SUPER-RESOLUTION METHODS FOR IMPROVING THE DETAILS OF ULTRASOUND IMAGES
DOI:
https://doi.org/10.32689/maup.it.2025.1.2Keywords:
ultrasound diagnostics, spatial resolution, clinical interpretability, transformer model, neural networkAbstract
The paper investigates the possibilities of using super-resolution methods to improve the spatial detail of ultrasound images in medical diagnostics. The relevance of the topic is due to the limitations of the hardware resolution of traditional ultrasound systems, which limits the accuracy of visualization of small anatomical structures and complicates the clinical diagnosis. The purpose of the article is to provide a comprehensive justification for the effectiveness and feasibility of introducing super-resolution methods into ultrasound diagnostics by systematically analyzing their technical characteristics, mechanisms for improving the quality of image reconstruction, and factors affecting the possibilities of clinical use. The research methodology is based on the generalization of modern approaches to the optimization of model architectures, preparation of input data, pre-training and clinical validation of results. Particular attention is paid to a comparative analysis of the advantages of transformable models, such as SwinIR, in the context of medical visualization. The paper characterizes the main factors of loss of spatial detail in ultrasound images, systematizes the classification of superresolution methods by technical parameters, analyzes organizational barriers to the implementation of algorithms in the clinical environment, and develops reasonable recommendations for the integration of such solutions into medical infrastructure. The study found that neural models of superresolution, in particular, architectures based on convolutional networks and transformers, have a high potential for improving the quality of ultrasound images without the need to upgrade hardware. The key problems associated with the lack of labeled ultrasound datasets, the difficulty of complying with DICOM and PACS standards, and the ethical aspects of medical liability are identified. The paper proves that successful implementation of superresolution methods requires adaptation of algorithms to the specifics of medical systems, gradual integration into existing software solutions, maintaining physician control, and ensuring compliance with regulatory requirements. The scientific novelty is a comprehensive analysis of ways to improve the efficiency of superresolution algorithms in ultrasound imaging and to determine the directions of their optimal use in medical practice.
References
Cammarasana S., Nicolardi P., Patanè G. Super-resolution of 2D ultrasound images and videos. Medical & Biological Engineering & Computing. 2023. Vol. 61, № 11. P. 2511–2526. DOI: https://doi.org/10.1007/s11517-023-02818-x (date of access: 25.03.2025).
Chen Q. et al. Current Development and Applications of Super-Resolution Ultrasound Imaging. Sensors. 2021. Vol. 21, no. 7. P. 2417. URL: https://doi.org/10.3390/s21072417 (date of access: 25.03.2025).
Choi W., Kim M., HakLee J., Kim J., BeomRa J. Deep CNN-Based Ultrasound Super-Resolution for High-Speed High-Resolution B-Mode Imaging. 2018 IEEE International Ultrasonics Symposium (IUS). 2018. P. 1–4. DOI: https://doi.org/10.1109/ULTSYM.2018.8580032 (date of access: 25.03.2025).
Coinmonks on Medium: website. 2020. URL: https://medium.com/coinmonks/review-srcnn-super-resolution-3cb3a4f67a7c (date of access: 25.03.2025).
Couture O. et al. Ultrasound Localization Microscopy and Super-Resolution: A State of the Art. IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control. 2018. Vol. 65, no. 8. P. 1304–1320. URL: https://doi.org/10.1109/tuffc.2018.2850811 (date of access: 25.03.2025).
Ghosh D., Hoyt K. Advancements in Three‐Dimensional Super‐Resolution Ultrasound Imaging. Journal of Ultrasound in Medicine. 2025. URL: https://doi.org/10.1002/jum.16682 (date of access: 25.03.2025).
Hosseinpour M., Behnam H., Shojaeifard M. Temporal super resolution of ultrasound images using compressive sensing. Biomedical Signal Processing and Control. 2019. Vol. 52. P. 53–68. URL: https://doi.org/10.1016/j.bspc.2019.03.003 (date of access: 25.03.2025).
Liang J., Cao J., Sun G., Zhang K., Van Gool L., Timofte R. SwinIR: Image restoration using Swin Transformer. Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021. P. 1833–1844. DOI: https://doi.org/10.48550/arXiv.2108.10257 (date of access: 25.03.2025).
Liu H. et al. Progressive Residual Learning with Memory Upgrade for Ultrasound Image Blind Super-resolution. IEEE Journal of Biomedical and Health Informatics. 2022. P. 1. URL: https://doi.org/10.1109/jbhi.2022.3142076 (date of access: 25.03.2025).
Liu H., Liu J., Hou S., Tao T., Han J. Perception consistency ultrasound image super-resolution via self-supervised CycleGAN. Neural Computing and Applications. 2023. Vol. 35, № 5. P. 12331–12341. DOI: https://doi.org/10.1007/s00521-020-05687-9 (date of access: 25.03.2025).
Liu T., Han S., Xie L., Xing W., Liu C., Li B., Ta D. Super-resolution reconstruction of ultrasound image using a modified diffusion model. Physics in Medicine & Biology. 2024. Vol. 69, № 12. Article ID 125026. DOI: https://doi.org/10.1088/1361-6560/ad4086 (date of access: 25.03.2025).
Radiological Society of North America (RSNA): website. 2024. URL: https://www.rsna.org/annual-meeting (date of access: 25.03.2025).
Sawant A., Kulkarni S. Ultrasound image enhancement using super resolution. Biomedical Engineering Advances. 2022. Vol. 3, № 1. Article ID 100039. DOI: https://doi.org/10.1016/j.bea.2022.100039 (date of access: 25.03.2025).
Shu Y., Han C., Lv M., Liu X. Fast Super-Resolution Ultrasound Imaging With Compressed Sensing Reconstruction Method and Single Plane Wave Transmission. IEEE Access. 2018. Vol. 6, № 1. P. 39298–39306. DOI: https://doi.org/10.1109/ACCESS.2018.2853194 (date of access: 25.03.2025).
Song H., Yang Y. Super-resolution visualization of subwavelength defects via deep learning-enhanced ultrasonic beamforming: A proof-of-principle study. NDT & E International. 2020. Vol. 116. P. 102344. URL: https://doi.org/10.1016/j.ndteint.2020.102344 (date of access: 25.03.2025).
Temiz H., Bilge H. S. Super Resolution of B-Mode Ultrasound Images With Deep Learning. IEEE Access. 2020. Vol. 8, № 1. P. 78808–78820. DOI: https://doi.org/10.1109/ACCESS.2020.2990344 (date of access: 25.03.2025).
van Sloun R. J. et al. Super-resolution Ultrasound Localization Microscopy through Deep Learning. IEEE Transactions on Medical Imaging. 2020. P. 1. URL: https://doi.org/10.1109/tmi.2020.3037790 (date of access: 25.03.2025).
Zhang Y., Lu S., Peng C., Zhou S., Campo I., Bertolotto M., Li Q., Wang Z., Xu D., Wang Y., Xu J., Wu Q., Hu X., Zheng W., Zhou J. Deep learning-based super-resolution US radiomics to differentiate testicular seminoma. Oncology. 2023. Vol. 13, № 1. Article ID 1090823.