Tissue classification in intercostal and paravertebral ultrasound using spectral analysis of radiofrequency backscatter

Mapping adipose tissue in short-axis echocardiograms using spectral analysis

The number one cause of death in the United States is consistently cardiovascular disease (CVD). Studies have proven that the buildup of cardiac adipose tissue (CAT) around the heart is a biomarker of CVD. MRI is the gold standard for imaging CAT but is expensive and not widely available. Ultrasound is less expensive and portable, but the images are noisy, and it is difficult to identify or quantify CAT. The aim of this project is to use spectral analysis of raw radiofrequency (RF) ultrasound data as input for a machine learning classifier to automatically classify regions-of-interest (ROIs) around the heart as containing CAT or not. ROIs are labeled using corresponding MRI images of the same patients. A previous study used a random forest classifier with 9 spectral parameters as input to classify tissue types in echocardiograms. This project focuses on improving this classifier by experimenting with properties of the chosen ROIs. Experiments were performed independently varying the ROI circumference (length), width, the threshold CAT thickness used for labeling an ROI as CAT, and the signal level required for valid processing. Additional experiments explored the impact of the anatomical location of each ROI as an input. The addition of two parameters indicating the distance of each ROI from the two left and right myocardium intersections as well as the use of the optimal ROI parameters as determined from experimentation resulted in an accuracy of 75.5%. This demonstrates feasibility of this approach for identifying CAT around the heart and will lead to future work in estimating the thickness of fat in each ROI.

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.

Spectral analysis of ultrasound radiofrequency backscatter for the identification of epicardial adipose tissue

Purpose: The coronary arteries are embedded in a layer of fat known as epicardial adipose tissue (EAT). The EAT influences the development of coronary artery disease (CAD), and increased EAT volume can be indicative of the presence and type of CAD. Identification of EAT using echocardiography is challenging and only sometimes feasible on the free wall of the right ventricle. We investigated the use of spectral analysis of the ultrasound radiofrequency (RF) backscatter for its potential to provide a more complete characterization of the EAT. Approach: Autoregressive (AR) models facilitated analysis of the short-time signals and allowed tuning of the optimal order of the spectral estimation process. The spectra were normalized using a reference phantom and spectral features were computed from both normalized and non-normalized data. The features were used to train random forests for classification of EAT, myocardium, and blood. Results: Using an AR order of 15 with the normalized data, a Monte Carlo cross validation yielded accuracies of 87.9% for EAT, 84.8% for myocardium, and 93.3% for blood in a database of 805 regions-of-interest. Youden's index, the sum of sensitivity, and specificity minus 1 were 0.799, 0.755, and 0.933, respectively. Conclusions: We demonstrated that spectral analysis of the raw RF signals may facilitate identification of the EAT when it may not otherwise be visible in traditional B-mode images.