Dynamically constructed network with error correction for accurate ventricle volume estimation

Abstract

Automated ventricle volume estimation (AVVE) on cardiac magnetic resonance (CMR) images is very important for clinical cardiac disease diagnosis. However, current AVVE methods ignore the error correction for the estimated volume. This results in clinically intolerable ventricle volume estimation error and further leads to wrong ejection fraction (EF) assessment, which significantly limits the application potential of AVVE methods. The objective of this paper is to address this problem with AVVE and further make it more clinically applicable. We proposed a dynamically constructed network to achieve accurate AVVE. First, we introduced a novel dynamically constructed deep learning framework, that evolves a single model into a bi-model volume estimation network. In this way, the EF correlation can be built directly based on the bi-model network. Second, we proposed an error correction strategy using dynamically created residual nodes, which is based on stochastic configurations with an EF correlation constraint. Finally, we formulated the proposed method into an end-to-end joint optimization framework for accurate ventricle volume estimation with effective error correction. Experiments and comparisons on large-scale cardiac magnetic resonance datasets were carried out. Results show that the proposed method outperforms state-of-the-art methods, and has good potential for clinical application. Besides, the proposed method is the first work to achieve error correction for AVVE and also has the potential to be extended to other medical index estimation tasks.

Keywords: Dynamically constructed network; Ejection fraction correlation; Residual correction; Ventricle volume estimation.