Support vector analysis of color-Doppler images: a new approach for estimating indices of left ventricular function

Reliable noninvasive estimators of global left ventricular (LV) chamber function remain unavailable. We have previously demonstrated a potential relationship between color-Doppler M-mode (CDMM) images and two basic indices of LV function: peak-systolic elastance (Emax) and the time-constant of LV relaxation (tau). Thus, we hypothesized that these two indices could be estimated noninvasively by adequate postprocessing of CDMM recordings. A semiparametric regression (SR) version of support vector machine (SVM) is here proposed for building a blind model, capable of analyzing CDMM images automatically, as well as complementary clinical information. Simultaneous invasive and Doppler tracings were obtained in nine mini-pigs in a high-fidelity experimental setup. The model was developed using a test and validation leave-one-out design. Reasonably acceptable prediction accuracy was obtained for both Emax (intraclass correlation coefficient Ric, = 0.81) and tau (Ric, = 0.61). For the first time, a quantitative, noninvasive estimation of cardiovascular indices is addressed by processing Doppler-echocardiography recordings using a learning-from-samples method.

Detection of cardiac boundaries in echocardiographic images using a customized order statistics filter

Order statistics filters are nonlinear filters that suppress impulsive and Gaussian noise while preserving edges. These features are particularly useful for cardiac boundary detection in ultrasound images. Based on these facts, we have analyzed performance of a combined ranked order statistics filter. The filter subtracts ranks of ordered highest and lowest intensity values of pixels encompassed in a filter window. The rank extent and window size selection allow adjustment of filter properties for a particular application. Increasing the rank fosters the low-pass characteristics of the filter. Increasing the window size supports noise removal but reduces anatomic selectivity. The filter highlights cardiac boundaries in clinical echocardiograms with intensity proportional to the local probability of a presence of the boundary.

Neural network reconstruction of single-photon emission computed tomography images

An artificial neural network (ANN) trained on high-quality medical tomograms or phantom images may be able to learn the planar data-to-tomographic image relationship with very high precision. As a result, a properly trained ANN can produce comparably accurate image reconstruction without the high computational cost inherent in some traditional reconstruction techniques. We have previously shown that a standard backpropagation neural network can be trained to reconstruct sections of single photon emission computed tomography (SPECT) images based on the planar image projections as inputs. In this study, we present a method of deriving activation functions for a backpropagation ANN that make it readily trainable for full SPECT image reconstruction. The activation functions used for this work are based on the estimated probability density functions (PDFs) of the ANN training set data. The statistically tailored ANN and the standard sigmoidal backpropagation ANN methods are compared both in terms of their trainability and generalization ability. The results presented show that a statistically tailored ANN can reconstruct novel tomographic images of a quality comparable with that of the images used to train the network. Ultimately, an adequately trained ANN should be able to properly compensate for physical photon transport effects, background noise, and artifacts while reconstructing the tomographic image.