Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Physics Informed Deep Unfolded Full Waveform Inversion for Edema Detection

Ruizhi Zhang, Yhonatan Kvich, Rui Guo, Oded Cohen, Yonina C. Eldar

TL;DR

Deep unfolded FWI (DUFWI) is introduced, a physics-faithful unfolded iterative inversion method that exhibits FWI-like refinement behavior while learning the update rule from data, requiring only a small number of iterations for real-time SoS reconstruction.

Abstract

Edema is a potential indicator of underlying pathological changes. However, its low-contrast signature is often masked in conventional B-mode imaging by strong scatterers, making reliable detection challenging. Ultrasound (US) provides a non-invasive, non-ionizing, and cost-efficient imaging option that is widely used. Conventional techniques, which rely on beamforming, often lack sufficient physical interpretability. Quantitative US (QUS) can estimate physical properties such as the speed of sound (SoS) and density by solving a physics-based inverse problem directly on the measured US wavefields, i.e., the raw per-element channel data (CD), to recover their spatial distribution. However, state-of-the-art physics-based inversion methods, including full waveform inversion (FWI) and model-based quantitative radar and US (MB-QRUS), are computationally intensive and susceptible to local minima, which constrains their clinical utility. We introduce deep unfolded FWI (DUFWI), a physics-faithful unfolded iterative inversion method that exhibits FWI-like refinement behavior while learning the update rule from data, requiring only a small number of iterations for real-time SoS reconstruction. Across both simulated datasets and hardware measurements acquired with a Verasonics US system, the DUFWI significantly outperforms classical FWI and MB-QRUS in reconstruction quality while maintaining high computational efficiency. These results demonstrate real-time edema diagnosis in both simulation and hardware experiments, with phantom-based validation using cylindrical rods, supporting practical deployment under typical US imaging setting.

Physics Informed Deep Unfolded Full Waveform Inversion for Edema Detection

TL;DR

Deep unfolded FWI (DUFWI) is introduced, a physics-faithful unfolded iterative inversion method that exhibits FWI-like refinement behavior while learning the update rule from data, requiring only a small number of iterations for real-time SoS reconstruction.

Abstract

Edema is a potential indicator of underlying pathological changes. However, its low-contrast signature is often masked in conventional B-mode imaging by strong scatterers, making reliable detection challenging. Ultrasound (US) provides a non-invasive, non-ionizing, and cost-efficient imaging option that is widely used. Conventional techniques, which rely on beamforming, often lack sufficient physical interpretability. Quantitative US (QUS) can estimate physical properties such as the speed of sound (SoS) and density by solving a physics-based inverse problem directly on the measured US wavefields, i.e., the raw per-element channel data (CD), to recover their spatial distribution. However, state-of-the-art physics-based inversion methods, including full waveform inversion (FWI) and model-based quantitative radar and US (MB-QRUS), are computationally intensive and susceptible to local minima, which constrains their clinical utility. We introduce deep unfolded FWI (DUFWI), a physics-faithful unfolded iterative inversion method that exhibits FWI-like refinement behavior while learning the update rule from data, requiring only a small number of iterations for real-time SoS reconstruction. Across both simulated datasets and hardware measurements acquired with a Verasonics US system, the DUFWI significantly outperforms classical FWI and MB-QRUS in reconstruction quality while maintaining high computational efficiency. These results demonstrate real-time edema diagnosis in both simulation and hardware experiments, with phantom-based validation using cylindrical rods, supporting practical deployment under typical US imaging setting.
Paper Structure (17 sections, 10 equations, 12 figures, 5 tables)

This paper contains 17 sections, 10 equations, 12 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Foundations and Problem Statement
  3. Forward Modeling
  4. Conventional Approach
  5. FWI
  6. MB-QRUS
  7. Deep Unfolding of Full Waveform Inversion
  8. DUFWI Framework
  9. Block-wise Training Process
  10. Deep neural network architecture
  11. Deep neural network inference
  12. Hardware System
  13. Numerical Results
  14. MNIST Dataset Results
  15. Simulated Arm Dataset Results
  16. ...and 2 more sections

Figures (12)

  • Figure 1: A typical 2-D measurement setup for edema diagnosis, illustrating a target arm surrounded by a circular array of transducers.
  • Figure 2: Visual comparision of the gradient update of three inverse methods: (a) FWI, (b) MB-QRUS, (c) DUFWI.
  • Figure 3: Illustration of the overall CNN architecture.
  • Figure 4: Layout of the transducer elements. The circular array consists of 16 evenly spaced elements arranged on a 10 cm diameter ring.
  • Figure 5: Overall hardware system: (Left) a transparent water bath housing the circular transducer array; (Right) a Keysight InfiniiVision oscilloscope used only to illustrate example received CD waveforms in real time.
  • ...and 7 more figures