UltRAP‐Net: Reverse Approximation of Tissue Properties in Ultrasound Imaging

Medical ultrasound (US) has been widely used in clinical practices due to its merits of being low cost, real time, and radiation free. However, its capability to reveal the underlying tissue properties remains underexplored. A physics‐constrained learning framework is studied to reversely approximat...

Full description

Saved in:
Bibliographic Details
Main Authors: Yingqi Li, Ka‐Wai Kwok, Magdalena Wysocki, Nassir Navab, Zhongliang Jiang
Format: Article
Language:English
Published: Wiley 2025-08-01
Series:Advanced Intelligent Systems
Subjects:
Online Access:https://doi.org/10.1002/aisy.202400865
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849230090412490752
author Yingqi Li
Ka‐Wai Kwok
Magdalena Wysocki
Nassir Navab
Zhongliang Jiang
author_facet Yingqi Li
Ka‐Wai Kwok
Magdalena Wysocki
Nassir Navab
Zhongliang Jiang
author_sort Yingqi Li
collection DOAJ
description Medical ultrasound (US) has been widely used in clinical practices due to its merits of being low cost, real time, and radiation free. However, its capability to reveal the underlying tissue properties remains underexplored. A physics‐constrained learning framework is studied to reversely approximate tissue property representations from multiple B‐mode images acquired with varying dynamic ranges. First, an extractor network is used to generate property maps, that is, attenuation coefficient α, reflection coefficient β, border probability ρb, scattering density ρs, scattering amplitude ϕ, and one perturbation p map characterizing the variations caused by varying dynamic range. The α − ϕ maps are loosely regularized by rendering them forward to realistic US images using ray‐tracing simulator. To further enforce the physics constraints, a ranking loss is introduced to align the disparity between two estimated p maps with the discrepancy between two distinct inputs. Due to the missing ground truth α − ϕ maps, alternatively, the method is validated by evaluating the consistency between the feature maps inferred from distinct images. The results demonstrate that the proposed method can robustly extract consistent intermediate maps from images. Furthermore, one potential downstream application is showcased to perform realistic US augmentation by introducing specific noise into the physics‐inspired α − ϕ maps.
format Article
id doaj-art-768eb89632bc4ad492ecc261b6596e2c
institution Kabale University
issn 2640-4567
language English
publishDate 2025-08-01
publisher Wiley
record_format Article
series Advanced Intelligent Systems
spelling doaj-art-768eb89632bc4ad492ecc261b6596e2c2025-08-21T11:05:47ZengWileyAdvanced Intelligent Systems2640-45672025-08-0178n/an/a10.1002/aisy.202400865UltRAP‐Net: Reverse Approximation of Tissue Properties in Ultrasound ImagingYingqi Li0Ka‐Wai Kwok1Magdalena Wysocki2Nassir Navab3Zhongliang Jiang4Department of Mechanical Engineering The University of Hong Kong Hong Kong 999077 P. R. ChinaDepartment of Mechanical Engineering The University of Hong Kong Hong Kong 999077 P. R. ChinaChair for Computer‐Aided Medical Procedures and Augmented Reality Technical University of Munich 85748 Munich GermanyChair for Computer‐Aided Medical Procedures and Augmented Reality Technical University of Munich 85748 Munich GermanyChair for Computer‐Aided Medical Procedures and Augmented Reality Technical University of Munich 85748 Munich GermanyMedical ultrasound (US) has been widely used in clinical practices due to its merits of being low cost, real time, and radiation free. However, its capability to reveal the underlying tissue properties remains underexplored. A physics‐constrained learning framework is studied to reversely approximate tissue property representations from multiple B‐mode images acquired with varying dynamic ranges. First, an extractor network is used to generate property maps, that is, attenuation coefficient α, reflection coefficient β, border probability ρb, scattering density ρs, scattering amplitude ϕ, and one perturbation p map characterizing the variations caused by varying dynamic range. The α − ϕ maps are loosely regularized by rendering them forward to realistic US images using ray‐tracing simulator. To further enforce the physics constraints, a ranking loss is introduced to align the disparity between two estimated p maps with the discrepancy between two distinct inputs. Due to the missing ground truth α − ϕ maps, alternatively, the method is validated by evaluating the consistency between the feature maps inferred from distinct images. The results demonstrate that the proposed method can robustly extract consistent intermediate maps from images. Furthermore, one potential downstream application is showcased to perform realistic US augmentation by introducing specific noise into the physics‐inspired α − ϕ maps.https://doi.org/10.1002/aisy.202400865robotic ultrasoundsultrasound augmentationsultrasound image analyses
spellingShingle Yingqi Li
Ka‐Wai Kwok
Magdalena Wysocki
Nassir Navab
Zhongliang Jiang
UltRAP‐Net: Reverse Approximation of Tissue Properties in Ultrasound Imaging
Advanced Intelligent Systems
robotic ultrasounds
ultrasound augmentations
ultrasound image analyses
title UltRAP‐Net: Reverse Approximation of Tissue Properties in Ultrasound Imaging
title_full UltRAP‐Net: Reverse Approximation of Tissue Properties in Ultrasound Imaging
title_fullStr UltRAP‐Net: Reverse Approximation of Tissue Properties in Ultrasound Imaging
title_full_unstemmed UltRAP‐Net: Reverse Approximation of Tissue Properties in Ultrasound Imaging
title_short UltRAP‐Net: Reverse Approximation of Tissue Properties in Ultrasound Imaging
title_sort ultrap net reverse approximation of tissue properties in ultrasound imaging
topic robotic ultrasounds
ultrasound augmentations
ultrasound image analyses
url https://doi.org/10.1002/aisy.202400865
work_keys_str_mv AT yingqili ultrapnetreverseapproximationoftissuepropertiesinultrasoundimaging
AT kawaikwok ultrapnetreverseapproximationoftissuepropertiesinultrasoundimaging
AT magdalenawysocki ultrapnetreverseapproximationoftissuepropertiesinultrasoundimaging
AT nassirnavab ultrapnetreverseapproximationoftissuepropertiesinultrasoundimaging
AT zhongliangjiang ultrapnetreverseapproximationoftissuepropertiesinultrasoundimaging