE Journal of Biomedical and Health Informatics, vol. 24, pp. 568–576, 2020.

W. Xing-xing and L. Jin-guo, “A new early stopping algorithm for improving neural network generalization,” in 2009 Second International Conference on Intelligent Computation Technology and Automation, vol. 1, 2009, pp. 15–18.

N. Awasthi, G. Jain, S. K. Kalva, M. Pramanik, and P. Yalavarthy, “Deep neural network-based sinogram super-resolution and band-width enhancement for limited-data photoacoustic tomography,” IEEE Transactions on Ultrasonics Ferroelectrics and Frequency Control, vol. PP, 02 2020.




DOI: https://doi.org/10.37537/rev.elektron.7.2.185.2023

Enlaces de Referencia

  • Por el momento, no existen enlaces de referencia


Copyright (c) 2023 Alejandro Scopa Lopina

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Revista elektron,  ISSN-L 2525-0159
Facultad de Ingeniería. Universidad de Buenos Aires 
Paseo Colón 850, 3er piso
C1063ACV - Buenos Aires - Argentina
revista.elektron@fi.uba.ar
+54 (11) 528-50889