journal article·2023-12-20Open access

A Deep Neural Networks-Based Sound Speed Reconstruction with Enhanced Generalization by Training on a Natural Image Dataset

Yoshiki Watanabe, Takashi Azuma, Shu Takagi

Applied Sciences· Volume 14· Issue 1

Abstract

Sound speed reconstruction has been investigated for quantitative evaluation of tissue properties in breast examination. Full waveform inversion (FWI), a mainstream method for conventional sound speed reconstruction, is an iterative method that includes numerical simulation of wave propagation, resulting in high computational cost. In contrast, high-speed reconstruction of sound speed using a deep neural network (DNN) has been proposed in recent years. Although the generalization performance is highly dependent on the training data, how to generate data for sufficient generalization performance is still unclear. In this study, the quality and generalization performance of DNN-based sound speed reconstruction with a ring array transducer were evaluated on a natural image-derived dataset and a breast phantom dataset. The DNN trained on breast phantom data (BP-DNN) could not reconstruct the structures on natural image data with diverse structures. On the other hand, the DNN trained on natural image data (NI-DNN) successfully reconstructed the structures on both natural image and breast phantom test data. Furthermore, the NI-DNN successfully reconstructed tumour structures in the breast, while the BP-DNN overlooked them. From these results, it was demonstrated that natural image data enables DNNs to learn sound speed reconstruction with high generalization performance and high resolution.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Ultrasound Imaging and Elastography · Photoacoustic and Ultrasonic Imaging · AI in cancer detection

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Department of Bioengineering, School of Engineering, The University of Tokyo, Tokyo 113-8656, Japan

Lily MedTech Inc., Tokyo 113-8485, Japan

Department of Mechanical Engineering, School of Engineering, The University of Tokyo, Tokyo 113-8656, Japan

References (44)

Show source-provided references
1. Ultrasonography of soft tissue “oops lesions”10.14366/usg.14068 ↗
2. Biopsy rate and positive predictive value for breast cancer in BI-RADS category 4 breast lesions
3. The utility of breast cone-beam computed tomography, ultrasound, and digital mammography for detecting malignant breast tumors: A prospective study with 212 patients10.1016/j.ejrad.2015.11.029 ↗
4. Ultrasonographic findings of missed breast cancer: Pitfalls and pearls10.1007/s12282-013-0498-7 ↗
5. Rates of growth of human neoplasms: Part II10.1002/1096-9098(199601)61:1<68::AID-JSO2930610102>3.0.CO;2-E ↗
6. Ultrasound is at least as good as magnetic resonance imaging in predicting tumour size post-neoadjuvant chemotherapy in breast cancer10.1016/j.ejca.2015.10.010 ↗
7. Factors affecting pathologic complete response following neoadjuvant chemotherapy in breast cancer: Development and validation of a predictive nomogram10.1148/radiol.2021203871 ↗
8. Algebraic reconstruction of spatial distributions of acoustic velocities in tissue from their time-of-flight profiles10.1007/978-1-4615-8216-8_4 ↗
9. Detection of breast cancer with ultrasound tomography: First results with the Computed Ultrasound Risk Evaluation (CURE) prototype10.1118/1.2432161 ↗
10. Computerized tomography with ultrasound10.1109/PROC.1983.12591 ↗
11. Diffraction tomography I: The wave-equation10.1177/016173468000200302 ↗
12. A filtered backpropagation algorithm for diffraction tomography10.1177/016173468200400404 ↗
13. Reconstructive tomography with diffracting wavefields10.1088/0266-5611/2/2/008 ↗
14. Sandhu, G.Y., Li, C., Roy, O., Schmidt, S., and Duric, N. (2015). Frequency domain ultrasound waveform tomography: Breast imaging using a ring transducer. Phys. Med. Biol., 60.10.1088/0031-9155/60/14/5381 ↗
15. Roy, O., Jovanović, I., Hormati, A., Parhizkar, R., and Vetterli, M. (2010, January 13–18). Sound speed estimation using wave-based ultrasound tomography: Theory and GPU implementation. Proceedings of the SPIE Medical Imaging 2010, San Diego, CA, USA.10.1117/12.844691 ↗
16. Agudo, O.C., Guasch, L., Huthwaite, P., and Warner, M. (2017, January 1–3). 3D imaging of the breast using full-waveform inversion. Proceedings of the International Workshop on Medical Ultrasound Tomography, Speyer, Germany.10.1038/s41746-020-0240-8 ↗
17. Li, C., Sandhu, G.S., Roy, O., Duric, N., Allada, V., and Schmidt, S. (2014, January 15–20). Toward a practical ultrasound waveform tomography algorithm for improving breast imaging. Proceedings of the SPIE Medical Imaging 2014, San Diego, CA, USA.10.1117/12.2043686 ↗
18. Waveform inversion with source encoding for breast sound speed reconstruction in ultrasound computed tomography10.1109/TUFFC.2014.006788 ↗
19. Time domain reconstruction of sound speed and attenuation in ultrasound computed tomography using full wave inversion10.1121/1.4976688 ↗
20. Robust contrast source inversion method with automatic choice rule of regularization parameters for ultrasound waveform tomography10.7567/JJAP.55.07KB08 ↗
21. Robins, T., Camacho, J., Agudo, O.C., Herraiz, J.L., and Guasch, L. (2021). Deep-learning-driven full-waveform inversion for ultrasound breast imaging. Sensors, 21.10.3390/s21134570 ↗
22. A review on deep learning in medical image analysis10.1007/s13735-021-00218-1 ↗
23. Deep learning for tomographic image reconstruction10.1038/s42256-020-00273-z ↗
24. Model-data-driven image reconstruction with neural networks for ultrasound computed tomography breast imaging10.1016/j.neucom.2021.09.035 ↗
25. Prasad, S., and Almekkawy, M. (2022). Deepuct: Complex cascaded deep learning network for improved ultrasound tomography. Phys. Med. Biol., 67.10.1088/1361-6560/ac5296 ↗
26. A deep learning framework for single-sided sound speed inversion in medical ultrasound10.1109/TBME.2019.2931195 ↗
27. Farahani, A., Voghoei, S., Rasheed, K., and Arabnia, H.R. (2020, January 27–30). A brief review of domain adaptation. Proceedings of the ICDATA 2020 and IKE 2020, Las Vegas, NV, USA.
28. Deep Learning for Ultrasound Speed-of-Sound Reconstruction: Impacts of Training Data Diversity on Stability and Robustness
29. Lou, Y., Zhou, W., Matthews, T.P., Appleton, C.M., and Anastasio, M.A. (2017). Generation of anatomically realistic numerical phantoms for photoacoustic and ultrasonic breast imaging. J. Biomed. Opt., 22.10.1117/1.JBO.22.4.041015 ↗
30. Survey on deep learning with class imbalance10.1186/s40537-019-0192-5 ↗
31. Bria, A., Marrocco, C., and Tortorella, F. (2020). Addressing class imbalance in deep learning for small lesion detection on medical images. Comput. Biol. Med., 120.10.1016/j.compbiomed.2020.103735 ↗
32. The open images dataset v4: Unified image classification, object detection, and visual relationship detection at scale10.1007/s11263-020-01316-z ↗
33. Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., and Fei-Fei, L. (2009, January 20–25). Imagenet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.10.1109/CVPR.2009.5206848 ↗
34. Krizhevsky, A. (2009). Learning Multiple Layers of Features from Tiny Images, University of Toronto. Technical Report.
35. Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., and Zitnick, C.L. (2014, January 6–12). Microsoft coco: Common objects in context. Proceedings of the 13th European Conference on Computer Vision, Zurich, Switzerland.10.1007/978-3-319-10602-1_48 ↗
36. Cobbold, R.S. (2006). Foundations of Biomedical Ultrasound, Oxford University Press.10.1093/oso/9780195168310.001.0001 ↗
37. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference On Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
38. Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv.
39. Nonlinear total variation based noise removal algorithms10.1016/0167-2789(92)90242-F ↗
40. Tikhonov, A.N., and Arsenin, V.Y. (1977). Solution of Ill-Posed Problems, Wiley.
41. Hendrycks, D., and Gimpel, K. (2016). A baseline for detecting misclassified and out-of-distribution examples in neural networks. arXiv.
42. Lee, K., Lee, K., Lee, H., and Shin, J. (2018, January 3–8). A Simple Unified Framework for Detecting Out-of-distribution Samples and Adversarial Attacks. Proceedings of the 32rd Conference on Neural Information Processing Systems (NIPS’18), Montreal, QC, Canada.
43. Hsu, Y.C., Shen, Y., Jin, H., and Kira, Z. (2020, January 14–19). Generalized odin: Detecting out-of-distribution image without learning from out-of-distribution data. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.01096 ↗
44. Watanabe, Y., Azuma, T., and Takagi, S. (Neurocomputing, 2023). Array geometry dependency in sound speed reconstruction using Deep Neural Network, Neurocomputing, submitted.