arXiv subjects

Geoffrey P. Luke

Publications and source records attributed to Geoffrey P. Luke.

8 recordsLinked to original sources

arXiv2026

DiffSOS: Acoustic Conditional Diffusion Model for Speed-of-Sound Reconstruction in Ultrasound Computed Tomography

Accurate Speed-of-Sound (SoS) reconstruction from acoustic waveforms is a cornerstone of ultrasound computed tomography (USCT), enabling quantitative velocity mapping that reveals subtle anatomical details and pathological variations often invisible in conventional imaging. However, practical utility is hindered by the limitations of existing algorithms; traditional Full Waveform Inversion (FWI) is computationally intensive, while current deep learning approaches tend to produce oversmoothed results lacking fine details. We propose DiffSOS, a conditional diffusion model that directly maps acoustic waveforms to SoS maps. Our framework employs a specialized acoustic ControlNet to strictly ground the denoising process in physical wave measurements. To ensure structural consistency, we optimize a hybrid loss function that integrates noise prediction, spatial reconstruction, and noise frequency content. To accelerate inference, we employ stochastic Denoising Diffusion Implicit Model (DDIM) sampling, achieving near real-time reconstruction with only 10 steps. Crucially, we exploit the stochastic generative nature of our framework to estimate pixel-wise uncertainty, providing a measure of reliability that is often absent in deterministic approaches. Evaluated on the OpenPros USCT benchmark, DiffSOS significantly outperforms state-of-the-art networks, achieving an average Multi-scale Structural Similarity of 0.957. Our approach provides high-fidelity SoS maps with a principled measure of confidence, facilitating safer and faster clinical interpretation.

cs.CV↗

arXiv2026

IRSDE-Despeckle: A Physics-Grounded Diffusion Model for Generalizable Ultrasound Despeckling

Ultrasound imaging is widely used for real-time, noninvasive diagnosis, but speckle and related artifacts reduce image quality and can hinder interpretation. We present a diffusion-based ultrasound despeckling method built on the Image Restoration Stochastic Differential Equations framework. To enable supervised training, we curate large paired datasets by simulating ultrasound images from speckle-free magnetic resonance images using the Matlab UltraSound Toolbox. The proposed model reconstructs speckle-suppressed images while preserving anatomically meaningful edges and contrast. On a held-out simulated test set, our approach consistently outperforms classical filters and recent learning-based despeckling baselines. We quantify prediction uncertainty via cross-model variance and show that higher uncertainty correlates with higher reconstruction error, providing a practical indicator of difficult or failure-prone regions. Finally, we evaluate sensitivity to simulation probe settings and observe domain shift, motivating diversified training and adaptation for robust clinical deployment.

cs.CV↗

arXiv2025

Deep Learning-Driven Quantitative Spectroscopic Photoacoustic Imaging for Segmentation and Oxygen Saturation Estimation

Spectroscopic photoacoustic (sPA) imaging can potentially estimate blood oxygenation saturation (sO2) in vivo noninvasively. However, quantitatively accurate results require accurate optical fluence estimates. Robust modeling in heterogeneous tissue, where light with different wavelengths can experience significantly different absorption and scattering, is difficult. In this work, we developed a deep neural network (Hybrid-Net) for sPA imaging to simultaneously estimate sO2 in blood vessels and segment those vessels from surrounding background tissue. sO2 error was minimized only in blood vessels segmented in Hybrid-Net, resulting in more accurate predictions. Hybrid-Net was first trained on simulated sPA data (at 700 nm and 850 nm) representing initial pressure distributions from three-dimensional Monte Carlo simulations of light transport in breast tissue. Then, for experimental verification, the network was retrained on experimental sPA data (at 700 nm and 850 nm) acquired from simple tissue mimicking phantoms with an embedded blood pool. Quantitative measures were used to evaluate Hybrid-Net performance with an averaged segmentation accuracy of >= 0.978 in simulations with varying noise levels (0dB-35dB) and 0.998 in the experiment, and an averaged sO2 mean squared error of <= 0.048 in simulations with varying noise levels (0dB-35dB) and 0.003 in the experiment. Overall, these results show that Hybrid-Net can provide accurate blood oxygenation without estimating the optical fluence, and this study could lead to improvements in in-vivo sO2 estimation.

eess.IV↗

arXiv2024

Joint Segmentation and Image Reconstruction with Error Prediction in Photoacoustic Imaging using Deep Learning

Deep learning has been used to improve photoacoustic (PA) image reconstruction. One major challenge is that errors cannot be quantified to validate predictions when ground truth is unknown. Validation is key to quantitative applications, especially using limited-bandwidth ultrasonic linear detector arrays. Here, we propose a hybrid Bayesian convolutional neural network (Hybrid-BCNN) to jointly predict PA image and segmentation with error (uncertainty) predictions. Each output pixel represents a probability distribution where error can be quantified. The Hybrid-BCNN was trained with simulated PA data and applied to both simulations and experiments. Due to the sparsity of PA images, segmentation focuses Hybrid-BCNN on minimizing the loss function in regions with PA signals for better predictions. The results show that accurate PA segmentations and images are obtained, and error predictions are highly statistically correlated to actual errors. To leverage error predictions, confidence processing created PA images above a specific confidence level.

eess.IV↗

arXiv2023

Multiplex ultrasound imaging of perfluorocarbon nanodroplets enabled by decomposition of post-vaporization dynamics

Among the various molecular imaging modalities, ultrasound imaging benefits from its real-time, nonionizing, and cost-effective nature. Despite its benefits, there is a dearth of methods to visualize two or more populations of contrast agents simultaneously, a technique known as multiplex imaging. In this paper, we present a new approach to multiplex ultrasound imaging using perfluorocarbon (PFC) nanodroplets. The nanodroplets, which undergo a liquid-to-gas phase transition in response to an acoustic trigger, act as activatable contrast agents. By using two populations of PFC nanodroplets, each with a different core boiling point, their unique temporal responses to an acoustic trigger were leveraged to differentiate their unique contributions to the overall ultrasound signal. This work characterized the dynamic responses of two PFC nanodroplets with boiling points of 28 and 56 °C. These characteristic responses were then used to demonstrate that the relative concentrations of the two populations of PFC nanodroplets could be accurately measured in the same imaging volume within an average error of 1.1%. Overall, the findings indicate the potential of this approach for multiplex ultrasound imaging, allowing for the visualization of multiple molecular targets simultaneously.

eess.IV↗

arXiv2021

Deep-learning-driven Reliable Single-pixel Imaging with Uncertainty Approximation

Single-pixel imaging (SPI) has the advantages of high-speed acquisition over a broad wavelength range and system compactness, which are difficult to achieve by conventional imaging sensors. However, a common challenge is low image quality arising from undersampling. Deep learning (DL) is an emerging and powerful tool in computational imaging for many applications and researchers have applied DL in SPI to achieve higher image quality than conventional reconstruction approaches. One outstanding challenge, however, is that the accuracy of DL predictions in SPI cannot be assessed in practical applications where the ground truths are unknown. Here, we propose the use of the Bayesian convolutional neural network (BCNN) to approximate the uncertainty (coming from finite training data and network model) of the DL predictions in SPI. Each pixel in the predicted result from BCNN represents the parameter of a probability distribution rather than the image intensity value. Then, the uncertainty can be approximated with BCNN by minimizing a negative log-likelihood loss function in the training stage and Monte Carlo dropout in the prediction stage. The results show that the BCNN can reliably approximate the uncertainty of the DL predictions in SPI with varying compression ratios and noise levels. The predicted uncertainty from BCNN in SPI reveals that most of the reconstruction errors in deep-learning-based SPI come from the edges of the image features. The results show that the proposed BCNN can provide a reliable tool to approximate the uncertainty of DL predictions in SPI and can be widely used in many applications of SPI.

eess.IV↗

arXiv2020

A Two-step-training Deep Learning Framework for Real-time Computational Imaging without Physics Priors

Deep learning (DL) is a powerful tool in computational imaging for many applications. A common strategy is to reconstruct a preliminary image as the input of a neural network to achieve an optimized image. Usually, the preliminary image is acquired with the prior knowledge of the imaging model. One outstanding challenge, however, is the degree to which the actual imaging model deviates from the assumed model. Model mismatches degrade the quality of the preliminary image and therefore affect the DL predictions. Another main challenge is that since most imaging inverse problems are ill-posed and the networks are over-parameterized, DL networks have flexibility to extract features from the data that are not directly related to the imaging model. To solve these challenges, a two-step-training DL (TST-DL) framework is proposed for real-time computational imaging without physics priors. First, a single fully-connected layer (FCL) is trained to directly learn the model. Then, this FCL is fixed and concatenated with an un-trained U-Net architecture for a second-step training to improve the output image fidelity, resulting in four main advantages. First, it does not rely on an accurate representation of the imaging model since the model is directly learned. Second, real-time imaging can be achieved. Third, the TST-DL network is trained in the desired direction and the predictions are improved since the first step is constrained to learn the model and the second step improves the result by learning the optimal regularizer. Fourth, the approach accommodates any size and dimensionality of data. We demonstrate this framework using a linear single-pixel camera imaging model. The results are quantitatively compared with those from other DL frameworks and model-based iterative optimization approaches. We further extend this concept to nonlinear models in the application of image de-autocorrelation.

eess.IV↗

arXiv2019

O-Net: A Convolutional Neural Network for Quantitative Photoacoustic Image Segmentation and Oximetry

Estimation of blood oxygenation with spectroscopic photoacoustic imaging is a promising tool for several biomedical applications. For this method to be quantitative, it relies on an accurate method of the light fluence in the tissue. This is difficult deep in heterogeneous tissue, where different wavelengths of light can experience significantly different attenuation. In this work, we developed a new deep neural network to simultaneously estimate the oxygen saturation in blood vessels and segment the vessels from the surrounding background tissue. The network was trained on estimated initial pressure distributions from three-dimensional Monte Carlo simulations of light transport in breast tissue. The network estimated vascular SO2 in less than 50 ms with as little as 5.1% median error and better than 95% segmentation accuracy. Overall, these results show that the blood oxygenation can be quantitatively mapped in real-time with high accuracy.

eess.IV↗