Papers
Topics
Authors
Recent
Search
2000 character limit reached

Robust CNN Multi-Nested-LSTM Framework with Compound Loss for Patch-based Multi-Push Ultrasound Shear Wave Imaging and Segmentation

Published 30 Jul 2024 in eess.IV and q-bio.QM | (2407.20558v1)

Abstract: Ultrasound Shear Wave Elastography (SWE) is a noteworthy tool for in-vivo noninvasive tissue pathology assessment. State-of-the-art techniques can generate reasonable estimates of tissue elasticity, but high-quality and noise-resiliency in SWE reconstruction have yet to demonstrate advancements. In this work, we propose a two-stage DL pipeline producing reliable reconstructions and denoise said reconstructions to obtain lower noise prevailing elasticity mappings. The reconstruction network consists of a Resnet3D Encoder to extract temporal context from the sequential multi-push data. The encoded features are sent to multiple Nested CNN LSTMs which process them in a temporal attention-guided windowing basis and map the 3D features to 2D using FFT-attention, which are then decoded into an elasticity map as primary reconstruction. The 2D maps from each multi-push region are merged and cleaned using a dual-decoder denoiser network, which independently denoises foreground and background before fusion. The post-denoiser generates a higher-quality reconstruction and an inclusion-segmentation mask. A multi-objective loss is designed to accommodate the denoising, fusing, and segmentation processes. The method is validated on sequential multi-push SWE motion data with multiple overlapping regions. A patch-based training procedure is introduced with network modifications to handle data scarcity. Evaluations produce 32.66dB PSNR, 43.19dB CNR in noisy simulation, and 22.44dB PSNR, 36.88dB CNR in experimental data, across all test samples. Moreover, IoUs (0.909 and 0.781) were quite satisfactory in the datasets. After comparing with other reported deep-learning approaches, our method proves quantitatively and qualitatively superior in dealing with noise influences in SWE data. From a performance point of view, our deep-learning pipeline has the potential to become utilitarian in the clinical domain.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (46)
  1. M. Tanter, J. Bercoff, A. Athanasiou, T. Deffieux, J.-L. Gennisson, G. Montaldo, M. Muller, A. Tardivon, and M. Fink, “Quantitative assessment of breast lesion viscoelasticity: initial clinical results using supersonic shear imaging,” Ultrasound Med. Biol., vol. 34, no. 9, pp. 1373–1386, 2008.
  2. S. Mueller and L. Sandrin, “Liver stiffness: a novel parameter for the diagnosis of liver disease,” Hepatic medicine: evidence and research, pp. 49–67, 2010.
  3. J. H. Youk, E. J. Son, H. M. Gweon, H. Kim, Y. J. Park, and J.-A. Kim, “Comparison of strain and shear wave elastography for the differentiation of benign from malignant breast lesions, combined with b-mode ultrasonography: qualitative and quantitative assessments,” Ultrasound Med. Biol., vol. 40, no. 10, pp. 2336–2344, 2014.
  4. J. F. Greenleaf, M. Fatemi, and M. Insana, “Selected methods for imaging elastic properties of biological tissues,” Annu. Rev. Biomed. Eng., vol. 5, no. 1, pp. 57–78, 2003.
  5. J. C. Bamber et al., “Ultrasound elasticity imaging: definition and technology,” E. Radiol., vol. 9, no. 3, p. S327, 1999.
  6. A. P. Sarvazyan, O. V. Rudenko, S. D. Swanson, J. B. Fowlkes, and S. Y. Emelianov, “Shear wave elasticity imaging: a new ultrasonic technology of medical diagnostics,” Ultrasound Med. Biol., vol. 24, no. 9, pp. 1419–1435, 1998.
  7. J. H. Yoon, M. H. Kim, E.-K. Kim, H. J. Moon, J. Y. Kwak, and M. J. Kim, “Interobserver variability of ultrasound elastography: how it affects the diagnosis of breast lesions,” AJR, vol. 196, no. 3, pp. 730–736, 2011.
  8. J. H. Youk, H. Gweon, and E. Son, “Shear-wave elastography in breast ultrasonography: state of the art,” Ultrasonography, vol. 36, 04 2017.
  9. G. Ferraioli, P. Parekh, A. B. Levitov, and C. Filice, “Shear wave elastography for evaluation of liver fibrosis,” J. Ultrasound Med., vol. 33, no. 2, pp. 197–203, 2014.
  10. S. Woo, C. H. Suh, S. Y. Kim, J. Cho, and S. H. Kim, “Shear-wave elastography for detection of prostate cancer: A systematic review and diagnostic meta-analysis,” AJR, vol. 209, pp. 1–9, 08 2017.
  11. K. Nightingale, “Acoustic radiation force impulse (arfi) imaging: a review,” Current medical imaging, vol. 7, no. 4, pp. 328–339, 2011.
  12. L. Sandrin, B. Fourquet, J.-M. Hasquenoph, S. Yon, C. Fournier, F. Mal, C. Christidis, M. Ziol, B. Poulet, F. Kazemi et al., “Transient elastography: a new noninvasive method for assessment of hepatic fibrosis,” Ultrasound Med. Biol., vol. 29, no. 12, pp. 1705–1713, 2003.
  13. M. L. Palmeri, M. H. Wang, J. J. Dahl, K. D. Frinkley, and K. R. Nightingale, “Quantifying hepatic shear modulus in vivo using acoustic radiation force,” Ultrasound Med. Biol., vol. 34, no. 4, pp. 546–558, 2008.
  14. J. McLaughlin and D. Renzi, “Shear wave speed recovery in transient elastography and supersonic imaging using propagating fronts,” Inverse Probl., vol. 22, no. 2, p. 681, 2006.
  15. P. Song, H. Zhao, A. Manduca, M. W. Urban, J. F. Greenleaf, and S. Chen, “Comb-push ultrasound shear elastography (cuse): a novel method for two-dimensional shear elasticity imaging of soft tissues,” IEEE Trans. Med. Imaging, vol. 31, no. 9, pp. 1821–1832, 2012.
  16. P. Kijanka and M. W. Urban, “Fast local phase velocity-based imaging: Shear wave particle velocity and displacement motion study,” IEEE Trans. Ultrason. Ferroelectr. Freq. Control, vol. 67, no. 3, pp. 526–537, 2019.
  17. N. C. Rouze, M. H. Wang, M. L. Palmeri, and K. R. Nightingale, “Parameters affecting the resolution and accuracy of 2-d quantitative shear wave images,” IEEE Trans. Ultrason. Ferroelectr. Freq. Control, vol. 59, no. 8, pp. 1729–1740, 2012.
  18. J. Bercoff, M. Tanter, and M. Fink, “Supersonic shear imaging: a new technique for soft tissue elasticity mapping,” IEEE Trans. Ultrason. Ferroelectr. Freq. Control, vol. 51, no. 4, pp. 396–409, 2004.
  19. P. Kijanka and M. W. Urban, “Local phase velocity based imaging: A new technique used for ultrasound shear wave elastography,” IEEE Trans. Med. Imaging, vol. 38, no. 4, pp. 894–908, 2018.
  20. A. Zayed and H. Rivaz, “Fast strain estimation and frame selection in ultrasound elastography using machine learning,” IEEE Trans. Ultrason. Ferroelectr. Freq. Control, vol. 68, no. 3, pp. 406–415, 2020.
  21. F. K. Jush, M. Biele, P. M. Dueppenbecker, and A. Maier, “Deep learning for ultrasound speed-of-sound reconstruction: Impacts of training data diversity on stability and robustness,” arXiv preprint arXiv:2202.01208, 2022.
  22. L. He, B. Peng, T. Yang, and J. Jiang, “An application of super-resolution generative adversary networks for quasi-static ultrasound strain elastography: A feasibility study,” IEEE Access, vol. 8, pp. 65 769–65 779, 2020.
  23. A. K. Tehrani, M. Sharifzadeh, E. Boctor, and H. Rivaz, “Bi-directional semi-supervised training of convolutional neural networks for ultrasound elastography displacement estimation,” IEEE Trans. Ultrason. Ferroelectr. Freq. Control, vol. 69, no. 4, pp. 1181–1190, 2022.
  24. S. Ahmed, U. Kamal, and M. K. Hasan, “Dswe-net: A deep learning approach for shear wave elastography and lesion segmentation using single push acoustic radiation force,” Ultrasonics, vol. 110, p. 106283, 2021.
  25. M. Neidhardt, M. Bengs, S. Latus, S. Gerlach, C. J. Cyron, J. Sprenger, and A. Schlaefer, “Ultrasound shear wave elasticity imaging with spatio-temporal deep learning,” IEEE Trans. Biomed. Eng., 2022.
  26. P. Song, A. Manduca, H. Zhao, M. W. Urban, J. F. Greenleaf, and S. Chen, “Fast shear compounding using robust 2-d shear wave speed calculation and multi-directional filtering,” Ultrasound Med. Biol., vol. 40, no. 6, pp. 1343–1355, 2014.
  27. T. S. N. M. N. Inoue, “Development of shear wave measurement with a reliability indicator,” Ultrasound Med. Biol., vol. 2, p. 3.
  28. J. Hu, L. Shen, and G. Sun, “Squeeze-and-excitation networks,” in Proceedings of the IEEE Conf. on Comput. Vis. and Pattern Recognition, 2018, pp. 7132–7141.
  29. O. Couture, M. Fink, and M. Tanter, “Ultrasound contrast plane wave imaging,” IEEE Trans. Ultrason. Ferroelectr. Freq. Control, vol. 59, no. 12, pp. 2676–2683, 2012.
  30. K. Hara, H. Kataoka, and Y. Satoh, “Learning spatio-temporal features with 3d residual networks for action recognition,” in Proceedings of the IEEE Int. Conf. Comput. Vis. Workshops, 2017, pp. 3154–3160.
  31. S. Hochreiter, “The vanishing gradient problem during learning recurrent neural nets and problem solutions,” Int. J. Uncertain., Fuzziness and Knowledge-Based Syst., vol. 6, no. 02, pp. 107–116, 1998.
  32. H. So, Y. Chan, Q. Ma, and k. P. Ching, “Comparison of various periodograms for sinusoid detection and frequency estimation,” IEEE Trans. Aerosp. Electron. Syst., vol. 35, no. 3, pp. 945–952, 1999.
  33. X. Shi, Z. Chen, H. Wang, D.-Y. Yeung, W. K. Wong, and W.-c. WOO, “Convolutional lstm network: A machine learning approach for precipitation nowcasting,” 06 2015.
  34. T. Deffieux, J.-L. Gennisson, J. Bercoff, and M. Tanter, “On the effects of reflected waves in transient shear wave elastography,” IEEE Trans. Ultrason. Ferroelectr. Freq. Control, vol. 58, no. 10, pp. 2032–2035, 2011.
  35. E. C. Elegbe and S. A. McAleavey, “Single tracking location methods suppress speckle noise in shear wave velocity estimation,” Ultrasonic imaging, vol. 35, no. 2, pp. 109–125, 2013.
  36. N. Nitta, M. Yamakawa, H. Hachiya, and T. Shiina, “A review of physical and engineering factors potentially affecting shear wave elastography,” J. Med. Ultrason., vol. 48, no. 4, pp. 403–414, 2021.
  37. J. Cui, K. Gong, N. Guo, C. Wu, X. Meng, K. Kim, K. Zheng, Z. Wu, L. Fu, B. Xu et al., “Pet image denoising using unsupervised deep learning,” EJNMMI, vol. 46, pp. 2780–2789, 2019.
  38. W. Jifara, F. Jiang, S. Rho, M. Cheng, and S. Liu, “Medical image denoising using convolutional neural network: a residual learning approach,” J. Supercomput., vol. 75, pp. 704–718, 2019.
  39. W. El-Shafai, S. A. El-Nabi, E.-S. M. El-Rabaie, A. M. Ali, N. F. Soliman, A. D. Algarni, A. El-Samie, and E. Fathi, “Efficient deep-learning-based autoencoder denoising approach for medical image diagnosis.” Comput. Mater. Contin., vol. 70, no. 3, 2022.
  40. A. Amyar, R. Modzelewski, H. Li, and S. Ruan, “Multi-task deep learning based ct imaging analysis for covid-19 pneumonia: Classification and segmentation,” Comput. Biol. Med., vol. 126, p. 104037, 2020.
  41. L. Song, J. Lin, Z. J. Wang, and H. Wang, “An end-to-end multi-task deep learning framework for skin lesion analysis,” IEEE J. Biomed. Health. Inform., vol. 24, no. 10, pp. 2912–2921, 2020.
  42. Y. Zhou, H. Chen, Y. Li, Q. Liu, X. Xu, S. Wang, P.-T. Yap, and D. Shen, “Multi-task learning for segmentation and classification of tumors in 3d automated breast ultrasound images,” Med. Image Anal., vol. 70, p. 101918, 2021.
  43. M. L. Palmeri, B. Qiang, S. Chen, and M. W. Urban, “Guidelines for finite-element modeling of acoustic radiation force-induced shear wave propagation in tissue-mimicking media,” IEEE Trans. Ultrason. Ferroelectr. Freq. Control, vol. 64, no. 1, pp. 78–92, 2016.
  44. M. Buckland and F. Gey, “The relationship between recall and precision,” JASIST, vol. 45, no. 1, pp. 12–19, 1994.
  45. D. P. Huttenlocher, G. A. Klanderman, and W. J. Rucklidge, “Comparing images using the hausdorff distance,” IEEE Trans. Pattern. Anal. Mach. Intell., vol. 15, no. 9, pp. 850–863, 1993.
  46. T. Heimann, B. Van Ginneken, M. A. Styner, Y. Arzhaeva, V. Aurich, C. Bauer, A. Beck, C. Becker, R. Beichel, G. Bekes et al., “Comparison and evaluation of methods for liver segmentation from ct datasets,” IEEE Trans. Med. Imaging, vol. 28, no. 8, pp. 1251–1265, 2009.

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up