Deep Learning for Point-of-Care Ultrasound Image Quality Enhancement: A Review
Source abstract
Abstract
The popularity of handheld devices for point-of-care ultrasound (POCUS) has increased in recent years due to their portability and cost-effectiveness. However, POCUS has the drawback of lower imaging quality compared to conventional ultrasound because of hardware limitations. Improving the quality of POCUS through post-image processing would therefore be beneficial, with deep learning approaches showing promise in this regard. This review investigates the state-of-the-art progress of image enhancement using deep learning suitable for POCUS applications. A systematic search was conducted from January 2024 to February 2024 on PubMed and Scopus. From the 457 articles that were found, the full text was retrieved for 69 articles. From this selection, 15 articles were identified addressing multiple quality enhancement aspects. A disparity in the baseline performance of the low-quality input images was seen across these studies, ranging between 8.65 and 29.24 dB for the Peak Signal-to-Noise Ratio (PSNR) and between 0.03 an 0.71 for the Structural Similarity Index Measure (SSIM). In six studies, where both the PSNR and the SSIM metrics were reported for the baseline and the generated images, mean differences of 6.60 (SD ± 2.99) and 0.28 (SD ± 0.15) were observed for the PSNR and SSIM, respectively. The reported performance outcomes demonstrate the potential of deep learning-based image enhancement for POCUS. However, variability in the extent of the performance gain across datasets and articles was notable, and the heterogeneity across articles makes quantifying the exact improvements challenging.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Photoacoustic and Ultrasonic Imaging · Ultrasound Imaging and Elastography · Ultrasound and Hyperthermia Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Image-Guided Surgery, Department of Surgery, Netherlands Cancer Institute, Plesmanlaan 121, 1066 CX Amsterdam, The Netherlands
Technical Medicine, Faculty of Mechanical, Maritime, and Materials Engineering (3ME), Delft University of Technology, Mekelweg 2, 2628 CD Delft, The Netherlands
Funding
Dutch Cancer Society · Dutch Ministry of Health, Welfare and Sport
References (100+)
Show source-provided references
1. The utility of point of care ultrasonography (POCUS)10.1016/j.amsu.2021.102982 ↗
2. Utility of hand-held echocardiography in outpatient pediatric cardiology management10.1007/s00246-014-0940-4 ↗
3. Point of care ultrasound: The next evolution of medical education10.21037/atm.2020.04.41 ↗
4. Comparison of a pocket-size ultrasound device with a premium ultrasound machine: Diagnostic value and time required in bedside ultrasound examination10.1007/s00261-015-0406-z ↗
5. Evidence basis for a point-of-care ultrasound examination to refine referral for outpatient echocardiography10.1016/j.amjmed.2018.10.012 ↗
6. Image Quality Improvement of Hand-Held Ultrasound Devices with a Two-Stage Generative Adversarial Network10.1109/TBME.2019.2912986 ↗
7. Out of hospital point of care ultrasound: Current use models and future directions10.1007/s00068-015-0494-z ↗
8. Point of care ultrasound (POCUS) telemedicine project in rural Nicaragua and its impact on patient management10.1007/s40477-014-0126-1 ↗
9. Trends in Ultrasound Use in Low and Middle Income Countries: A Systematic Review10.21106/ijma.294 ↗
10. The use of portable ultrasound devices in low- and middle-income countries: A systematic review of the literature10.1111/tmi.12657 ↗
11. Cost-effective remote iPhone-teathered telementored trauma telesonography10.1097/TA.0b013e3181e61ea9 ↗
12. Hand-held cardiac ultrasound screening performed by family doctors with remote expert support interpretation10.1136/heartjnl-2015-308421 ↗
13. Ultrasound Image Quality Comparison Between a Handheld Ultrasound Transducer and Mid-Range Ultrasound Machine10.24908/pocus.v7i1.15052 ↗
14. Handheld Ultrasound Video High-Quality Reconstruction Using a Low-Rank Representation Multipathway Generative Adversarial Network10.1109/TNNLS.2020.3025380 ↗
15. Khan, S., Huh, J., and Ye, J.C. (2021). Contrast and resolution improvement of pocus using self-consistent cyclegan. Proceedings of the MICCAI Workshop on Domain Adaptation and Representation Transfer, Springer.10.1007/978-3-030-87722-4_15 ↗
16. Cardiac point-of-care to cart-based ultrasound translation using constrained CycleGAN10.1007/s11548-020-02141-y ↗
17. Henderson, R., and Murphy, S. (2017). Portability Enhancing Hardware for a Portable Ultrasound System. 2017. (No. 9,629,606), US Patent.
18. Real-time 3-D ultrasound imaging using sparse synthetic aperture beamforming10.1109/58.710573 ↗
19. The delay multiply and sum beamforming algorithm in ultrasound B-mode medical imaging10.1109/TMI.2014.2371235 ↗
20. Ultrasound image enhancement: A review10.1016/j.bspc.2012.02.002 ↗
21. An overview of deep learning in medical imaging10.1016/j.imu.2021.100723 ↗
22. A review on deep learning in medical image reconstruction10.1007/s40305-019-00287-4 ↗
23. Medical Image Processing based on Generative Adversarial Networks: A Systematic Review10.2174/0115734056258198230920042358 ↗
24. A deep journey into image enhancement: A survey of current and emerging trends10.1016/j.inffus.2022.12.012 ↗
25. The PRISMA 2020 statement: An updated guideline for reporting systematic reviews10.1136/bmj.n71 ↗
26. Chakraborty, C., Bhattacharya, M., Pal, S., and Lee, S.S. (2023). From machine learning to deep learning: An advances of the recent data-driven paradigm shift in medicine and healthcare. Curr. Res. Biotechnol., 7.10.1016/j.crbiot.2023.100164 ↗
27. Makwana, G., Yadav, R.N., and Gupta, L. (2022). Analysis of Various Noise Reduction Techniques for Breast Ultrasound Image Enhancement. Internet of Things and Its Applications: Select Proceedings of ICIA 2020, Springer.10.1007/978-981-16-7637-6_27 ↗
28. Despeckling of medical ultrasound images10.1109/TUFFC.2006.1588392 ↗
29. Resolution in ultrasound imaging10.1093/bjaceaccp/mkr030 ↗
30. Image quality assessment through FSIM, SSIM, MSE and PSNR—A comparative study10.4236/jcc.2019.73002 ↗
31. Hore, A., and Ziou, D. (2010, January 23–26). Image quality metrics: PSNR vs. SSIM. Proceedings of the 2010 20th International Conference on Pattern Recognition, Istanbul, Turkey.10.1109/ICPR.2010.579 ↗
32. Awasthi, N., van Anrooij, L., Jansen, G., Schwab, H.M., Pluim, J.P., and Lopata, R.G. (2022). Bandwidth Improvement in Ultrasound Image Reconstruction Using Deep Learning Techniques. Healthcare, 11.10.3390/healthcare11010123 ↗
33. High-quality plane wave compounding using convolutional neural networks10.1109/TUFFC.2017.2736890 ↗
34. Fast multi-focus ultrasound image recovery using generative adversarial networks10.1109/TCI.2020.3019137 ↗
35. Guo, B., Zhang, B., Ma, Z., Li, N., Bao, Y., and Yu, D. High-quality plane wave compounding using deep learning for hand-held ultrasound devices. Proceedings 16, Proceedings of the Advanced Data Mining and Applications: 16th International Conference, ADMA 2020, Foshan, China, 12–14 November 2020, Springer.10.1007/978-3-030-65390-3_41 ↗
36. Huang, C.Y., Chen, O.T.C., Wu, G.Z., Chang, C.C., and Hu, C.L. (2018, January 22–25). Ultrasound imaging improved by the context encoder reconstruction generative adversarial network. Proceedings of the 2018 IEEE International Ultrasonics Symposium, Kobe, Japan.10.1109/ULTSYM.2018.8579658 ↗
37. Reconstruction for diverging-wave imaging using deep convolutional neural networks10.1109/TUFFC.2020.2986166 ↗
38. Lyu, Y., Jiang, X., Xu, Y., Hou, J., Zhao, X., and Zhu, X. (2023). ARU-GAN: U-shaped GAN based on Attention and Residual connection for super-resolution reconstruction. Comput. Biol. Med., 164.10.1016/j.compbiomed.2023.107316 ↗
39. Moinuddin, M., Khan, S., Alsaggaf, A.U., Abdulaal, M.J., Al-Saggaf, U.M., and Ye, J.C. (2022). Medical ultrasound image speckle reduction and resolution enhancement using texture compensated multi-resolution convolution neural network. Front. Physiol., 13.10.3389/fphys.2022.961571 ↗
40. Monkam, P., Lu, W., Jin, S., Shan, W., Wu, J., Zhou, X., Tang, B., Zhao, H., Zhang, H., and Ding, X. (2023). US-Net: A lightweight network for simultaneous speckle suppression and texture enhancement in ultrasound images. Comput. Biol. Med., 152.10.1016/j.compbiomed.2022.106385 ↗
41. Plane-Wave Image Reconstruction via Generative Adversarial Network and Attention Mechanism10.1109/TIM.2021.3087819 ↗
42. Zhang, X., Li, J., He, Q., Zhang, H., and Luo, J. (2018, January 22–25). High-quality reconstruction of plane-wave imaging using generative adversarial network. Proceedings of the 2018 IEEE International Ultrasonics Symposium, Kobe, Japan.10.1109/ULTSYM.2018.8579877 ↗
43. Zhou, Z., Wang, Y., Yu, J., Guo, W., and Fang, Z. Super-resolution reconstruction of plane-wave ultrasound imaging based on the improved CNN method. Proceedings of the VipIMAGE 2017: Proceedings of the VI ECCOMAS Thematic Conference on Computational Vision and Medical Image Processing Porto, Portugal, 18–20 October 2017, Springer.10.1007/978-3-319-68195-5_12 ↗
44. High Spatial-Temporal Resolution Reconstruction of Plane-Wave Ultrasound Images with a Multichannel Multiscale Convolutional Neural Network10.1109/TUFFC.2018.2865504 ↗
45. High Frequency Ultrasound Image Recovery Using Tight Frame Generative Adversarial Networks
46. Goudarzi, S., Asif, A., and Rivaz, H. (2019, January 8–11). Multi-focus ultrasound imaging using generative adversarial networks. Proceedings of the 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), Venice, Italy.10.1109/ISBI.2019.8759216 ↗
47. Lu, J., and Liu, W. (2018, January 27–29). Unsupervised super-resolution framework for medical ultrasound images using dilated convolutional neural networks. Proceedings of the 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC), Chongqing, China.10.1109/ICIVC.2018.8492821 ↗
48. Li, Y., Lu, W., Monkam, P., and Wang, Y. (2023, January 3–8). IA-Noise2Noise: An Image Alignment Strategy for Echocardiography Despeckling. Proceedings of the 2023 IEEE International Ultrasonics Symposium, Montreal, QC, Canada.10.1109/IUS51837.2023.10307810 ↗
49. Attention gated encoder-decoder for ultrasonic signal denoising
50. Basile, M., Gibiino, F., Cavazza, J., Semplici, P., Bechini, A., and Vanello, N. (2023, January 28–29). Blind Approach Using Convolutional Neural Networks to a New Ultrasound Image Denoising Task. Proceedings of the 2023 IEEE International Workshop on Biomedical Applications, Technologies and Sensors, BATS 2023, Catanzaro, Italy.10.1109/BATS59463.2023.10303265 ↗
51. Removal of Speckle Noises from Ultrasound Images Using Parallel Convolutional Neural Network10.1007/s00034-023-02349-8 ↗
52. Gan, J., Wang, L., Liu, Z., and Wang, J. (2023, January 25–27). Multi-scale ultrasound image denoising algorithm based on deep learning model for super-resolution reconstruction. Proceedings of the ACM International Conference Proceeding Series, Guangzhou, China.10.1145/3622896.3622898 ↗
53. Asgariandehkordi, H., Goudarzi, S., Basarab, A., and Rivaz, H. (2023, January 3–8). Deep Ultrasound Denoising Using Diffusion Probabilistic Models. Proceedings of the IEEE International Ultrasonics Symposium, Montreal, QC, Canada.10.1109/IUS51837.2023.10306544 ↗
54. Liu, J., Li, C., Liu, L., Chen, H., Han, H., Zhang, B., and Zhang, Q. (2023). Speckle noise reduction for medical ultrasound images based on cycle-consistent generative adversarial network. Biomed. Signal Process. Control, 86.10.1016/j.bspc.2023.105150 ↗
55. Deep Learning-Based Ultrasound Image Despeckling by Noise Model Estimation
56. Senthamizh Selvi, R., Suruthi, S., Samyuktha Shrruthi, K.R., Varsha, B., Saranya, S., and Babu, B. (2023, January 20–22). Ultrasound Image Denoising Using Cascaded Median Filter and Autoencoder. Proceedings of the 4th International Conference on Smart Electronics and Communication, ICOSEC 2023, Trichy, India.
57. Mikaeili, M., and Bilge, H.S. (2023, January 10–12). Evaluating Deep Neural Network Models on Ultrasound Single Image Super Resolution. Proceedings of the TIPTEKNO 2023—Medical Technologies Congress, Famagusta, Cyprus.10.1109/TIPTEKNO59875.2023.10359188 ↗
58. Perception consistency ultrasound image super-resolution via self-supervised CycleGAN10.1007/s00521-020-05687-9 ↗
59. Advanced Image Processing Techniques for Ultrasound Images using Multiscale Self Attention CNN10.1007/s11063-023-11404-z ↗
60. Ultrasound Speckle Filtering Using Deep Learning10.1007/978-3-031-49404-8_28 ↗
61. Li, Y., Zeng, X., Dong, Q., and Wang, X. (2023). RED-MAM: A residual encoder-decoder network based on multi-attention fusion for ultrasound image denoising. Biomed. Signal Process. Control, 79.10.1016/j.bspc.2022.104062 ↗
62. FDDL-Net: Frequency domain decomposition learning for speckle reduction in ultrasound images10.1007/s11042-022-13481-z ↗
63. Removal of speckle noises from ultrasound images using five different deep learning networks
64. Texture-driven super-resolution of ultrasound images using optimized deep learning model10.1080/13682199.2023.2218224 ↗
65. Speckle Noise Suppression in Ultrasound Images Using Modular Neural Networks10.32604/iasc.2023.022631 ↗
66. Kalaiyarasi, M., Janaki, R., Sampath, A., Ganage, D., Chincholkar, Y.D., and Budaraju, S. (2023). Non-additive noise reduction in medical images using bilateral filtering and modular neural networks. Soft Comput., 1–10.10.1007/s00500-023-08968-2 ↗
67. Sawant, A., Kasar, M., Saha, A., Gore, S., Birwadkar, P., and Kulkarni, S. (2022, January 25–26). Medical Image De-Speckling Using Fusion of Diffusion-Based Filters And CNN. Proceedings of the 8th International Conference on Advanced Computing and Communication Systems, ICACCS 2022, Coimbatore, India.10.1109/ICACCS54159.2022.9785110 ↗
68. Dutta, S., Georgeot, B., Kouame, D., Garcia, D., and Basarab, A. (2022, January 10–13). Adaptive Contrast Enhancement of Cardiac Ultrasound Images using a Deep Unfolded Many-Body Quantum Algorithm. Proceedings of the IEEE International Ultrasonics Symposium (IUS), Venice, Italy.10.1109/IUS54386.2022.9958691 ↗
69. Sanjeevi, G., Krishnan Pathinarupothi, R., Uma, G., and Madathil, T. (2022, January 7–9). Deep Learning Pipeline for Echocardiogram Noise Reduction. Proceedings of the 2022 IEEE 7th International conference for Convergence in Technology, I2CT 2022, Mumbai, India.10.1109/I2CT54291.2022.9825236 ↗
70. An efficient transfer learning-based Super-Resolution model for Medical Ultrasound Image10.1088/1742-6596/1964/6/062050 ↗
71. Chennakeshava, N., Luijten, B., Drori, O., Mischi, M., Eldar, Y.C., and Van Sloun, R.J.G. (2020, January 7–11). High resolution plane wave compounding through deep proximal learning. Proceedings of the IEEE International Ultrasonics Symposium (IUS), Las Vegas, NV, USA.10.1109/IUS46767.2020.9251399 ↗
72. Feature-Guided CNN for Denoising Images from Portable Ultrasound Devices10.1109/ACCESS.2021.3059003 ↗
73. Jarosik, P., Lewandowski, M., Klimonda, Z., and Byra, M. (2021, January 11–16). Pixel-Wise Deep Reinforcement Learning Approach for Ultrasound Image Denoising. Proceedings of the IEEE International Ultrasonics Symposium (IUS), Xi’an, China.10.1109/IUS52206.2021.9593591 ↗
74. Adaptive comprehensive particle swarm optimisation-based functional-link neural network filtre model for denoising ultrasound images10.1049/ipr2.12100 ↗
75. Deep Learning-Based Wavelet Threshold Function Optimization on Noise Reduction in Ultrasound Images
76. Kokil, P., and Sudharson, S. (2020). Despeckling of clinical ultrasound images using deep residual learning. Comput. Methods Programs Biomed., 194.10.1016/j.cmpb.2020.105477 ↗
77. Ultrasound image de-speckling by a hybrid deep network with transferred filtering and structural prior10.1016/j.neucom.2020.09.002 ↗
78. Ma, Y., Yang, F., and Basu, A. (2021, January 10–15). Edge-guided CNN for denoising images from portable ultrasound devices. Proceedings of the International Conference on Pattern Recognition, Milan, Italy.10.1109/ICPR48806.2021.9412758 ↗
79. Real-time ultrasound image despeckling using mixed-attention mechanism based residual UNet10.1109/ACCESS.2020.3034230 ↗
80. Noise Reduction Using OBNLM Filter and Deep Learning for Polycystic Ovary Syndrome Ultrasound Images
81. Deep Belief Network for the Enhancement of Ultrasound Images with Pelvic Lesions
82. Singh, P., Mukundan, R., and De Ryke, R. (2019, January 16–18). Feature Enhancement of Medical Ultrasound Scans Using Multifractal Measures. Proceedings of the 2019 IEEE International Conference on Signals and Systems, ICSigSys 2019, Bandung, Indonesia.10.1109/ICSIGSYS.2019.8811087 ↗
83. Choi, W., Kim, M., Haklee, J., Kim, J., and Beomra, J. (2018, January 22–25). Deep CNN-Based Ultrasound Super-Resolution for High-Speed High-Resolution B-Mode Imaging. Proceedings of the IEEE International Ultrasonics Symposium (IUS), Kobe, Japan.10.1109/ULTSYM.2018.8580032 ↗
84. Speckle reduction of medical ultrasound images using deep learning with fully convolutional network10.35848/1347-4065/ab80a5 ↗
85. Super Resolution of B-Mode Ultrasound Images with Deep Learning10.1109/ACCESS.2020.2990344 ↗
86. Exploring multi-scale deep encoder-decoder and patchgan for perceptual ultrasound image super-resolution10.1007/978-981-15-7670-6_5 ↗
87. Ultrasound image enhancement using structure oriented adversarial network10.1109/LSP.2018.2858147 ↗
88. Mishra, D., Tyagi, S., Chaudhury, S., Sarkar, M., and Singhsoin, A. (2018, January 20–24). Despeckling CNN with Ensembles of Classical Outputs. Proceedings of the International Conference on Pattern Recognition, Beijing, China.10.1109/ICPR.2018.8545031 ↗
89. Oliveira-Saraiva, D., Mendes, J., Leote, J., Gonzalez, F.A., Garcia, N., Ferreira, H.A., and Matela, N. (2023). Make It Less Complex: Autoencoder for Speckle Noise Removal-Application to Breast and Lung Ultrasound. J. Imaging, 9.10.3390/jimaging9100217 ↗
90. Vimala, B.B., Srinivasan, S., Mathivanan, S.K., Muthukumaran, V., Babu, J.C., Herencsar, N., and Vilcekova, L. (2023). Image Noise Removal in Ultrasound Breast Images Based on Hybrid Deep Learning Technique. Sensors, 23.10.3390/s23031167 ↗
91. Sineesh, A., Shankar, M.R., Hareendranathan, A., Panicker, M.R., and Palanisamy, P. (2023). Single Image based Super Resolution Ultrasound Imaging Using Residual Learning of Wavelet Features. Annu. Int. Conf. IEEE Eng. Med. Biol. Soc., 2023.10.1109/EMBC40787.2023.10340196 ↗
92. Li, X., Wang, Y., Zhao, Y., and Wei, Y. (2022). Fast Speckle Noise Suppression Algorithm in Breast Ultrasound Image Using Three-Dimensional Deep Learning. Front. Physiol., 13.10.3389/fphys.2022.880966 ↗
93. Tamang, L.D., and Kim, B.W. (2022). Super-Resolution Ultrasound Imaging Scheme Based on a Symmetric Series Convolutional Neural Network. Sensors, 22.10.3390/s22083076 ↗
94. USDL: Inexpensive Medical Imaging Using Deep Learning Techniques and Ultrasound Technology
95. Yu, H., Ding, M., Zhang, X., and Wu, J. (2018). PCANet based nonlocal means method for speckle noise removal in ultrasound images. PLoS ONE, 13.10.1371/journal.pone.0205390 ↗
96. Bayesian Framework-Based Adaptive Hybrid Filtering for Speckle Noise Reduction in Ultrasound Images Via Lion Plus FireFly Algorithm10.1007/s10278-021-00517-3 ↗
97. Liebgott, H., Rodriguez-Molares, A., Cervenansky, F., Jensen, J.A., and Bernard, O. (2016, January 18–21). Plane-wave imaging challenge in medical ultrasound. Proceedings of the 2016 IEEE International Ultrasonics Symposium (IUS), Tours, France.10.1109/ULTSYM.2016.7728908 ↗
98. Automated breast ultrasound lesions detection using convolutional neural networks10.1109/JBHI.2017.2731873 ↗
99. Xia, C., Li, J., Chen, X., Zheng, A., and Zhang, Y. (2017, January 21–26). What is and what is not a salient object? Learning salient object detector by ensembling linear exemplar regressors. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.468 ↗
100. van den Heuvel, T.L., de Bruijn, D., de Korte, C.L., and Ginneken, B.v. (2018). Automated measurement of fetal head circumference using 2D ultrasound images. PLoS ONE, 13.10.1371/journal.pone.0200412 ↗