Optimization of feature extraction for automated identification of heart wall regions in different cross sections

Abstract

In most current methods of evaluating the cardiac function based on echocardiography, the heart wall in an ultrasonic image is currently identified manually by an operator. However, this task is very time-consuming and leads to inter-and intraobserver variability. To facilitate the analysis and eliminate operator dependence, automated identification of heart wall regions is essential. We previously proposed a method of automatic identification of heart wall regions using multiple features based on information of the amplitude and phase of the ultrasonic RF echo signal by pattern recognition. In the present study, we investigate a new method of segmenting an ultrasonic image into the heart wall, lumen, and external tissues (includes pericardium) by two-step pattern recognition. Also, parameters in the proposed classification method were examined for application to different cross sections, i.e., long-axis and short-axis views, by considering differences in the motion and echogenicity of the heart walls. Furthermore, moving target indicator (MTI) filtering to suppress echoes from clutters was improved to enhance the separability in the shortaxis view.

Singular value decomposition filter for speckle reduction in adaptive ultrasound imaging

“…In the present study, the feasibility of the AM filter 39,41) in improvement of CNR was examined. The AM filter can smooth out random noise while keeping boundaries sharp.…”

“…The adaptive mean (AM) filter smooths out images while preserving boundaries between different structures in an image. [39][40][41] The AM filter realizes such adaptive processing by utilizing mean and standard deviation of intensities in an region of interest (ROI). In the present study, the image contrast was first improved by an adaptive beamforming method developed by our group.…”

Identification of the heart wall and chamber based on temporal change of ultrasonic scatterer distribution

“…In the present study, the automatic method for identification of the heart wall and the chamber was employed. 27) At the beginning, in order to reduce the clutter component from the surrounding tissue, a moving target indicator (MTI) filter for RF signals was applied as a high-path filter, its cut-off frequency being 10 Hz. 26,32) After MTI filtering, the features described above were calculated at all discrete points in all frames and were spatially smoothed by adaptive mean (AM) filtering.…”

A Model for Measured Traveling Waves at End-Diastole in Human Heart Wall by Ultrasonic Imaging Method

“…8,9) The behaviors of modulated propagating pulsive waves at the time of the T-wave of ECG have been observed by the ultrasonic imaging method. [10][11][12][13] One of the observed phase jumps for one-dimensional traveling waves specified by Éðx; tÞ with a fixed y can be described by the Bekki-Nozaki (BN) hole solutions 8,9,14,15) with moving sources in the CGLE, [16][17][18][19][20][21][22][23][24][25][26] which is written as…”

“…Traveling pulsive waves on the IVS have been measured by the ultrasonic imaging modality with high spatial and temporal resolutions for healthy young males. [10][11][12] However, the one-dimensional dynamics of large-amplitude traveling waves at the time of the R-wave of ECG (end-diastole) has not been investigated yet. To understand part of the onedimensional behaviors of the traveling waves in the human heart wall, therefore, a phenomenological model of explanation is at least needed on the basis of the direct measurement of traveling waves at end-diastole by the ultrasonic imaging method.…”