Experimental Phantom Data Research Articles

Spatial Ambiguity Correction in Coherence-Based Average Sound Speed Estimation.

Sound speed estimation can potentially correct the focusing errors in medical ultrasound. Maximizing the echo spatial coherence as a function of beamforming sound speed is a known technique to estimate the average sound speed. However, beamformation with changing sound speed causes a spatial shift of the echo signals resulting in noise and registration errors in the average sound speed estimates. We show that the spatial shift can be predicted and corrected, leading to superior sound speed estimates. Methods are presented for axial and 2-D location correction. Methods were evaluated using simulations and experimental phantom data. The location correction strategies improved the variance of sound speed estimates and reduced artifacts in the presence of strong backscatter variations. Limitations of the proposed methods and potential improvement strategies were evaluated.

Score-based generative model-assisted information compensation for high-quality limited-view reconstruction in photoacoustic tomography

Photoacoustic tomography (PAT) regularly operates in limited-view cases owing to data acquisition limitations. The results using traditional methods in limited-view PAT exhibit distortions and numerous artifacts. Here, a novel limited-view PAT reconstruction strategy that combines model-based iteration with score-based generative model was proposed. By incrementally adding noise to the training samples, prior knowledge can be learned from the complex probability distribution. The acquired prior is then utilized as constraint in model-based iteration. The information of missing views can be gradually compensated by cyclic iteration to achieve high-quality reconstruction. The performance of the proposed method was evaluated with the circular phantom and in vivo experimental data. Experimental results demonstrate the outstanding effectiveness of the proposed method in limited-view cases. Notably, the proposed method exhibits excellent performance in limited-view case of 70° compared with traditional method. It achieves a remarkable improvement of 203% in PSNR and 48% in SSIM for the circular phantom experimental data, and an enhancement of 81% in PSNR and 65% in SSIM for in vivo experimental data, respectively. The proposed method has capability of reconstructing PAT images in extremely limited-view cases, which will further expand the application in clinical scenarios.

Correcting gradient chain induced fat quantification errors in radial multi-echo Dixon imaging using a gradient modulation transfer function

Purpose: Multi-echo Stack-of-stars (SoS) radial k-space trajectories with golden angle ordering are becoming popular for free-breathing abdominal Dixon imaging and proton density fat fraction (PDFF) mapping. Gradient chain imperfections including eddy currents and system delays are known to affect the image quality of radial imaging and to confound the estimation of PDFF mapping. This work proposes a retrospective trajectory correction method based on a simple gradient modulation transfer function (GMTF) measurement to predict and correct gradient chain induced k-space trajectory errors.Methods: The GMTF was measured using the standard hardware of a 3 Tesla scanner on a phantom using the thin slice method and was applied to a 3D radial SoS Dixon imaging sequence. The impact of the GMTF-based correction on image reconstruction and PDFF quantification was investigated using numerical simulations and validated on experimental phantom data as well as on in vivo leg and liver data of healthy volunteers.Results: Correcting the k-space trajectories with the measured GMTF during image reconstruction reduced PDFF quantification errors for phantom and in vivo acquisitions. A Bland-Altman comparison of the measured PDFF phantom and reference data confirmed that the GMTF correction narrowed down the limits of agreement (LoA) from 1.3% ± 8.1% (uncorrected) to 1.9% ± 5.4% (GMTF-corrected) over the full PDFF range (0%–100%) and from −0.26% ± 2.8% (uncorrected) to 0.12% ± 1.5% (GMTF-corrected) within the 0%–50% PDFF range. Liver PDFF estimation was improved by reducing the standard deviation of the mean liver PDFF and the bias of the mean liver PDFF for all subjects.Conclusion: The proposed GMTF-based k-space trajectory correction is a fast alternative method for avoiding PDFF quantitation errors caused by gradient-system induced k-space trajectory errors in 3D radial multi-echo gradient-echo acquisitions.

Simulated and experimental phantom data for multi-center quality assurance of quantitative susceptibility maps at 3 T, 7 T and 9.4 T

PurposeTo develop methods for quality assurance of quantitative susceptibility mapping (QSM) using MRI at different magnetic field strengths, and scanners, using different MR-sequence protocols, and post-processing pipelines. MethodsWe built a custom phantom based on iron in two forms: homogeneous susceptibility (‘free iron’) and with fine-scaled variations in susceptibility (‘clustered iron’) at different iron concentrations. The phantom was measured at 3.0 T (two scanners), 7.0 T and 9.4 T using multi-echo, gradient echo acquisition sequences. A digital phantom analogue to the iron-phantom, tailored to obtain similar results as in experimentation was developed, with similar geometry and susceptibility values. Morphology enabled dipole inversion was applied to the phase images to obtain QSM for experimental and simulated data using the MEDI + 0 approach for background regularization. ResultsAcross all scanners, QSM-values showed a linear increase with iron concentrations. The QSM-relaxivity was 0.231 ± 0.047 ppm/mM for free and 0.054 ± 0.013 ppm/mM for clustered iron, with adjusted determination coefficients (DoC) ≥ 0.87. Similarly, the simulations yielded linear increases (DoC ≥ 0.99). In both the experimental and digital phantoms, the estimated molar susceptibility was lower with clustered iron, because clustering led to highly localized field effects. ConclusionOur iron phantom can be used to evaluate the capability of QSM to detect local variations in susceptibility across different field strengths, when using different MR-sequence protocols. The devised simulation method captures the effect of iron clustering in QSM as seen experimentally and could be used in the future to optimize QSM processing pipelines and achieve higher accuracy for local field effects, as also seen in Alzheimer’s beta-amyloid plaques.

Reconstruction of conductivity distribution variation with Tikhonov and wavelet frame combined method for electrical impedance tomography

Electrical impedance tomography (EIT) is receiving considerable research interest in a variety of applications. With this technique, it is possible to reconstruct conductivity distribution inside the detected region. Note that reconstruction of conductivity distribution is an ill-posed inverse problem. To deal with this problem, Tikhonov regularization method has been preferred. However, this method suffers from poor reconstruction quality. In this work, a novel approach which combines Tikhonov regularization method with wavelet frame is proposed for image reconstruction of EIT. The proposed method is superior to the popular Tikhonov regularization method in enforcing sparse of the solution and enhancing sharp feature. Simulation work has been conducted to validate the performance of the proposed method. Compared with Landweber method, total variation (TV) regularization method, and Tikhonov regularization method, reconstructions of six different models show that images reconstructed by the proposed method have better quality and are more robust to noise. In addition, image reconstruction is also performed based on phantom experimental data. The results further demonstrate that the proposed method outperforms other three methods since the inclusion has been more accurately reconstructed, and there are almost no artifacts in the reconstructed images.

Ultrasonic envelope statistical analysis in motion compensated images during temperature change

Motion compensation was applied in the envelope statistical analysis to develop robust thermometry for in vivo situations. Numerical data were reproduced with the temporal change in the scatterer distribution due to thermal expansion and arbitrary translational motions, and experimental phantom data were obtained under heating with the probe motion. Additionally, the case under respiratory motion was evaluated using the data collected from in vivo rat tumor. Ultrasound signals were acquired using a 7.5 MHz linear probe, and their misalignments of envelopes due to the motions were compensated by a block-matching-based motion estimator. The absolute change in the Nakagami shape parameter, in each frame was calculated by normalizing with the initial frame to indicate the temperature change. The uncompensated with physical motions deviated from that without motion, whereas the motion-compensated numerical and experimental data suppressed the rapid or gradual change and showed the same trend of without motion.

HYPR4D kernel method on TOF PET data with validations including image-derived input function

BackgroundPositron emission tomography (PET) images are typically noisy especially in dynamic imaging where the PET data are divided into a number of short temporal frames often with a low number of counts. As a result, image features such as contrast and time–activity curves are highly variable. Noise reduction in PET is thus essential. Typical noise reduction methods tend to not preserve image features/patterns (e.g. contrast and size dependent) accurately. In this work, we report the first application of our HYPR4D kernel method on time-of-flight (TOF) PET data (i.e. PSF-HYPR4D-K-TOFOSEM). The proposed HYPR4D kernel method makes use of the mean 4D high frequency features and inconsistent noise patterns over OSEM subsets as well as the low noise property of the early reconstruction updates to achieve prior-free de-noising. The method was implemented and tested on the GE SIGNA PET/MR and was compared to the TOF reconstructions with PSF resolution modeling available on the system, namely PSF-TOFOSEM with and without standard post filter and PSF-TOFBSREM (TOF Q.Clear) with various beta values (regularization strengths).ResultsResults from experimental contrast phantom and human subject data with various PET tracers showed that the proposed method provides more robust and accurate image features compared to other regularization methods. The preservation of contrast for the PSF-HYPR4D-K-TOFOSEM was observed to be better and less dependent on the contrast and size of the target structures as compared to TOF Q.Clear and PSF-TOFOSEM with filter. At the same contrast level, PSF-HYPR4D-K-TOFOSEM achieved better 4D noise suppression than other methods (e.g. >2 times lower noise than TOF Q.Clear at the highest contrast). We also present a novel voxel search method to obtain an image-derived input function (IDIF) and demonstrate that the obtained IDIF is the most quantitative w.r.t. the measured blood samples when the acquired data are reconstructed with PSF-HYPR4D-K-TOFOSEM.ConclusionsThe overall results support superior performance of the PSF-HYPR4D-K-TOFOSEM for TOF PET data and demonstrate that the proposed method is likely suitable for all imaging tasks including the generation of IDIF without requiring any prior information as well as further improving the effective sensitivity of the imaging system.

A Multiobjective Comparative Analysis of Reconstruction Algorithms in the Context of Low-Statistics 90Y-PET Imaging

The popularity of yttrium-90 ( <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">90</sup> Y) PET is growing. However, due to the very low branching ratio of <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">90</sup> Y ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$3.2\times 10^{-5}$ </tex-math></inline-formula> ), images reconstructed are characterized by a high noise level and positive bias in low-activity regions. To overcome this problem, some algorithms use penalized reconstructions, and others allow for negative values in the image. Recently, a post-processing method has also been proposed that removes the induced negative values while maintaining bias reduction. The work presented in this article aims to evaluate and compare these methods to guide the reader in the choice of the best-suited reconstruction algorithm and associated parameters. First, several algorithms were tested using experimental phantom data. Pareto fronts and Pareto sets from the multiobjective optimization formalism were used for the comparison. Next, a dosimetric study (using phantom and patient data) was conducted to assess the final impact of these algorithms. The lowest biases were reached by unconstrained algorithms. When compared to penalized algorithms, the latter allowed for noise reduction at a fixed level of bias, with the best results obtained using a penalty based on relative differences. A good compromise between noise and bias could be reached by combining penalty, early stopping of iterative algorithms, unconstrained algorithms, and post-processing.

Partial Hadamard encoded synthetic transmit aperture for high frame rate imaging with minimal l 2-norm least squares method

Objective. Synthetic transmit aperture (STA) ultrasound imaging is well known for ideal focusing in the full field of view. However, it suffers from low signal-to-noise ratio (SNR) and low frame rate, because each transducer element must be activated individually. In our previous study, we encoded all the transducer elements with partial Hadamard matrix and reconstructed the complete STA dataset with compressed sensing (CS) algorithm (CS-STA). As all the elements are activated in each transmission and the number of transmissions is smaller than that of STA, this method can achieve higher SNR and higher frame rate. Its main drawback is the time-consuming CS reconstruction (∼hours). In this study, we propose to accelerate the complete STA dataset reconstruction with minimal l 2-norm least squares method. Approach. Partial Hadamard apodized plane wave (PW) transmissions were performed to acquire the PW dataset. Thereafter, the complete STA dataset can be reconstructed from the PW dataset with minimal l 2-norm least squares method. Due to the orthogonality of partial Hadamard matrix, the minimal l 2-norm least squares solution can be easily calculated. Main results. The proposed method is tested with simulation data and experimental phantom and in-vivo data. The results demonstrate that the proposed method achieves ∼5 × 103 times faster reconstruction speed than CS algorithm. The simulation results demonstrate that the proposed method is capable of achieving the same accuracy as the conventional CS-STA method for the STA dataset reconstruction. The simulations, phantom and in-vivo experiments show that the proposed method is capable of improving the generalized contrast-to-noise ratio (gCNR) and SNR with maintained spatial resolution and fewer transmissions, compared with STA. Significance. In conclusion, the improved image quality and reduced computational time of LS-STA pave the way for its real-time applications in the clinics.

Bi-Directional Semi-Supervised Training of Convolutional Neural Networks for Ultrasound Elastography Displacement Estimation.

The performance of ultrasound elastography (USE) heavily depends on the accuracy of displacement estimation. Recently, convolutional neural networks (CNNs) have shown promising performance in optical flow estimation and have been adopted for USE displacement estimation. Networks trained on computer vision images are not optimized for USE displacement estimation since there is a large gap between the computer vision images and the high-frequency radio frequency (RF) ultrasound data. Many researchers tried to adopt the optical flow CNNs to USE by applying transfer learning to improve the performance of CNNs for USE. However, the ground-truth displacement in real ultrasound data is unknown, and simulated data exhibit a domain shift compared to the real data and are also computationally expensive to generate. To resolve this issue, semisupervised methods have been proposed in which the networks pretrained on computer vision images are fine-tuned using real ultrasound data. In this article, we employ a semisupervised method by exploiting the first- and second-order derivatives of the displacement field for regularization. We also modify the network structure to estimate both forward and backward displacements and propose to use consistency between the forward and backward strains as an additional regularizer to further enhance the performance. We validate our method using several experimental phantom and in vivo data. We also show that the network fine-tuned by our proposed method using experimental phantom data performs well on in vivo data similar to the network fine-tuned on in vivo data. Our results also show that the proposed method outperforms current deep learning methods and is comparable to computationally expensive optimization-based algorithms.

Direct left-ventricular global longitudinal strain (GLS) computation with a fully convolutional network

This study's purpose was to develop a direct MRI-based, deep-learning semantic segmentation approach for computing global longitudinal strain (GLS), a known metric for detecting left-ventricular (LV) cardiotoxicity in breast cancer. Displacement Encoding with Stimulated Echoes cardiac image phases acquired from 30 breast cancer patients and 30 healthy females were unwrapped via a DeepLabV3 + fully convolutional network (FCN). Myocardial strains were directly computed from the unwrapped phases with the Radial Point Interpolation Method. FCN-unwrapped phases of a phantom’s rotating gel were validated against quality-guided phase-unwrapping (QGPU) and robust transport of intensity equation (RTIE) phase-unwrapping. FCN performance on unwrapping human LV data was measured with F1 and Dice scores versus QGPU ground-truth. The reliability of FCN-based strains was assessed against RTIE-based strains with Cronbach's alpha (C-α) intraclass correlation coefficient. Mean squared error (MSE) of unwrapping the phantom experiment data at 0 dB signal-to-noise ratio were 1.6, 2.7 and 6.1 with FCN, QGPU and RTIE techniques. Human data classification accuracies were F1 = 0.95 (Dice = 0.96) with FCN and F1 = 0.94 (Dice = 0.95) with RTIE. GLS results from FCN and RTIE were −16 ± 3% vs. −16 ± 3% (C-α = 0.9) for patients and −20 ± 3% vs. −20 ± 3% (C-α = 0.9) for healthy subjects. The low MSE from the phantom validation demonstrates accuracy of phase-unwrapping with the FCN and comparable human subject results versus RTIE demonstrate GLS analysis accuracy. A deep-learning methodology for phase-unwrapping in medical images and GLS computation was developed and validated in a heterogeneous cohort.

Development of three-dimensional integral-type reconstruction formula for magnetic resonance elastography.

The viscoelasticity (storage modulus and loss modulus) of living tissues is known to be related to diseases. Magnetic resonance elastography (MRE) is a quantitative method for non-invasive measuring viscoelasticity. The viscoelasticity is calculated from the elastic wave images using an inversion algorithm. The estimation accuracy of the inversion algorithm is degraded by background noise. This study aims to propose novel inversion algorithms that are applicable for noisy elastic wave images. The proposed algorithms are based on the Voigt-type viscoelastic equation. The algorithms are designed to improve the noise robustness by avoiding direct differentiation of measurement data by virtue of Green's formula. Similarly, stabilization is introduced to the curl-operator which works to eliminate the compression waves in measurement data. To clarify the characteristics of the algorithms, the proposed algorithms were compared with the conventional algorithms using isotropic and anisotropic voxel numerical simulations and phantom experimental data. From the results of the numerical simulations, normalized errors of stiffness of proposed algorithms were 3% or less. The proposed algorithms mostly showed better results than the conventional algorithms despite noisy elastic wave images. From the gel phantom experiment, we confirmed the same tendency as the characteristics of the algorithms observed in the numerical simulation results. We have developed a novel inversion algorithm and evaluated it quantitatively. The results confirm that the proposed algorithms are highly quantitative and noise-robust methods for estimating storage and loss modulus regardless of noise, voxel anisotropy, and propagation direction. Therefore, the proposed algorithms will appropriate to various three-dimensional MRE systems.

A two-stage image reconstruction strategy for electrical impedance tomography

Electrical impedance tomography (EIT) is a potential and promising tomographic technique. Based on a reconstruction strategy, conductivity distribution can be imaged by processing boundary measurements. It should be noticed that the process of image reconstruction involves the solution of a nonlinear ill-posed inverse problem. To tackle this problem, a novel two-stage image reconstruction strategy is proposed in this work. It combines the advantages of total generalized variation regularization method and tight wavelet approach. The solution of the proposed method is acquired by employing alternating minimization algorithm and spilt Bregman algorithm. In the numerical simulation, reconstruction of five models is studied. Aside from the visual observation, we have also validated the proposed method with quantitative comparison. Meanwhile, the impact of noise on the reconstruction is considered. Furthermore, the proposed method is evaluated by phantom experimental data. The simulation and experimental results have demonstrated the superior performance of the proposed method in visualizing conductivity distribution.

Tattoo tomography: Freehand 3D photoacoustic image reconstruction with an optical pattern

PurposePhotoacoustic tomography (PAT) is a novel imaging technique that can spatially resolve both morphological and functional tissue properties, such as vessel topology and tissue oxygenation. While this capacity makes PAT a promising modality for the diagnosis, treatment, and follow-up of various diseases, a current drawback is the limited field of view provided by the conventionally applied 2D probes.MethodsIn this paper, we present a novel approach to 3D reconstruction of PAT data (Tattoo tomography) that does not require an external tracking system and can smoothly be integrated into clinical workflows. It is based on an optical pattern placed on the region of interest prior to image acquisition. This pattern is designed in a way that a single tomographic image of it enables the recovery of the probe pose relative to the coordinate system of the pattern, which serves as a global coordinate system for image compounding.ResultsTo investigate the feasibility of Tattoo tomography, we assessed the quality of 3D image reconstruction with experimental phantom data and in vivo forearm data. The results obtained with our prototype indicate that the Tattoo method enables the accurate and precise 3D reconstruction of PAT data and may be better suited for this task than the baseline method using optical tracking.ConclusionsIn contrast to previous approaches to 3D ultrasound (US) or PAT reconstruction, the Tattoo approach neither requires complex external hardware nor training data acquired for a specific application. It could thus become a valuable tool for clinical freehand PAT.

Exploring CNN potential in discriminating benign and malignant calcifications in conventional and dual-energy FFDM: simulations and experimental observations.

Purpose: Deep convolutional neural networks (CNN) have demonstrated impressive success in various image classification tasks. We investigated the use of CNNs to distinguish between benign and malignant microcalcifications, using either conventional or dual-energy mammography x-ray images. The two kinds of calcifications, known as type-I (calcium oxalate crystals) and type-II (calcium phosphate aggregations), have different attenuation properties in the mammographic energy range. However, variations in microcalcification shape, size, and density as well as compressed breast thickness and breast tissue background make this a challenging discrimination task for the human visual system. Approach: Simulations (conventional and dual-energy mammography) and phantom experiments (conventional mammography only) were conducted using the range of breast thicknesses and randomly shaped microcalcifications. The off-the-shelf Resnet-18 CNN was trained on the regions of interest with calcification clusters of the two kinds. Results: Both Monte Carlo simulations and experimental phantom data suggest that deep neural networks can be trained to separate the two classes of calcifications with high accuracy, using dual-energy mammograms. Conclusions: Our work shows the encouraging results of using the CNNs for non-invasive testing for type-I and type-II microcalcifications and may stimulate further research in this area with expanding presence of the novel breast imaging modalities like dual-energy mammography or systems using photon-counting detectors.

Deep Convolutional Neural Networks for Displacement Estimation in ARFI Imaging.

Ultrasound elasticity imaging in soft tissue with acoustic radiation force requires the estimation of displacements, typically on the order of several microns, from serially acquired raw data A-lines. In this work, we implement a fully convolutional neural network (CNN) for ultrasound displacement estimation. We present a novel method for generating ultrasound training data, in which synthetic 3-D displacement volumes with a combination of randomly seeded ellipsoids are created and used to displace scatterers, from which simulated ultrasonic imaging is performed using Field II. Network performance was tested on these virtual displacement volumes, as well as an experimental ARFI phantom data set and a human in vivo prostate ARFI data set. In the simulated data, the proposed neural network performed comparably to Loupas's algorithm, a conventional phase-based displacement estimation algorithm; the rms error was [Formula: see text] for the CNN and 0.73 [Formula: see text] for Loupas. Similarly, in the phantom data, the contrast-to-noise ratio (CNR) of a stiff inclusion was 2.27 for the CNN-estimated image and 2.21 for the Loupas-estimated image. Applying the trained network to in vivo data enabled the visualization of prostate cancer and prostate anatomy. The proposed training method provided 26 000 training cases, which allowed robust network training. The CNN had a computation time that was comparable to Loupas's algorithm; further refinements to the network architecture may provide an improvement in the computation time. We conclude that deep neural network-based displacement estimation from ultrasonic data is feasible, providing comparable performance with respect to both accuracy and speed compared to current standard time-delay estimation approaches.

Dynamic PET image reconstruction utilizing intrinsic data-driven HYPR4D denoising kernel.

Reconstructed PET images are typically noisy, especially in dynamic imaging where the acquired data are divided into several short temporal frames. High noise in the reconstructed images translates to poor precision/reproducibility of image features. One important role of "denoising" is therefore to improve the precision of image features. However, typical denoising methods achieve noise reduction at the expense of accuracy. In this work, we present a novel four-dimensional (4D) denoised image reconstruction framework, which we validate using 4D simulations, experimental phantom, and clinical patient data, to achieve 4D noise reduction while preserving spatiotemporal patterns/minimizing error introduced by denoising. Our proposed 4D denoising operator/kernel is based on HighlY constrained backPRojection (HYPR), which is applied either after each update of OSEM reconstruction of dynamic 4D PET data or within the recently proposed kernelized reconstruction framework inspired by kernel methods in machine learning. Our HYPR4D kernel makes use of the spatiotemporal high frequency features extracted from a 4D composite, generated within the reconstruction, to preserve the spatiotemporal patterns and constrain the 4D noise increment of the image estimate. Results from simulations, experimental phantom, and patient data showed that the HYPR4D kernel with our proposed 4D composite outperformed other denoising methods, such as the standard OSEM with spatial filter, OSEM with 4D filter, and HYPR kernel method with the conventional 3D composite in conjunction with recently proposed High Temporal Resolution kernel (HYPRC3D-HTR), in terms of 4D noise reduction while preserving the spatiotemporal patterns or 4D resolution within the 4D image estimate. Consequently, the error in outcome measures obtained from the HYPR4D method was less dependent on the region size, contrast, and uniformity/functional patterns within the target structures compared to the other methods. For outcome measures that depend on spatiotemporal tracer uptake patterns such as the nondisplaceable Binding Potential (BPND ), the root mean squared error in regional mean of voxel BPND values was reduced from ~8% (OSEM with spatial or 4D filter) to ~3% using HYPRC3D-HTR and was further reduced to ~2% using our proposed HYPR4D method for relatively small target structures (~10mm in diameter). At the voxel level, HYPR4D produced two to four times lower mean absolute error in BPND relative to HYPRC3D-HTR. As compared to conventional methods, our proposed HYPR4D method can produce more robust and accurate image features without requiring any prior information.

Material Decomposition in Spectral CT Using Deep Learning: A Sim2Real Transfer Approach

The state-of-the art for solving the nonlinear material decomposition problem in spectral computed tomography is based on variational methods, but these are computationally slow and critically depend on the particular choice of the regularization functional. Convolutional neural networks have been proposed for addressing these issues. However, learning algorithms require large amounts of experimental data sets. We propose a deep learning strategy for solving the material decomposition problem based on a U-Net architecture and a Sim2Real transfer learning approach where the knowledge that we learn from synthetic data is transferred to a real-world scenario. In order for this approach to work, synthetic data must be realistic and representative of the experimental data. For this purpose, numerical phantoms are generated from human CT volumes of the KiTS19 Challenge dataset, segmented into specific materials (soft tissue and bone). These volumes are projected into sinogram space in order to simulate photon counting data, taking into account the energy response of the scanner. We compared projection- and image-based decomposition approaches where the network is trained to decompose the materials either in the projection or in the image domain. The proposed Sim2Real transfer strategies are compared to a regularized Gauss-Newton (RGN) method on synthetic data, experimental phantom data and human thorax data.

Fusion of Magnetic Resonance and Ultrasound Images for Endometriosis Detection.

This paper introduces a new fusion method for magnetic resonance (MR) and ultrasound (US) images, which aims at combining the advantages of each modality, i.e., good contrast and signal to noise ratio for the MR image and good spatial resolution for the US image. The proposed algorithm is based on two inverse problems, performing a super-resolution of the MR image and a denoising of the US image. A polynomial function is introduced to model the relationships between the gray levels of the two modalities. The resulting inverse problem is solved using a proximal alternating linearized minimization framework. The accuracy and the interest of the fusion algorithm are shown quantitatively and qualitatively via evaluations on synthetic and experimental phantom data.

An efficient forward model based on the Lattice Boltzmann method for optical tomography

Optical tomography is a powerful tool for preclinical and clinical biomedical research, which enables quantitative observation and precise localization of regions of interest within biological tissues. However, the excessive time caused by the forward model of optical tomography is the main limitation of its application in many fields, such as the dynamic imaging. In this paper, we present an efficient forward model based on the Lattice Boltzmann method (LBM), which is realized by radiation transfer equation discretization to simplify the mathematical structures and apply it for optical tomography. To demonstrate the feasibility of the proposed model for optical tomography, we carried out numerical cylinder simulation to validate the simulated light source distribution. To evaluate the performance of the proposed model for optical tomography, we performed a numerical phantom and a physical phantom experiments on a hybrid fluorescence diffuse optical tomography/X-CT imaging system to observe the tomographic reconstruction, by using the simulated phantom data and the experimental phantom data, respectively. The results showed that our proposed forward model obtained similar light source distribution comparing with the standard Monte Carlo method and the cosine similarity was about 96%. Further, our proposed forward model greatly improves the efficiency of optical tomography without a degradation of quality. The LBM provided about 5 times speed enhancement for phantom experiment and 2 times contrast-to-noise ratio boost for physical phantom experiment. Experimental results showed that our proposed model has large potential for performance improvement in optical tomography.