Evaluating Curvature-Induced Variation in Deep Learning-Based Beamforming for Flexible Transducers in Ultrasound-Guided Radiation Therapy

Feng, Ziwei; Huang, Xinyue; Hooshangnejad, Hamed; China, Debarghya; Lee, Junghoon; McNutt, Todd; Bell, Muyinatu A. Lediju; Ding, Kai

doi:10.3390/bioengineering13040398

Open AccessArticle

Evaluating Curvature-Induced Variation in Deep Learning-Based Beamforming for Flexible Transducers in Ultrasound-Guided Radiation Therapy

by

Ziwei Feng

^1,2,

Xinyue Huang

³

,

Hamed Hooshangnejad

^1,3

,

Debarghya China

³

,

Junghoon Lee

¹

,

Todd McNutt

¹,

Muyinatu A. Lediju Bell

^2,3,4

and

Kai Ding

^1,*

¹

Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University School of Medicine, Baltimore, MD 21287, USA

²

Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD 21218, USA

³

Department of Biomedical Engineering, Johns Hopkins University School of Medicine, Baltimore, MD 21287, USA

⁴

Department of Computer Science, Johns Hopkins University, Baltimore, MD 21218, USA

^*

Author to whom correspondence should be addressed.

Bioengineering 2026, 13(4), 398; https://doi.org/10.3390/bioengineering13040398

Submission received: 25 November 2025 / Revised: 7 March 2026 / Accepted: 24 March 2026 / Published: 29 March 2026

(This article belongs to the Special Issue Novel Imaging Techniques in Radiotherapy)

Download

Browse Figures

Versions Notes

Abstract

Ultrasound imaging is a crucial tool for guiding radiation therapy, particularly for cancers such as pancreatic cancer, where tumors exhibit respiration-induced motion. While flexible ultrasound transducers offer improved anatomical conformity and reduced compression-induced distortion compared to rigid probes, their variable geometry presents significant challenges for conventional beamforming. In this study, we investigate a deep learning-based beamforming framework that directly predicts delayed RF data from raw RF input, bypassing explicit transducer shape estimation and traditional delay-and-sum computations. Building upon an artificial curvature simulation strategy, we systematically analyze the impact of curvature-induced variation and inherent RF noise on model performance and generalizability. We further introduce frequency-domain analysis to quantify RF-level signal variation that may not be apparent in spatial-domain image comparisons. Our results demonstrate that although noise-augmented training improves prediction consistency, reconstruction performance remains limited under the current prototype noise conditions. These findings highlight the importance of RF data diversity and noise characterization in developing clinically robust deep learning beamformers for flexible transducer-based ultrasound-guided radiation therapy.

Keywords: ultrasound flexible transducer; machine learning; radiation oncology; ultrasound image reconstruction

Share and Cite

MDPI and ACS Style

Feng, Z.; Huang, X.; Hooshangnejad, H.; China, D.; Lee, J.; McNutt, T.; Bell, M.A.L.; Ding, K. Evaluating Curvature-Induced Variation in Deep Learning-Based Beamforming for Flexible Transducers in Ultrasound-Guided Radiation Therapy. Bioengineering 2026, 13, 398. https://doi.org/10.3390/bioengineering13040398

AMA Style

Feng Z, Huang X, Hooshangnejad H, China D, Lee J, McNutt T, Bell MAL, Ding K. Evaluating Curvature-Induced Variation in Deep Learning-Based Beamforming for Flexible Transducers in Ultrasound-Guided Radiation Therapy. Bioengineering. 2026; 13(4):398. https://doi.org/10.3390/bioengineering13040398

Chicago/Turabian Style

Feng, Ziwei, Xinyue Huang, Hamed Hooshangnejad, Debarghya China, Junghoon Lee, Todd McNutt, Muyinatu A. Lediju Bell, and Kai Ding. 2026. "Evaluating Curvature-Induced Variation in Deep Learning-Based Beamforming for Flexible Transducers in Ultrasound-Guided Radiation Therapy" Bioengineering 13, no. 4: 398. https://doi.org/10.3390/bioengineering13040398

APA Style

Feng, Z., Huang, X., Hooshangnejad, H., China, D., Lee, J., McNutt, T., Bell, M. A. L., & Ding, K. (2026). Evaluating Curvature-Induced Variation in Deep Learning-Based Beamforming for Flexible Transducers in Ultrasound-Guided Radiation Therapy. Bioengineering, 13(4), 398. https://doi.org/10.3390/bioengineering13040398

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Evaluating Curvature-Induced Variation in Deep Learning-Based Beamforming for Flexible Transducers in Ultrasound-Guided Radiation Therapy

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI