Reverberation Suppression in Echocardiography Using a Causal Convolutional Neural Network
While ultrasound imaging has seen vast technical advances over the last decades, trans-thoracic echocardiography still suffers from image quality degradation caused by acoustic interaction with inhomogeneous tissue layers between the transducer and the heart. The acoustic energy reflections from ech...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10172202/ |
| _version_ | 1797776337759371264 |
|---|---|
| author | Tollef Struksnes Jahren Anders Rasmus Sornes Bastien Denarie Erik Steen Tore Bjastad Anne H. Schistad Solberg |
| author_facet | Tollef Struksnes Jahren Anders Rasmus Sornes Bastien Denarie Erik Steen Tore Bjastad Anne H. Schistad Solberg |
| author_sort | Tollef Struksnes Jahren |
| collection | DOAJ |
| description | While ultrasound imaging has seen vast technical advances over the last decades, trans-thoracic echocardiography still suffers from image quality degradation caused by acoustic interaction with inhomogeneous tissue layers between the transducer and the heart. The acoustic energy reflections from echogenic structures such as skin, subcutaneous fat, bone, cartilage, intercostal muscle tissue, and lungs can form a dense overlay of echoes occluding the structural information resulting in a degradation of the diagnostic value. We propose a new method for reducing this reverberational clutter inspired by how the brain addresses the problem; identifying the reverberation overlay by the way it constitutes a pattern of speckles that moves in one cohesive motion different from that of the underlying structures. With this approach, we effectively render the clutter suppression as a video separation problem. Compared to traditional clutter rejection methods that tend to specialize in either temporal or spatial qualities, we find a neural network to be more flexible in incorporating both temporal and spatial information. We generate a pseudo-paired data set using <italic>in vivo</italic> data by excising patches off hypo-echoic regions of strongly reverberation-affected clinical recordings and superimposing them onto clean clinical recordings. The pseudo-paired data set of beamformed in-phase and quadrature component (IQ)-data is used to train a neural network to suppress reverberations in cine-loops. We demonstrate that this post-beamformer method can enhance image quality in <italic>in vivo</italic> and make valuable clinical structures clearer in a commercial system. We show that the method does not display any tendency to generate false cardiac structures, and that rapid motions from e.g. valve leaflets retain high structural integrity and low levels of blurring. Our results suggest that this method can be an effective and robust tool for suppressing reverberations in transthoracic ultrasound imaging. |
| first_indexed | 2024-03-12T22:48:32Z |
| format | Article |
| id | doaj.art-d458e850775c40a6a354e11e1b6234c1 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-12T22:48:32Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-d458e850775c40a6a354e11e1b6234c12023-07-20T23:00:24ZengIEEEIEEE Access2169-35362023-01-0111679226793710.1109/ACCESS.2023.329221210172202Reverberation Suppression in Echocardiography Using a Causal Convolutional Neural NetworkTollef Struksnes Jahren0https://orcid.org/0000-0002-7116-1982Anders Rasmus Sornes1Bastien Denarie2https://orcid.org/0009-0006-1270-4998Erik Steen3Tore Bjastad4Anne H. Schistad Solberg5https://orcid.org/0000-0002-6149-971XDepartment of Informatics, University of Oslo, Oslo, NorwayGE Healthcare, Horten, NorwayGE Healthcare, Horten, NorwayGE Healthcare, Horten, NorwayGE Healthcare, Horten, NorwayDepartment of Informatics, University of Oslo, Oslo, NorwayWhile ultrasound imaging has seen vast technical advances over the last decades, trans-thoracic echocardiography still suffers from image quality degradation caused by acoustic interaction with inhomogeneous tissue layers between the transducer and the heart. The acoustic energy reflections from echogenic structures such as skin, subcutaneous fat, bone, cartilage, intercostal muscle tissue, and lungs can form a dense overlay of echoes occluding the structural information resulting in a degradation of the diagnostic value. We propose a new method for reducing this reverberational clutter inspired by how the brain addresses the problem; identifying the reverberation overlay by the way it constitutes a pattern of speckles that moves in one cohesive motion different from that of the underlying structures. With this approach, we effectively render the clutter suppression as a video separation problem. Compared to traditional clutter rejection methods that tend to specialize in either temporal or spatial qualities, we find a neural network to be more flexible in incorporating both temporal and spatial information. We generate a pseudo-paired data set using <italic>in vivo</italic> data by excising patches off hypo-echoic regions of strongly reverberation-affected clinical recordings and superimposing them onto clean clinical recordings. The pseudo-paired data set of beamformed in-phase and quadrature component (IQ)-data is used to train a neural network to suppress reverberations in cine-loops. We demonstrate that this post-beamformer method can enhance image quality in <italic>in vivo</italic> and make valuable clinical structures clearer in a commercial system. We show that the method does not display any tendency to generate false cardiac structures, and that rapid motions from e.g. valve leaflets retain high structural integrity and low levels of blurring. Our results suggest that this method can be an effective and robust tool for suppressing reverberations in transthoracic ultrasound imaging.https://ieeexplore.ieee.org/document/10172202/Reverberationhazeclutterultrasoundechocardiographyneural network |
| spellingShingle | Tollef Struksnes Jahren Anders Rasmus Sornes Bastien Denarie Erik Steen Tore Bjastad Anne H. Schistad Solberg Reverberation Suppression in Echocardiography Using a Causal Convolutional Neural Network IEEE Access Reverberation haze clutter ultrasound echocardiography neural network |
| title | Reverberation Suppression in Echocardiography Using a Causal Convolutional Neural Network |
| title_full | Reverberation Suppression in Echocardiography Using a Causal Convolutional Neural Network |
| title_fullStr | Reverberation Suppression in Echocardiography Using a Causal Convolutional Neural Network |
| title_full_unstemmed | Reverberation Suppression in Echocardiography Using a Causal Convolutional Neural Network |
| title_short | Reverberation Suppression in Echocardiography Using a Causal Convolutional Neural Network |
| title_sort | reverberation suppression in echocardiography using a causal convolutional neural network |
| topic | Reverberation haze clutter ultrasound echocardiography neural network |
| url | https://ieeexplore.ieee.org/document/10172202/ |
| work_keys_str_mv | AT tollefstruksnesjahren reverberationsuppressioninechocardiographyusingacausalconvolutionalneuralnetwork AT andersrasmussornes reverberationsuppressioninechocardiographyusingacausalconvolutionalneuralnetwork AT bastiendenarie reverberationsuppressioninechocardiographyusingacausalconvolutionalneuralnetwork AT eriksteen reverberationsuppressioninechocardiographyusingacausalconvolutionalneuralnetwork AT torebjastad reverberationsuppressioninechocardiographyusingacausalconvolutionalneuralnetwork AT annehschistadsolberg reverberationsuppressioninechocardiographyusingacausalconvolutionalneuralnetwork |