In vivo monitoring of microwave ablation in a porcine model using ultrasonic differential attenuation coefficient intercept imaging

Suppressing the HIFU interference in ultrasound guiding images with a diffusion-based deep learning model

BACKGROUND AND OBJECTIVES

In ultrasound guided high-intensity focused ultrasound (HIFU) surgery, it is necessary to transmit sound waves at different frequencies simultaneously using two transducers: one for the HIFU therapy and another for the ultrasound imaging guidance. In this specific setting, real-time monitoring of non-invasive surgery is challenging due to severe contamination of the ultrasound guiding images by strong acoustic interference from the HIFU sonication.

METHODS

This paper proposed the use of a deep learning (DL) solution, specifically a diffusion implicit model, to suppress the HIFU interference. We considered the images contaminated with HIFU interference as low-resolution images, and those free from interference as high-resolution. While suppressing HIFU interference using the diffusion implicit (HIFU-Diff) model, the task was transformed into generating a high-resolution image through a series of forward diffusion steps and reverse sampling. A series of ex-vivo and in-vivo experiments, conducted under various parameters, were designed to validate the performance of the proposed network.

RESULTS

Quantitative evaluation and statistical analysis demonstrated that the HIFU-Diff network achieved superior performance in reconstructing interference-free images under a variety of ex-vivo and in-vivo conditions, compared to the most commonly used notch filtering and the recent 1D FUS-Net deep learning network. The HIFU-Diff maintains high performance with 'unseen' datasets from separate experiments, and its superiority is more pronounced under strong HIFU interferences and in complex in-vivo situations. Furthermore, the reconstructed interference-free images can also be used for quantitative attenuation imaging, indicating that the network preserves acoustic characteristics of the ultrasound images.

CONCLUSIONS

With the proposed technique, HIFU therapy and the ultrasound imaging can be conducted simultaneously, allowing for real-time monitoring of the treatment process. This capability could significantly enhance the safety and efficacy of the non-invasive treatment across various clinical applications. To the best of our knowledge, this is the first diffusion-based model developed for HIFU interference suppression.

Multiple ultrasonic parametric imaging for the detection and monitoring of high-intensity focused ultrasound ablation

Numerous quantitative ultrasound imaging techniques have demonstrated superior monitoring performance for thermal ablation when compared to conventional ultrasonic B-mode imaging. However, the absence of comparative studies involving various quantitative ultrasound imaging techniques hinders further clinical exploration. In this study, we simultaneously reconstructed ultrasonic Nakagami imaging, ultrasonic horizontally normalized Shannon entropy (hNSE) imaging, and ultrasonic differential attenuation coefficient intercept (DACI) imaging from ultrasound backscattered envelope data collected during high-intensity focused ultrasound ablation treatment. We comprehensively investigated their performance differences through qualitative and quantitative analyses, including the calculation of contrast-to-noise ratios (CNR) for ultrasonic images, receiver operating characteristic (ROC) analysis with corresponding indicators, the analysis of lesion area fitting relationships, and computational time consumption comparison. The mean CNR of hNSE imaging was 10.98 ± 4.48 dB, significantly surpassing the 3.82 ± 1.40 dB (p < 0.001, statistically significant) of Nakagami imaging and the 2.45 ± 0.74 dB (p < 0.001, statistically significant) of DACI imaging. This substantial difference underscores that hNSE imaging offers the highest contrast resolution for lesion recognition. Furthermore, we evaluated the ability of multiple ultrasonic parametric imaging to detect thermal ablation lesions using ROC curves. The area under the curve (AUC) for hNSE was 0.874, exceeding the values of 0.848 for Nakagami imaging and 0.832 for DACI imaging. Additionally, hNSE imaging exhibited the strongest linear correlation coefficient (R = 0.92) in the comparison of lesion area fitting, outperforming Nakagami imaging (R = 0.87) and DACI imaging (R = 0.85). hNSE imaging also performs best in real-time monitoring with each frame taking 6.38 s among multiple ultrasonic parametric imaging. Our findings unequivocally demonstrate that hNSE imaging excels in monitoring HIFU ablation treatment and holds the greatest potential for further clinical exploration.

Suppressing HIFU interference in ultrasound images using 1D U-Net-based neural networks

Objective.One big challenge with high-intensity focused ultrasound (HIFU) is that the intense acoustic interference generated by HIFU irradiation overwhelms the B-mode monitoring images, compromising monitoring effectiveness. This study aims to overcome this problem using a one-dimensional (1D) deep convolutional neural network.Approach. U-Net-based networks have been proven to be effective in image reconstruction and denoising, and the two-dimensional (2D) U-Net has already been investigated for suppressing HIFU interference in ultrasound monitoring images. In this study, we propose that the one-dimensional (1D) convolution in U-Net-based networks is more suitable for removing HIFU artifacts and can better recover the contaminated B-mode images compared to 2D convolution.Ex vivoandinvivoHIFU experiments were performed on a clinically equivalent ultrasound-guided HIFU platform to collect image data, and the 1D convolution in U-Net, Attention U-Net, U-Net++, and FUS-Net was applied to verify our proposal.Main results.All 1D U-Net-based networks were more effective in suppressing HIFU interference than their 2D counterparts, with over 30% improvement in terms of structural similarity (SSIM) to the uncontaminated B-mode images. Additionally, 1D U-Nets trained usingex vivodatasets demonstrated better generalization performance ininvivoexperiments.Significance.These findings indicate that the utilization of 1D convolution in U-Net-based networks offers great potential in addressing the challenges of monitoring in ultrasound-guided HIFU systems.

Ultrasound Homodyned-K Contrast-Weighted Summation Parametric Imaging Based on H-scan for Detecting Microwave Ablation Zones

The homodyned-K (HK) distribution is a generalized model of envelope statistics whose parameters α (the clustering parameter) and k (the coherent-to-diffuse signal ratio) can be used to monitor the thermal lesions. In this study, we proposed an ultrasound HK contrast-weighted summation (CWS) parametric imaging algorithm based on the H-scan technique and investigated the optimal window side length (WSL) of the HK parameters estimated by the XU estimator (an estimation method based on the first moment of the intensity and two log-moments, which was used in the proposed algorithm) through phantom simulations. H-scan diversified ultrasonic backscattered signals into low- and high-frequency passbands. After envelope detection and HK parameter estimation for each frequency band, the α and k parametric maps were obtained, respectively. According to the contrast between the target region and background, the (α or k) parametric maps of the dual-frequency band were weighted and summed, and then the CWS images were yielded by pseudo-color imaging. The proposed HK CWS parametric imaging algorithm was used to detect the microwave ablation coagulation zones of porcine liver ex vivo under different powers and treatment durations. The performance of the proposed algorithm was compared with that of the conventional HK parametric imaging and frequency diversity and compounding Nakagami imaging algorithms. For two-dimensional HK parametric imaging, it was found that a WSL equal to 4 pulse lengths of the transducer was sufficient for estimating the α and k parameters in terms of both parameter estimation stability and parametric imaging resolution. The HK CWS parametric imaging provided an improved contrast-to-noise ratio over conventional HK parametric imaging, and the HK α_cws parametric imaging achieved the best accuracy and Dice score of coagulation zone detection.

A Review of Quantitative Ultrasound-Based Approaches to Thermometry and Ablation Zone Identification Over the Past Decade

Percutaneous thermal therapy is an important clinical treatment method for some solid tumors. It is critical to use effective image visualization techniques to monitor the therapy process in real time because precise control of the therapeutic zone directly affects the prognosis of tumor treatment. Ultrasound is used in thermal therapy monitoring because of its real-time, non-invasive, non-ionizing radiation, and low-cost characteristics. This paper presents a review of nine quantitative ultrasound-based methods for thermal therapy monitoring and their advances over the last decade since 2011. These methods were analyzed and compared with respect to two applications: ultrasonic thermometry and ablation zone identification. The advantages and limitations of these methods were compared and discussed, and future developments were suggested.

Detection of microwave ablation coagulation areas using ultrasound Nakagami imaging based on Gaussian pyramid decomposition: A feasibility study

In this paper, we explored the feasibility of using ultrasound Nakagami-m parametric imaging based on Gaussian pyramid decomposition (GPD) to detect microwave ablation coagulation areas. Monte Carlo simulation and phantom simulation results demonstrated that a 2-layer GPD model was sufficient to achieve the same m parameter estimation accuracy, smoothness and resolution as 3-layer and 4-layer. The performances of GPD, moment-based estimator (MBE) and window-modulated compounding (WMC) algorithms were compared in terms of parameter estimation, smoothness, resolution and contrast-to-noise (CNR). Results showed that the m parameter estimation obtained by GPD algorithm was better than that of MBE and WMC algorithms except the small window size (27 × 5). When using a window size of >3 pulse lengths, GPD algorithm could achieve better smoothness and CNR than MBE and WMC algorithms, but there was a certain loss of axial resolution. The computation time of GPD algorithm was less than that of WMC algorithm, while about 2.24 times that of MBE algorithm. Experimental results of porcine liver microwave ablation ex vivo (n = 20) illustrated that the average areas under the operating characteristic curve (AUCs) of Nakagami m_GPD, m_MBE and m_WMC parametric imaging and homodyned-K (HK) α and k parametric imaging to detect coagulation areas were significantly improved by polynomial approximation (PAX). Kruskal-Wallis test showed that the accuracy of coagulation area detection obtained by PAX imaging of m_GPD parameter had no significant difference with that of m_MBE, m_WMC, HK_α and HK_k parameters. This preliminary study suggested that Nakagami imaging based on GPD algorithm may have the potential to detect microwave ablation coagulation areas.

Ultrasound Entropy Imaging for Detection and Monitoring of Thermal Lesion During Microwave Ablation of Liver

Ultrasonic B-mode imaging offers non-invasive and real-time monitoring of thermal ablation treatment in clinical use, however it faces challenges of moderate lesion-normal contrast and detection accuracy. Quantitative ultrasound imaging techniques have been proposed as promising tools to evaluate the microstructure of ablated tissue. In this study, we introduced Shannon entropy, a non-model based statistical measurement of disorder, to quantitatively detect and monitor microwave-induced ablation in porcine livers. Performance of typical Shannon entropy (TSE), weighted Shannon entropy (WSE), and horizontally normalized Shannon entropy (hNSE) were explored and compared with conventional B-mode imaging. TSE estimated from non-normalized probability distribution histograms was found to have insufficient discernibility of different disorder of data. WSE that improves from TSE by adding signal amplitudes as weights obtained area under receiver operating characteristic (AUROC) curve of 0.895, whereas it underestimated the periphery of lesion region. hNSE provided superior ablated area prediction with the correlation coefficient of 0.90 against ground truth, AUROC of 0.868, and remarkable lesion-normal contrast with contrast-to-noise ratio of 5.86 which was significantly higher than other imaging methods. Data distributions shown in horizontally normalized probability distribution histograms indicated that the disorder of backscattered envelope signal from ablated region increased as treatment went on. These findings suggest that hNSE imaging could be a promising technique to assist ultrasound guided percutaneous thermal ablation.

Monitoring microwave ablation using ultrasound homodyned K imaging based on the noise-assisted correlation algorithm: An ex vivo study

In this paper, we proposed ultrasound homodyned K (HK) imaging based on the noise-assisted correlation algorithm (NCA) for monitoring microwave ablation of porcine liver ex vivo. The NCA-based HK (α_NCA and k_NCA) imaging was compared with NCA-based Nakagami (m_NCA) imaging and NCA-based cumulative echo decorrelation (CED_NCA) imaging. Backscattered ultrasound radiofrequency signals of porcine liver ex vivo during and after the heating of microwave ablation were collected (n = 15), which were processed for constructing B-mode imaging, NCA-based HK imaging, NCA-based Nakagami imaging, and NCA-based CED imaging. To quantitatively evaluate the final coagulation zone, the polynomial approximation (PAX) technique was applied. The accuracy of detecting coagulation area with α_NCA, k_NCA, m_NCA, and CED_NCA parametric imaging was evaluated by comparing the PAX imaging with the gross pathology. The receiver operating characteristic (ROC) curve was used to further evaluate the performance of the three quantitative ultrasound imaging methods for detecting the coagulation zone. Experimental results showed that the average accuracies of α_NCA, k_NCA, m_NCA, and CED_NCA parametric imaging combined with PAX imaging were 89.6%, 83.25%, 89.23%, and 91.6%, respectively. The average areas under the ROC curve (AUROCs) of α_NCA, k_NCA, m_NCA, and CED_NCA parametric imaging were 0.83, 0.77, 0.83, and 0.86, respectively. The proposed NCA-based HK imaging may be used as a new method for monitoring microwave ablation.

Monitoring Microwave Ablation Using Ultrasound Echo Decorrelation Imaging: An ex vivo Study

In this study, a microwave-induced ablation zone (thermal lesion) monitoring method based on ultrasound echo decorrelation imaging was proposed. A total of 15 cases of ex vivo porcine liver microwave ablation (MWA) experiments were carried out. Ultrasound radiofrequency (RF) signals at different times during MWA were acquired using a commercial clinical ultrasound scanner with a 7.5-MHz linear-array transducer. Instantaneous and cumulative echo decorrelation images of two adjacent frames of RF data were calculated. Polynomial approximation images were obtained on the basis of the thresholded cumulative echo decorrelation images. Experimental results showed that the instantaneous echo decorrelation images outperformed conventional B-mode images in monitoring microwave-induced thermal lesions. Using gross pathology measurements as the reference standard, the estimation of thermal lesions using the polynomial approximation images yielded an average accuracy of 88.60%. We concluded that instantaneous ultrasound echo decorrelation imaging is capable of monitoring the change of thermal lesions during MWA, and cumulative ultrasound echo decorrelation imaging and polynomial approximation imaging are feasible for quantitatively depicting thermal lesions.