Tiny-VBF: Resource-Efficient Vision Transformer based Lightweight Beamformer for Ultrasound Single-Angle Plane Wave Imaging
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913195783880704 |
|---|---|
| author | Rahoof, Abdul Chaturvedi, Vivek Panicker, Mahesh Raveendranatha Shafique, Muhammad |
| author_facet | Rahoof, Abdul Chaturvedi, Vivek Panicker, Mahesh Raveendranatha Shafique, Muhammad |
| contents | Accelerating compute intensive non-real-time beam-forming algorithms in ultrasound imaging using deep learning architectures has been gaining momentum in the recent past. Nonetheless, the complexity of the state-of-the-art deep learning techniques poses challenges for deployment on resource-constrained edge devices. In this work, we propose a novel vision transformer based tiny beamformer (Tiny-VBF), which works on the raw radio-frequency channel data acquired through single-angle plane wave insonification. The output of our Tiny-VBF provides fast envelope detection requiring very low frame rate, i.e. 0.34 GOPs/Frame for a frame size of 368 x 128 in comparison to the state-of-the-art deep learning models. It also exhibited an 8% increase in contrast and gains of 5% and 33% in axial and lateral resolution respectively when compared to Tiny-CNN on in-vitro dataset. Additionally, our model showed a 4.2% increase in contrast and gains of 4% and 20% in axial and lateral resolution respectively when compared against conventional Delay-and-Sum (DAS) beamformer. We further propose an accelerator architecture and implement our Tiny-VBF model on a Zynq UltraScale+ MPSoC ZCU104 FPGA using a hybrid quantization scheme with 50% less resource consumption compared to the floating-point implementation, while preserving the image quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_12082 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Tiny-VBF: Resource-Efficient Vision Transformer based Lightweight Beamformer for Ultrasound Single-Angle Plane Wave Imaging Rahoof, Abdul Chaturvedi, Vivek Panicker, Mahesh Raveendranatha Shafique, Muhammad Image and Video Processing Machine Learning Accelerating compute intensive non-real-time beam-forming algorithms in ultrasound imaging using deep learning architectures has been gaining momentum in the recent past. Nonetheless, the complexity of the state-of-the-art deep learning techniques poses challenges for deployment on resource-constrained edge devices. In this work, we propose a novel vision transformer based tiny beamformer (Tiny-VBF), which works on the raw radio-frequency channel data acquired through single-angle plane wave insonification. The output of our Tiny-VBF provides fast envelope detection requiring very low frame rate, i.e. 0.34 GOPs/Frame for a frame size of 368 x 128 in comparison to the state-of-the-art deep learning models. It also exhibited an 8% increase in contrast and gains of 5% and 33% in axial and lateral resolution respectively when compared to Tiny-CNN on in-vitro dataset. Additionally, our model showed a 4.2% increase in contrast and gains of 4% and 20% in axial and lateral resolution respectively when compared against conventional Delay-and-Sum (DAS) beamformer. We further propose an accelerator architecture and implement our Tiny-VBF model on a Zynq UltraScale+ MPSoC ZCU104 FPGA using a hybrid quantization scheme with 50% less resource consumption compared to the floating-point implementation, while preserving the image quality. |
| title | Tiny-VBF: Resource-Efficient Vision Transformer based Lightweight Beamformer for Ultrasound Single-Angle Plane Wave Imaging |
| topic | Image and Video Processing Machine Learning |
| url | https://arxiv.org/abs/2311.12082 |