CNN-based spatio-temporal nonlinear filtering and endocardial boundary detection in echocardiography

In this paper, a CNN-based spatio-temporal approach is introduced for findi ng the endocardial (inner) boundary of the left ventricle from a sequence o f echocardiographic images. The discussed analogic dagger CNN algorithm com bines optimal non-linear filtering and constrained wave propagation in orde r to estimate the continuous contour of a moving object in a medium where t he edges are ill-defined. In the preprocessing phase, non-linear filtering is employed to remove the coherent speckle noise that corrupts the images. It is verified that an optimal filtering strategy should estimate the mode of the local intensity histogram. Three different approximations of the mod e filter were implemented, derived from robust statistics double dagger and geometry-driven diffusion,<SUP></SUP> that give an output consistent with the maximum likelihood estimate of the noisy sequence. The kernel of the le ft ventricle is located and the boundary is found using a fuzzy-adaptive te chnique that embodies constrained wave propagation, Boundary dislocation, a rea and smoothness constraints are transformed into the transient length of the CNN while the a priori knowledge about the heart morphology is built i nto the spatial template parameters (weight values). Special emphasis is gi ven to VLSI implementation complexity. It is shown that the core of the alg orithm can be realized using the already available CNN chips. Furthermore, it is argued that all templates of the complete solution belong to the impl ementation frame that is considered for the next generation of CNN Universa l Chips. This study demonstrates that the discussed novel approach allows a reliable endocardial boundary tracking of the left ventricle in real-time using a spatio-temporal CNN visual microprocessor. Copyright (C) 1999 John Wiley & Sons, Ltd.