Enhanced complex local frequency elastography method for tumor viscoelastic shear modulus reconstruction

On the soft tissue ultrasound elastography using FEM based inversion approach

Elastography is a medical imaging modality that enables visualization of tissue stiffness. It involves quasi-static or harmonic mechanical stimulation of the tissue to generate a displacement field which is used as input in an inversion algorithm to reconstruct tissue elastic modulus. This paper considers quasi-static stimulation and presents a novel inversion technique for elastic modulus reconstruction. The technique follows an inverse finite element framework. Reconstructed elastic modulus maps produced in this technique do not depend on the initial guess, while it is computationally less involved than iterative reconstruction approaches. The method was first evaluated using simulated data (in-silico) where modulus reconstruction's sensitivity to displacement noise and elastic modulus was assessed. To demonstrate the method's performance, displacement fields of two tissue mimicking phantoms determined using three different motion tracking techniques were used as input to the developed elastography method to reconstruct the distribution of relative elastic modulus of the inclusion to background tissue. In the next stage, the relative elastic modulus of three clinical cases pertaining to liver cancer patient were determined. The obtained results demonstrate reasonably high elastic modulus reconstruction accuracy in comparison with similar direct methods. Also it is associated with reduced computational cost in comparison with iterative techniques, which suffer from convergence and uniqueness issues, following the same formulation concept. Moreover, in comparison with other methods which need initial guess, the presented method does not require initial guess while it is easy to understand and implement.

MR Elastography With Optimization-Based Phase Unwrapping and Traveling Wave Expansion-Based Neural Network (TWENN)

Magnetic Resonance Elastography (MRE) can characterize biomechanical properties of soft tissue for disease diagnosis and treatment planning. However, complicated wavefields acquired from MRE coupled with noise pose challenges for accurate displacement extraction and modulus estimation. Using optimization-based displacement extraction and Traveling Wave Expansion-based Neural Network (TWENN) modulus estimation, we propose a new pipeline for processing MRE images. An objective function with Dual Data Consistency (Dual-DC) has been used to ensure accurate phase unwrapping and displacement extraction. For the estimation of complex wavenumbers, a complex-valued neural network with displacement covariance as an input has been developed. A model of traveling wave expansion is used to generate training datasets for the network with varying levels of noise. The complex shear modulus map is obtained through fusion of multifrequency and multidirectional data. Validation using brain and liver simulation images demonstrates the practical value of the proposed pipeline, which can estimate the biomechanical properties with minimal root-mean-square errors when compared to state-of-the-art methods. Applications of the proposed method for processing MRE images of phantom, brain, and liver reveal clear anatomical features, robustness to noise, and good generalizability of the pipeline.

A wavelet neural operator based elastography for localization and quantification of tumors

BACKGROUND AND OBJECTIVES

The application of intelligent imaging techniques and deep learning in the field of computer-aided diagnosis and medical imaging have improved and accelerated the early diagnosis of many diseases. Elastography is an imaging modality where an inverse problem is solved to extract the elastic properties of tissues and subsequently mapped to anatomical images for diagnostic purposes. In the present work, we propose a wavelet neural operator-based approach for correctly learning the non-linear mapping of elastic properties directly from measured displacement field data.

METHODS

The proposed framework learns the underlying operator behind the elastic mapping and thus can map any displacement data from a family to the elastic properties. The displacement fields are first uplifted to a high-dimensional space using a fully connected neural network. On the lifted data, certain iterations are performed using wavelet neural blocks. In each wavelet neural block, the lifted data are decomposed into low, and high-frequency components using wavelet decomposition. To learn the most relevant patterns and structural information from the input, the neural network kernels are directly convoluted with the outputs of the wavelet decomposition. Thereafter the elasticity field is reconstructed from the outputs from convolution. The mapping between the displacement and the elasticity using wavelets is unique and remains stable during training.

RESULTS

The proposed framework is tested on several artificially fabricated numerical examples, including a benign-cum-malignant tumor prediction problem. The trained model was also tested on real Ultrasound-based elastography data to demonstrate the applicability of the proposed scheme in clinical usage. The proposed framework reproduces the highly accurate elasticity field directly from the displacement inputs.

CONCLUSIONS

The proposed framework circumvents different data pre-processing and intermediate steps utilized in traditional methods, hence providing an accurate elasticity map. The computationally efficient framework requires fewer epochs for training, which bodes well for its clinical usability for real-time predictions. The weights and biases from pre-trained models can also be employed for transfer learning, which reduces the effective training time with random initialization.

Reverberant magnetic resonance elastographic imaging using a single mechanical driver

Reverberant elastography provides fast and robust estimates of shear modulus; however, its reliance on multiple mechanical drivers hampers clinical utility. In this work, we hypothesize that for constrained organs such as the brain, reverberant elastography can produce accurate magnetic resonance elastograms with a single mechanical driver. To corroborate this hypothesis, we performed studies on healthy volunteers (n= 3); and a constrained calibrated brain phantom containing spherical inclusions with diameters ranging from 4-18 mm. In both studies (i.e. phantom and clinical), imaging was performed at frequencies of 50 and 70 Hz. We used the accuracy and contrast-to-noise ratio performance metrics to evaluate reverberant elastograms relative to those computed using the established subzone inversion method. Errors incurred in reverberant elastograms varied from 1.3% to 16.6% when imaging at 50 Hz and 3.1% and 16.8% when imaging at 70 Hz. In contrast, errors incurred in subzone elastograms ranged from 1.9% to 13% at 50 Hz and 3.6% to 14.9% at 70 Hz. The contrast-to-noise ratio of reverberant elastograms ranged from 63.1 to 73 dB compared to 65 to 66.2 dB for subzone elastograms. The average global brain shear modulus estimated from reverberant and subzone elastograms was 2.36 ± 0.07 kPa and 2.38 ± 0.11 kPa, respectively, when imaging at 50 Hz and 2.70 ± 0.20 kPa and 2.89 ± 0.60 kPa respectively, when imaging at 70 Hz. The results of this investigation demonstrate that reverberant elastography can produce accurate, high-quality elastograms of the brain with a single mechanical driver.

Ensemble Kalman inversion for magnetic resonance elastography

Magnetic resonance elastography (MRE) is an MRI-based diagnostic method for measuring mechanical properties of biological tissues. MRE measurements are processed by an inversion algorithm to produce a map of the biomechanical properties. In this paper a new and powerful method (ensemble Kalman inversion with level sets (EKI)) of MRE inversion is proposed and tested. The method has critical advantages: material property variation at disease boundaries can be accurately identified, and uncertainty of the reconstructed material properties can be evaluated by consequence of the probabilistic nature of the method. EKI is tested in 2D and 3D experiments with synthetic MRE data of the human kidney. It is demonstrated that the proposed inversion method is accurate and fast.

Biophysics involved in the process of tumor immune escape

Much of the current research into immune escape from cancer is focused on molecular and cellular biology, an area of biophysics that is easily overlooked. A large number of immune drugs entering the clinic are not effective for all patients. Apart from the molecular heterogeneity of tumors, the biggest reason for this may be that knowledge of biophysics has not been considered, and therefore an exploration of biophysics may help to address this challenge. To help researchers better investigate the relationship between tumor immune escape and biophysics, this paper provides a brief overview on recent advances and challenges of the biophysical factors and strategies by which tumors acquire immune escape and a comprehensive analysis of the relevant forces acting on tumor cells during immune escape. These include tumor and stromal stiffness, fluid interstitial pressure, shear stress, and viscoelasticity. In addition, advances in biophysics cannot be made without the development of detection tools, and this paper also provides a comprehensive summary of the important detection tools available at this stage in the field of biophysics.

Fast magnetic resonance elastography with multiphase radial encoding and harmonic motion sparsity based reconstruction

Objective. To achieve fast magnetic resonance elastography (MRE) at a low frequency for better shear modulus estimation of the brain. Approach. We proposed a multiphase radial DENSE MRE (MRD-MRE) sequence and an improved GRASP algorithm utilizing the sparsity of the harmonic motion (SH-GRASP) for fast MRE at 20 Hz. For the MRD-MRE sequence, the initial position encoded by spatial modulation of magnetization (SPAMM) was decoded by an arbitrary number of readout blocks without increasing the number of phase offsets. Based on the harmonic motion, a modified total variation and temporal Fourier transform were introduced to utilize the sparsity in the temporal domain. Both phantom and brain experiments were carried out and compared with that from multiphase Cartesian DENSE-MRE (MCD-MRE), and conventional gradient echo sequence (GRE-MRE). Reconstruction performance was also compared with GRASP and compressed sensing. Main results. Results showed the scanning time of a fully sampled image with four phase offsets for MRD-MRE was only 1/5 of that from GRE-MRE. The wave patterns and estimated stiffness maps were similar to those from MCD-MRE and GRE-MRE. With SH-GRASP, the total scan time could be shortened by additional 4 folds, achieving a total acceleration factor of 20. Better metric values were also obtained using SH-GRASP for reconstruction compared with other algorithms. Significance. The MRD-MRE sequence and SH-GRASP algorithm can be used either in combination or independently to accelerate MRE, showing the potentials for imaging the brain as well as other organs.

Deep neural networks for magnetic resonance elastography acceleration in thermal ablation monitoring

PURPOSE

To develop a deep neural network for accelerating magnetic resonance elastography (MRE) acquisition, to validate the ability to generate reliable MRE results with the down-sampled k-space data, and to demonstrate the feasibility of the proposed method in monitoring the stiffness changes during thermal ablation in a phantom study.

MATERIALS AND METHODS

MRE scans were performed with 60 Hz excitation on porcine ex-vivo liver gel phantoms in a 0.36T MRI scanner to generate the training dataset. The acquisition protocol was based on a spin-echo MRE pulse sequence with tailored motion-sensitive gradients to reduce echo time (TE). A U-Net based deep neural network was developed and trained to interpolate the missing data from down-sampled k-space. We calculated the errors of 80 sets magnitude/phase images reconstructed from the zero-filled, compressive sensing (CS) and deep learning (DL) method for comparison. The peak signal-to-noise rate (PSNR) and structural similarity (SSIM) of the magnitude/phase images were also calculated for comparison. The stiffness changes were recorded before, during, and after ablation. The mean stiffness values over the region of interest (ROI) were compared between the elastograms reconstructed from the fully-sampled k-space and interpolated k-space after thermal ablation.

RESULTS

The mean absolute error (MAE), PSNR, and SSIM of the proposed deep learning approach were significantly better than the results from the zero-filled method (p<0.0001) and CS (p<0.0001). The stiffness changes before and after thermal ablation assessed by the proposed approach (before: 7.7±1.1 kPa, after: 11.9±4.0 kPa, 4.2-kPa increase) gave close agreement with the values calculated from the fully-sampled data (before: 8.0±1.0 kPa, after: 12.6±4.2 kPa, 4.6-kPa increase). In contrast, the stiffness changes computed from the zero-filled method (before: 4.9±1.4 kPa, after: 5.6±2.8 kPa, 0.7-kPa increase) were substantially underestimated.

CONCLUSION

This study demonstrated the capability of the proposed deep learning method for rapid MRE acquisition and provided a promising solution for monitoring the MRI-guided thermal ablation. This article is protected by copyright. All rights reserved.

Viscoelastic parameters of invasive breast cancer in correlation with porous structure and elemental analysis data

BACKGROUND AND OBJECTIVE

Invasive ductal carcinoma (IDC) is the most common and aggressive type of breast cancer. As many clinical diagnoses are concerned with the tumor behavior at the compression, the IDC characterization using a compression test is performed in the present study. In the field of tissue characterization, most of the previous studies have focused on healthy and cancerous breast tissues at the cellular level; however, characterization of cancerous tissue at the tissue level has been under-represented, which is the target of the present study.

METHODS

Throughout this article, 18 IDC samples are tested using a ramp-relaxation test. The strain rate in the ramp phase is similar for all samples, whereas the strain level is set at 2,4 and 6%. The experimental stress-time data is interpolated by a viscoelastic model. Two relaxation times, as well as the instantaneous and long-term shear moduli, are calculated for each specimen.

RESULTS

The results show that the long-term and instantaneous shear moduli vary in the range of 0.31-17.03 kPa and 6.03-55.13 kPa, respectively. Our assessment of the viscoelastic parameters is accompanied by observing structural images of the IDCs and inspecting their elemental composition. It is concluded that IDCs with lower Magnesium to Calcium ratio (Mg:Ca) have smaller shear modulus and longer relaxation time, with a p-value of 0.001 and 0.01 for the correlation between Mg:Ca and long-term shear modulus, and Mg:Ca and early relaxation time.

CONCLUSIONS

Our identification of the IDC viscoelastic parameters can contribute to the IDC inspection at the tissue level. The results also provide useful information for modeling of breast cancer.

MR elastography inversion by compressive recovery

Direct inversion (DI) derives tissue shear modulus by inverting the Helmholtz equation. However, conventional DI is sensitive to data quality due to the ill-posed nature of Helmholtz inversion and thus providing reliable stiffness estimation can be challenging. This becomes more problematic in the case of estimating shear stiffness of the lung in which the low tissue density and short T2* result in considerably low signal-to-noise ratio during lung MRE. In the present study, we propose to perform MRE inversion by compressive recovery (MICRo). Such a technique aims to improve the numerical stability and the robustness to data noise of Helmholtz inversion by using prior knowledge on data noise and transform sparsity of the stiffness map. The developed inversion strategy was first validated in simulated phantoms with known stiffness. Next, MICRo was compared to the standard clinical multi-modal DI (MMDI) method forin vivoliver MRE in healthy subjects and patients with different stages of liver fibrosis. After establishing the accuracy of MICRo, we demonstrated the robustness of the proposed technique against data noise in lung MRE with healthy subjects. In simulated phantoms with single-directional or multi-directional waves, MICRo outperformed DI with Romano filter or Savitsky and Golay filter, especially when the stiffness and/or noise level was high. In hepatic MRE application, agreement was observed between MICRo and MMDI. Measuringin vivolung stiffness, MICRo demonstrated its advantages over filtered DI by yielding stable stiffness estimation at both residual volume and total lung capacity. These preliminary results demonstrate the potential value of the proposed technique and also warrant further investigation in a larger clinical population.