Print Email Facebook Twitter 3-D contrast enhanced ultrasound imaging of an in vivo chicken embryo with a sparse array and deep learning based adaptive beamforming Title 3-D contrast enhanced ultrasound imaging of an in vivo chicken embryo with a sparse array and deep learning based adaptive beamforming Author Ossenkoppele, B.W. (TU Delft ImPhys/Imaging Physics; TU Delft ImPhys/Medical Imaging) Wei, Luxi (Erasmus MC) Luijten, Ben (Eindhoven University of Technology) Vos, H.J. (TU Delft ImPhys/Medical Imaging; Erasmus MC) de Jong, N. (TU Delft ImPhys/Medical Imaging; Erasmus MC) Van Sloun, Ruud J.G. (Eindhoven University of Technology; Philips Research) Verweij, M.D. (TU Delft ImPhys/Medical Imaging; Erasmus MC) Department ImPhys/Imaging Physics Date 2022 Abstract 3-D contrast enhanced ultrasound enables better visualization of inherently 3-D vascular geometries compared to an intersecting plane. Additionally, it would allow the application of motion correction techniques for all directions. Both contrast detection and motion correction work better on high-frame rate data. However high-frame rate 3-D ultrasound imaging with dense matrix arrays is challenging to realize. Sparse arrays alleviate some of the limitations in cable count and data rate that fully populated arrays encounter, but their increased level of secondary lobes negatively impacts image contrast. Meanwhile the use of unfocused transmit beams needed to achieve high-frame rates negatively impacts resolution. Here we propose to use adaptive beamforming by deep learning (ABLE) to improve the image quality of contrast enhanced ultrasound images acquired with a sparse spiral array. We train the neural network on simulated data and evaluate simulated images and in vivo images of an ex ovo chicken embryo. ABLE improved resolution compared to delay-and-sum (DAS) and spatial coherence (SC) beamforming on the simulated and in vivo data. The qualitative improvements persist after histogram matching, indicating that the image quality improvement of the ABLE images was not purely due to dynamic range stretching. Subject beamformingcontrast enhanced ultrasounddeep learningsparse arrayspiral array To reference this document use: http://resolver.tudelft.nl/uuid:4ae5e757-eaa2-4aae-825a-ddca25448182 DOI https://doi.org/10.1109/IUS54386.2022.9957383 Publisher IEEE Embargo date 2023-07-01 ISBN 9781665466578 Source IUS 2022 - IEEE International Ultrasonics Symposium Event 2022 IEEE International Ultrasonics Symposium, IUS 2022, 2022-10-10 → 2022-10-13, Venice, Italy Series IEEE International Ultrasonics Symposium, IUS, 1948-5719, 2022-October Bibliographical note Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. Part of collection Institutional Repository Document type conference paper Rights © 2022 B.W. Ossenkoppele, Luxi Wei, Ben Luijten, H.J. Vos, N. de Jong, Ruud J.G. Van Sloun, M.D. Verweij Files PDF 3_D_contrast_enhanced_ult ... orming.pdf 2.46 MB Close viewer /islandora/object/uuid:4ae5e757-eaa2-4aae-825a-ddca25448182/datastream/OBJ/view