Shear wave elastography-based ultrasomics: differentiating malignant from benign focal liver lesions

Super-resolution ultrasound and microvasculomics: a consensus statement

This is a summary of a consensus statement on the introduction of "Ultrasound microvasculomics" produced by The Chinese Artificial Intelligence Alliance for Thyroid and Breast Ultrasound. The evaluation of microvessels is a very important part for the assessment of diseases. Super-resolution ultrasound (SRUS) microvascular imaging surpasses traditional ultrasound imaging in the morphological and functional analysis of microcirculation. SRUS microvascular imaging relies on contrast microbubbles to gain sensitivity to microvessels and improves the spatial resolution of ultrasound blood flow imaging for a more detailed depiction of vascular structures and hemodynamics. This method has been applied in preclinical animal models and pilot clinical studies, involving areas including neurology, oncology, nephrology, and cardiology. However, the current quantitative parameters of SRUS images are not enough for precise evaluation of microvessels. Therefore, by employing omics methods, more quantification indicators can be obtained, enabling a more precise and personalized assessment of microvascular status. Ultrasound microvasculomics - a high-throughput extraction of image features from SRUS images - is one novel approach that holds great promise but needs further validation in both bench and clinical settings. CLINICAL RELEVANCE STATEMENT: Super-resolution Ultrasound (SRUS) blood flow imaging improves spatial resolution. Ultrasound microvasculomics is possible to acquire high-throughput information of features from SRUS images. It provides more precise and abundant micro-blood flow information in clinical medicine. KEY POINTS: This consensus statement reviews the development and application of super-resolution ultrasound (SRUS). The shortcomings of the current quantification indicators of SRUS and strengths of the omics methodology are addressed. "Ultrasound microvasculomics" is introduced for a high-throughput extraction of image features from SRUS images.

Artificial intelligence - based ultrasound elastography for disease evaluation - a narrative review

Ultrasound elastography (USE) provides complementary information of tissue stiffness and elasticity to conventional ultrasound imaging. It is noninvasive and free of radiation, and has become a valuable tool to improve diagnostic performance with conventional ultrasound imaging. However, the diagnostic accuracy will be reduced due to high operator-dependence and intra- and inter-observer variability in visual observations of radiologists. Artificial intelligence (AI) has great potential to perform automatic medical image analysis tasks to provide a more objective, accurate and intelligent diagnosis. More recently, the enhanced diagnostic performance of AI applied to USE have been demonstrated for various disease evaluations. This review provides an overview of the basic concepts of USE and AI techniques for clinical radiologists and then introduces the applications of AI in USE imaging that focus on the following anatomical sites: liver, breast, thyroid and other organs for lesion detection and segmentation, machine learning (ML) - assisted classification and prognosis prediction. In addition, the existing challenges and future trends of AI in USE are also discussed.

Multiparametric Dynamic Ultrasound Approach for Differential Diagnosis of Primary Liver Tumors

A correct differentiation between hepatocellular carcinoma (HCC) and intracellular cholangiocarcinoma (ICC) is essential for clinical management and prognostic prediction. However, non-invasive differential diagnosis between HCC and ICC remains highly challenging. Dynamic contrast-enhanced ultrasound (D-CEUS) with standardized software is a valuable tool in the diagnostic approach to focal liver lesions and could improve accuracy in the evaluation of tumor perfusion. Moreover, the measurement of tissue stiffness could add more information concerning tumoral environment. To explore the diagnostic performance of multiparametric ultrasound (MP-US) in differentiating ICC from HCC. Our secondary aim was to develop an US score for distinguishing ICC and HCC. Between January 2021 and September 2022 consecutive patients with histologically confirmed HCC and ICC were enrolled in this prospective monocentric study. A complete US evaluation including B mode, D-CEUS and shear wave elastography (SWE) was performed in all patients and the corresponding features were compared between the tumor entities. For better inter-individual comparability, the blood volume-related D-CEUS parameters were analyzed as a ratio between lesions and surrounding liver parenchyma. Univariate and multivariate regression analysis was performed to select the most useful independent variables for the differential diagnosis between HCC and ICC and to establish an US score for non-invasive diagnosis. Finally, the diagnostic performance of the score was evaluated by receiver operating characteristic (ROC) curve analysis. A total of 82 patients (mean age ± SD, 68 ± 11 years, 55 men) were enrolled, including 44 ICC and 38 HCC. No statistically significant differences in basal US features were found between HCC and ICC. Concerning D-CEUS, blood volume parameters (peak intensity, PE; area under the curve, AUC; and wash-in rate, WiR) showed significantly higher values in the HCC group, but PE was the only independent feature associated with HCC diagnosis at multivariate analysis (p = 0.02). The other two independent predictors of histological diagnosis were liver cirrhosis (p < 0.01) and SWE (p = 0.01). A score based on those variables was highly accurate for the differential diagnosis of primary liver tumors, with an area under the ROC curve of 0.836 and the optimal cut-off values of 0.81 and 0.20 to rule in or rule out ICC respectively. MP-US seems to be a useful tool for non-invasive discrimination between ICC and HCC and could prevent the need for liver biopsy at least in a subgroup of patients.

Differential diagnosis of different types of solid focal liver lesions using two-dimensional shear wave elastography

BACKGROUND

The clinical management and prognosis differ between benign and malignant solid focal liver lesions (FLLs), as well as among different pathological types of malignant FLLs. Accurate diagnosis of the possible types of solid FLLs is important. Our previous study confirmed the value of shear wave elastography (SWE) using maximal elasticity (Emax) as the parameter in the differential diagnosis between benign and malignant FLLs. However, the value of SWE in the differential diagnosis among different pathological types of malignant FLLs has not been proved.

AIM

To explore the value of two-dimensional SWE (2D-SWE) using Emax in the differential diagnosis of FLLs, especially among different pathological types of malignant FLLs.

METHODS

All the patients enrolled in this study were diagnosed as benign, malignant or undetermined FLLs by conventional ultrasound. Emax of FLLs and the periphery of FLLs was measured using 2D-SWE and compared between benign and malignant FLLs or among different pathological types of malignant FLLs.

RESULTS

The study included 32 benign FLLs in 31 patients and 100 malignant FLLs in 96 patients, including 16 cholangiocellular carcinomas (CCCs), 72 hepatocellular carcinomas (HCCs) and 12 liver metastases. Thirty-five FLLs were diagnosed as undetermined by conventional ultrasound. There were significant differences between Emax of malignant (2.21 ± 0.57 m/s) and benign (1.59 ± 0.37 m/s) FLLs (P = 0.000), and between Emax of the periphery of malignant (1.52 ± 0.39 m/s) and benign (1.36 ± 0.44 m/s) FLLs (P = 0.040). Emax of liver metastases (2.73 ± 0.99 m/s) was significantly higher than that of CCCs (2.14 ± 0.34 m/s) and HCCs (2.14 ± 0.46 m/s) (P = 0.002). The sensitivity, specificity and accuracy were 71.00%, 84.38% and 74.24% respectively, using Emax > 1.905 m/s (AUC 0.843) to diagnose as malignant and 23 of 35 (65.74%) FLLs with undetermined diagnosis by conventional ultrasound were diagnosed correctly.

CONCLUSION

Malignant FLLs were stiffer than benign ones and liver metastases were stiffer than primary liver carcinomas. 2D-SWE with Emax was a useful complement to conventional ultrasound for the differential diagnosis of FLLs.

Machine learning prediction of prostate cancer from transrectal ultrasound video clips

Objective

To build a machine learning (ML) prediction model for prostate cancer (PCa) from transrectal ultrasound video clips of the whole prostate gland, diagnostic performance was compared with magnetic resonance imaging (MRI).

Methods

We systematically collated data from 501 patients—276 with prostate cancer and 225 with benign lesions. From a final selection of 231 patients (118 with prostate cancer and 113 with benign lesions), we randomly chose 170 for the purpose of training and validating a machine learning model, while using the remaining 61 to test a derived model. We extracted 851 features from ultrasound video clips. After dimensionality reduction with the least absolute shrinkage and selection operator (LASSO) regression, 14 features were finally selected and the support vector machine (SVM) and random forest (RF) algorithms were used to establish radiomics models based on those features. In addition, we creatively proposed a machine learning models aided diagnosis algorithm (MLAD) composed of SVM, RF, and radiologists’ diagnosis based on MRI to evaluate the performance of ML models in computer-aided diagnosis (CAD). We evaluated the area under the curve (AUC) as well as the sensitivity, specificity, and precision of the ML models and radiologists’ diagnosis based on MRI by employing receiver operator characteristic curve (ROC) analysis.

Results

The AUC, sensitivity, specificity, and precision of the SVM in the diagnosis of PCa in the validation set and the test set were 0.78, 63%, 80%; 0.75, 65%, and 67%, respectively. Additionally, the SVM model was found to be superior to senior radiologists’ (SR, more than 10 years of experience) diagnosis based on MRI (AUC, 0.78 vs. 0.75 in the validation set and 0.75 vs. 0.72 in the test set), and the difference was statistically significant (p< 0.05).

Conclusion

The prediction model constructed by the ML algorithm has good diagnostic efficiency for prostate cancer. The SVM model’s diagnostic efficiency is superior to that of MRI, as it has a more focused application value. Overall, these prediction models can aid radiologists in making better diagnoses.

The latest application progress of radiomics in prediction and diagnosis of liver diseases

INTRODUCTION

Early detection and individualized treatment of patients with liver disease is the key to survival. Radiomics can extract high-throughput quantitative features by multimode imaging, which has good application prospects for the diagnosis, staging and prognosis of benign and malignant liver diseases. Therefore, this paper summarizes the current research status in the field of liver disease, in order to help these patients achieve personalized and precision medical care.

AREAS COVERED

This paper uses several keywords on the PubMed database to search the references, and reviews the workflow of traditional radiomics, as well as the characteristics and influencing factors of different imaging modes. At the same time, the references on the application of imaging in different benign and malignant liver diseases were also summarized.

EXPERT OPINION

For patients with liver disease, the traditional imaging evaluation can only provide limited information. Radiomics exploits the characteristics of high-throughput and high-dimensional extraction, enabling liver imaging capabilities far beyond the scope of traditional visual image analysis. Recent studies have demonstrated the prospect of this technology in personalized diagnosis and treatment decision in various fields of the liver. However, further clinical validation is needed in its application and practice.

Potential value of tumor stiffness and sE-cadherin in predicting the response to neoadjuvant therapy in HER2-positive breast cancers

Background: This prospective study compared the diagnostic value of tumor stiffness and serum soluble E-cadherin (sE-cadherin) expression for predicting response to neoadjuvant therapy in HER2-positive breast cancers. Methods: 112 patients with early or locally advanced HER2-positive breast cancer were enrolled. Maximum stiffness (Emax), mean stiffness (Emean) and their relative changes were assessed at t0 and t2. sE-cadherin levels were analyzed using ELISA. Pathological complete response was defined as no invasive disease in the breast and axilla (ypT0/is, ypN0) after surgery. The ability of tumor stiffness, sE-cadherin and the combination of ΔEmean (the relative change in Emean after the second cycle of neoadjuvant therapy) and sE-cadherin in predicting tumor responses was assessed using receiver operating characteristic curves and the Z-test. Results: Tumor stiffness and sE-cadherin decreased during neoadjuvant therapy. ΔEmean and sE-cadherin revealed the best predictive performance, with areas under the curve (AUCs) of 0.843 and 0.857, respectively. No significant differences in AUCs were reported between ΔEmean and sE-cadherin (p = 0.795). The combined use of ΔEmean and sE-cadherin showed the highest sensitivity and specificity (93.22 and 90.57%, respectively), with an AUC of 0.937. Conclusion: The combination of ΔEmean and sE-cadherin may improve the predictive power of each single factor. Although further verification is required, this study may promote noninvasive prediction of neoadjuvant therapy responses and help personalize the treatment regimen.

Recent Advances in Machine Learning Applied to Ultrasound Imaging

Machine learning (ML) methods are pervading an increasing number of fields of application because of their capacity to effectively solve a wide variety of challenging problems. The employment of ML techniques in ultrasound imaging applications started several years ago but the scientific interest in this issue has increased exponentially in the last few years. The present work reviews the most recent (2019 onwards) implementations of machine learning techniques for two of the most popular ultrasound imaging fields, medical diagnostics and non-destructive evaluation. The former, which covers the major part of the review, was analyzed by classifying studies according to the human organ investigated and the methodology (e.g., detection, segmentation, and/or classification) adopted, while for the latter, some solutions to the detection/classification of material defects or particular patterns are reported. Finally, the main merits of machine learning that emerged from the study analysis are summarized and discussed.

Differentiation between combined hepatocellular carcinoma and hepatocellular carcinoma: comparison of diagnostic performance between ultrasomics-based model and CEUS LI-RADS v2017

Background

The imaging findings of combined hepatocellular cholangiocarcinoma (CHC) may be similar to those of hepatocellular carcinoma (HCC). CEUS LI-RADS may not perform well in distinguishing CHC from HCC. Studies have shown that radiomics has an excellent imaging analysis ability. This study aimed to establish and confirm an ultrasomics model for differentiating CHC from HCC.

Methods

Between 2004 and 2016, we retrospectively identified 53 eligible CHC patients and randomly included 106 eligible HCC patients with a ratio of HCC:CHC = 2:1, all of whom were categorized according to Contrast-Enhanced (CE) ultrasonography (US) Liver Imaging Reporting and Data System (LI-RADS) version 2017. The model based on ultrasomics features of CE US was developed in 74 HCC and 37 CHC and confirmed in 32 HCC and 16 CHC. The diagnostic performance of the LI-RADS or ultrasomics model was assessed by the area under the curve (AUC), accuracy, sensitivity and specificity.

Results

In the entire and validation cohorts, 67.0% and 81.3% of HCC cases were correctly assigned to LR-5 or LR-TIV contiguous with LR-5, and 73.6% and 87.5% of CHC cases were assigned to LR-M correctly. Up to 33.0% of HCC and 26.4% of CHC were misclassified by CE US LI-RADS. A total of 90.6% of HCC as well as 87.5% of CHC correctly diagnosed by the ultrasomics model in the validation cohort. The AUC, accuracy, sensitivity of the ultrasomics model were higher though without significant difference than those of CE US LI-RADS in the validation cohort.

Conclusion

The proposed ultrasomics model showed higher ability though the difference was not significantly different for differentiating CHC from HCC, which may be helpful in clinical diagnosis.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12880-022-00765-x.

Hepatocellular Carcinoma and Non-Alcoholic Fatty Liver Disease: A Step Forward for Better Evaluation Using Ultrasound Elastography

Simple Summary

Non-alcoholic fatty liver disease (NAFLD) attracts a lot of attention, due to the increasing prevalence and progression to fibrosis, cirrhosis, and hepatocellular carcinoma (HCC). Consequently, new non-invasive, cost-effective diagnostic methods are needed. This review aims to explore the diagnostic performance of ultrasound (US) elastography in NAFLD and NAFLD-related HCC, adding a new dimension to the conventional US examination—the liver stiffness quantification. The vibration controlled transient elastography (VCTE), and 2D-Shear wave elastography (2D-SWE) are effective in staging liver fibrosis in NAFLD. VCTE presents the upside of assessing steatosis through the controlled attenuation parameter. Hereby, we critically reviewed the elastography techniques for the quantitative characterization of focal liver lesions (FLLs), focusing on HCC: Point shear wave elastography and 2D-SWE. 2D-SWE presents a great potential to differentiate malignant from benign FLLs, guiding the clinician towards the next diagnostic steps. As a disease-specific surveillance tool, US elastography presents prognostic capability, improving the NAFLD-related HCC monitoring.

Abstract

The increasing prevalence of non-alcoholic fatty liver disease (NAFLD) in the general population prompts for a quick response from physicians. As NAFLD can progress to liver fibrosis, cirrhosis, and even hepatocellular carcinoma (HCC), new non-invasive, rapid, cost-effective diagnostic methods are needed. In this review, we explore the diagnostic performance of ultrasound elastography for non-invasive assessment of NAFLD and NAFLD-related HCC. Elastography provides a new dimension to the conventional ultrasound examination, by adding the liver stiffness quantification in the diagnostic algorithm. Whilst the most efficient elastographic techniques in staging liver fibrosis in NAFLD are vibration controlled transient elastography (VCTE) and 2D-Shear wave elastography (2D-SWE), VCTE presents the upside of assessing steatosis through the controlled attenuation parameter (CAP). Hereby, we have also critically reviewed the most important elastographic techniques for the quantitative characterization of focal liver lesions (FLLs), focusing on HCC: Point shear wave elastography (pSWE) and 2D-SWE. As our paper shows, elastography should not be considered as a substitute for FLL biopsy because of the stiffness values overlap. Furthermore, by using non-invasive, disease-specific surveillance tools, such as US elastography, a subset of the non-cirrhotic NAFLD patients at risk for developing HCC can be detected early, leading to a better outcome. A recent ultrasomics study exemplified the wide potential of 2D-SWE to differentiate benign FLLs from malignant ones, guiding the clinician towards the next steps of diagnosis and contributing to better long-term disease surveillance.