Complex Convolutional Neural Networks for Ultrafast Ultrasound Imaging Reconstruction From In-Phase/Quadrature Signal.
Saved in:
| Title: | Complex Convolutional Neural Networks for Ultrafast Ultrasound Imaging Reconstruction From In-Phase/Quadrature Signal. |
|---|---|
| Authors: | Lu, Jingfeng1 (AUTHOR) jingfeng.lu@hit.edu.cn, Millioz, Fabien2 (AUTHOR), Garcia, Damien2 (AUTHOR), Salles, Sebastien2 (AUTHOR), Ye, Dong3 (AUTHOR) yedong@hit.edu.cn, Friboulet, Denis2 (AUTHOR) |
| Source: | IEEE Transactions on Ultrasonics Ferroelectrics & Frequency Control. Feb2022, Vol. 9 Issue 2, p592-603. 12p. |
| Subjects: | Convolutional neural networks, Ultrasonic imaging, Image reconstruction, Deep learning, Radio frequency |
| Abstract: | Ultrafast ultrasound imaging remains an active area of interest in the ultrasound community due to its ultrahigh frame rates. Recently, a wide variety of studies based on deep learning have sought to improve ultrafast ultrasound imaging. Most of these approaches have been performed on radio frequency (RF) signals. However, in- phase/quadrature (I/Q) digital beamformers are now widely used as low-cost strategies. In this work, we used complex convolutional neural networks for reconstruction of ultrasound images from I/Q signals. We recently described a convolutional neural network architecture called ID-Net, which exploited an inception layer designed for reconstruction of RF diverging-wave ultrasound images. In the present study, we derive the complex equivalent of this network, i.e., complex-valued inception for diverging-wave network (CID-Net) that operates on I/Q data. We provide experimental evidence that CID-Net provides the same image quality as that obtained from RF-trained convolutional neural networks, i.e., using only three I/Q images, CID-Net produces high-quality images that can compete with those obtained by coherently compounding 31 RF images. Moreover, we show that CID-Net outperforms the straightforward architecture that consists of processing real and imaginary parts of the I/Q signal separately, which thereby indicates the importance of consistently processing the I/Q signals using a network that exploits the complex nature of such signals. [ABSTRACT FROM AUTHOR] |
| Copyright of IEEE Transactions on Ultrasonics Ferroelectrics & Frequency Control is the property of IEEE and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 154974772 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Complex Convolutional Neural Networks for Ultrafast Ultrasound Imaging Reconstruction From In-Phase/Quadrature Signal. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Lu%2C+Jingfeng%22">Lu, Jingfeng</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> jingfeng.lu@hit.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Millioz%2C+Fabien%22">Millioz, Fabien</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Garcia%2C+Damien%22">Garcia, Damien</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Salles%2C+Sebastien%22">Salles, Sebastien</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Ye%2C+Dong%22">Ye, Dong</searchLink><relatesTo>3</relatesTo> (AUTHOR)<i> yedong@hit.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Friboulet%2C+Denis%22">Friboulet, Denis</searchLink><relatesTo>2</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22IEEE+Transactions+on+Ultrasonics+Ferroelectrics+%26+Frequency+Control%22">IEEE Transactions on Ultrasonics Ferroelectrics & Frequency Control</searchLink>. Feb2022, Vol. 9 Issue 2, p592-603. 12p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Convolutional+neural+networks%22">Convolutional neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Ultrasonic+imaging%22">Ultrasonic imaging</searchLink><br /><searchLink fieldCode="DE" term="%22Image+reconstruction%22">Image reconstruction</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Radio+frequency%22">Radio frequency</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Ultrafast ultrasound imaging remains an active area of interest in the ultrasound community due to its ultrahigh frame rates. Recently, a wide variety of studies based on deep learning have sought to improve ultrafast ultrasound imaging. Most of these approaches have been performed on radio frequency (RF) signals. However, in- phase/quadrature (I/Q) digital beamformers are now widely used as low-cost strategies. In this work, we used complex convolutional neural networks for reconstruction of ultrasound images from I/Q signals. We recently described a convolutional neural network architecture called ID-Net, which exploited an inception layer designed for reconstruction of RF diverging-wave ultrasound images. In the present study, we derive the complex equivalent of this network, i.e., complex-valued inception for diverging-wave network (CID-Net) that operates on I/Q data. We provide experimental evidence that CID-Net provides the same image quality as that obtained from RF-trained convolutional neural networks, i.e., using only three I/Q images, CID-Net produces high-quality images that can compete with those obtained by coherently compounding 31 RF images. Moreover, we show that CID-Net outperforms the straightforward architecture that consists of processing real and imaginary parts of the I/Q signal separately, which thereby indicates the importance of consistently processing the I/Q signals using a network that exploits the complex nature of such signals. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of IEEE Transactions on Ultrasonics Ferroelectrics & Frequency Control is the property of IEEE and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=154974772 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1109/TUFFC.2021.3127916 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 12 StartPage: 592 Subjects: – SubjectFull: Convolutional neural networks Type: general – SubjectFull: Ultrasonic imaging Type: general – SubjectFull: Image reconstruction Type: general – SubjectFull: Deep learning Type: general – SubjectFull: Radio frequency Type: general Titles: – TitleFull: Complex Convolutional Neural Networks for Ultrafast Ultrasound Imaging Reconstruction From In-Phase/Quadrature Signal. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Lu, Jingfeng – PersonEntity: Name: NameFull: Millioz, Fabien – PersonEntity: Name: NameFull: Garcia, Damien – PersonEntity: Name: NameFull: Salles, Sebastien – PersonEntity: Name: NameFull: Ye, Dong – PersonEntity: Name: NameFull: Friboulet, Denis IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 02 Text: Feb2022 Type: published Y: 2022 Identifiers: – Type: issn-print Value: 08853010 Numbering: – Type: volume Value: 9 – Type: issue Value: 2 Titles: – TitleFull: IEEE Transactions on Ultrasonics Ferroelectrics & Frequency Control Type: main |
| ResultId | 1 |
