Abstract
AbstractUltrasound images are widespread in medical diagnosis for muscle-skeletal, cardiac, and obstetrical diseases, due to the efficiency and non-invasiveness of the acquisition methodology. However, ultrasound acquisition introduces noise in the signal, which corrupts the resulting image and affects further processing steps, e.g. segmentation and quantitative analysis. We define a novel deep learning framework for the real-time denoising of ultrasound images. Firstly, we compare state-of-the-art methods for denoising (e.g. spectral, low-rank methods) and select WNNM (Weighted Nuclear Norm Minimisation) as the best denoising in terms of accuracy, preservation of anatomical features, and edge enhancement. Then, we propose a tuned version of WNNM (tuned-WNNM) that improves the quality of the denoised images and extends its applicability to ultrasound images. Through a deep learning framework, the tuned-WNNM qualitatively and quantitatively replicates WNNM results in real-time. Finally, our approach is general in terms of its building blocks and parameters of the deep learning and high-performance computing framework; in fact, we can select different denoising algorithms and deep learning architectures.
Publisher
Springer Science and Business Media LLC
Subject
Computer Science Applications,Biomedical Engineering
Reference75 articles.
1. Esaote mylab-9. https://www.esaote.com/ultrasound/ultrasound-systems/p/mylab-9/. Accessed: 2022-02-11
2. Philips epiq elite. https://www.philips.it/c-dam/b2bhc/it/events/siumb/Epiq_Elite_GISS_6.0_452299156181_LR200-vb.pdf. Accessed: 2022-02-11
3. Philips xres pro. https://www.usa.philips.com/healthcare/education-resources/technologies/ultrasound/xres. Accessed: 2022-02-11
4. Aharon M, Elad M, Bruckstein A (2006) K-svd: An algorithm for designing overcomplete dictionaries for sparse representation. IEEE Trans on Signal Processing 54(11):4311–4322
5. Ahn B, Cho NI (2017) Block-matching convolutional neural network for image denoising. arXiv:1704.00524
Cited by
6 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献