Deep-Learning-Based Multitask Ultrasound Beamforming
In this paper, we present a new method for multitask learning applied to ultrasound beamforming. Beamforming is a critical component in the ultrasound image formation pipeline. Ultrasound images are constructed using sensor readings from multiple transducer elements, with each element typically capt...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/14/10/582 |
| _version_ | 1797573556859568128 |
|---|---|
| author | Elay Dahan Israel Cohen |
| author_facet | Elay Dahan Israel Cohen |
| author_sort | Elay Dahan |
| collection | DOAJ |
| description | In this paper, we present a new method for multitask learning applied to ultrasound beamforming. Beamforming is a critical component in the ultrasound image formation pipeline. Ultrasound images are constructed using sensor readings from multiple transducer elements, with each element typically capturing multiple acquisitions per frame. Hence, the beamformer is crucial for framerate performance and overall image quality. Furthermore, post-processing, such as image denoising, is usually applied to the beamformed image to achieve high clarity for diagnosis. This work shows a fully convolutional neural network that can learn different tasks by applying a new weight normalization scheme. We adapt our model to both high frame rate requirements by fitting weight normalization parameters for the sub-sampling task and image denoising by optimizing the normalization parameters for the speckle reduction task. Our model outperforms single-angle delay and sum on pixel-level measures for speckle noise reduction, subsampling, and single-angle reconstruction. |
| first_indexed | 2024-03-10T21:10:45Z |
| format | Article |
| id | doaj.art-5fedc02c17c64ed1aae7c28049714459 |
| institution | Directory Open Access Journal |
| issn | 2078-2489 |
| language | English |
| last_indexed | 2024-03-10T21:10:45Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj.art-5fedc02c17c64ed1aae7c280497144592023-11-19T16:48:30ZengMDPI AGInformation2078-24892023-10-01141058210.3390/info14100582Deep-Learning-Based Multitask Ultrasound BeamformingElay Dahan0Israel Cohen1Andrew and Erna Viterbi Faculty of Electrical & Computer Engineering, Technion–Israel Institute of Technology, Technion City, Haifa 3200003, IsraelAndrew and Erna Viterbi Faculty of Electrical & Computer Engineering, Technion–Israel Institute of Technology, Technion City, Haifa 3200003, IsraelIn this paper, we present a new method for multitask learning applied to ultrasound beamforming. Beamforming is a critical component in the ultrasound image formation pipeline. Ultrasound images are constructed using sensor readings from multiple transducer elements, with each element typically capturing multiple acquisitions per frame. Hence, the beamformer is crucial for framerate performance and overall image quality. Furthermore, post-processing, such as image denoising, is usually applied to the beamformed image to achieve high clarity for diagnosis. This work shows a fully convolutional neural network that can learn different tasks by applying a new weight normalization scheme. We adapt our model to both high frame rate requirements by fitting weight normalization parameters for the sub-sampling task and image denoising by optimizing the normalization parameters for the speckle reduction task. Our model outperforms single-angle delay and sum on pixel-level measures for speckle noise reduction, subsampling, and single-angle reconstruction.https://www.mdpi.com/2078-2489/14/10/582multitask learningbeamformingultrasound image formation |
| spellingShingle | Elay Dahan Israel Cohen Deep-Learning-Based Multitask Ultrasound Beamforming Information multitask learning beamforming ultrasound image formation |
| title | Deep-Learning-Based Multitask Ultrasound Beamforming |
| title_full | Deep-Learning-Based Multitask Ultrasound Beamforming |
| title_fullStr | Deep-Learning-Based Multitask Ultrasound Beamforming |
| title_full_unstemmed | Deep-Learning-Based Multitask Ultrasound Beamforming |
| title_short | Deep-Learning-Based Multitask Ultrasound Beamforming |
| title_sort | deep learning based multitask ultrasound beamforming |
| topic | multitask learning beamforming ultrasound image formation |
| url | https://www.mdpi.com/2078-2489/14/10/582 |
| work_keys_str_mv | AT elaydahan deeplearningbasedmultitaskultrasoundbeamforming AT israelcohen deeplearningbasedmultitaskultrasoundbeamforming |