Ultrasound speckle size and lesion signal to noise ratio: verification of theory

Rotational-invariant speckle-scanning ultrasonography through thick bones

Ultrasonography is a major medical imaging technique that has been broadly applied in many disease diagnoses. However, due to strong aberration and scattering in the human skull, high-resolution transcranial ultrasonic imaging remains a grand challenge. Here, we explore the rotational-invariant property of ultrasonic speckle and develop high-resolution speckle-scanning ultrasonography to image sub-millimeter-sized features through thick bones. We experimentally validate the rotational invariance of ultrasonic speckle. Based on this property, we scan a random ultrasonic speckle pattern across an object sandwiched between two thick bones so that the object features can be encoded to the ultrasonic waves. After receiving the transmitted ultrasonic waves, we reconstruct the image of the object using an iterative phase retrieval algorithm. We successfully demonstrate imaging of hole and tube features sized as fine as several hundreds of microns between two 0.5 ~ 1-cm-thick bones. With 2.5-MHz excitation and the third-harmonic detection, we measure the spatial resolution as 352 µm. Rotational-invariant speckle-scanning ultrasonography offers a new approach to image through thick bones and paves an avenue towards high-resolution ultrasonic imaging of the human brain.

Artificial intelligence-based myocardial texture analysis in etiological differentiation of left ventricular hypertrophy

Background

Transthoracic echocardiography (TTE) is widely used in clinics to evaluate left ventricular hypertrophy (LVH). However, TTE is usually insufficient for the etiological diagnoses when morphological and functional features are nonspecific. With the booming of computer science and artificial intelligence (AI), previous literature has reported the application of radiomics based on cardiac magnetic resonance imaging, cardiac computed tomography and TTE in diagnosing several myocardial abnormalities, such as myocardial infarction, myocarditis, cardiac amyloidosis, and hypertrophic cardiomyopathy (HCM). In this study, we explored the possibility of using myocardial texture features in differentiating HCM, hypertensive heart disease (HHD) and uremic cardiomyopathy (UCM) based on echocardiography. To our knowledge, this was the first study to explore TTE myocardial texture analysis for multiple LVH etiology differentiation.

Methods

TTE images were reviewed retrospectively from January 2018 to collect 50 cases for each group of HHD, HCM and UCM. The apical four chamber view was retrieved. Seventeen first-order statistics and 60 gray level co-occurrence matrix (GLCM) features were extracted for statistics and classification test by support vector machine (SVM).

Results

Of all the parameters, entropy of brightness (EtBrt), standard deviation (Std), coefficient of variation (CoV), skewness (Skew), contrast7 (Cont7) and homogeneity5 (Hm5) were found statistically significant among the three groups (all P<0.05) and with acceptable reproducibility (intraobserver and interobserver ICC >0.50). As a result, HCM showed the most homogeneous myocardial texture, and was significantly different from HHD and UCM (all six features: P≤0.005). HHD appeared slightly more homogeneous than UCM, as only EtBrt and CoV were significant (P=0.011 and P=0.008). According to higher areas under the receiver operating characteristic curve (AUC) (>0.50), EtBrt, Std, and CoV were selected for test of classification as a combination of features. The AUC derived from SVM model was slightly improved compared with those of EtBrt, Std and CoV individually.

Conclusions

AI-based myocardial texture analysis using ultrasonic images may be a potential approach to aiding LVH etiology differentiation.