CNN-based fully automatic mitral valve extraction using CT images and existence probability maps

TL;DR

This paper introduces a fully automated CNN-based method for extracting mitral valve shapes from CT images, utilizing existence probability maps to improve accuracy across all cardiac cycle phases.

Contribution

It proposes a novel approach combining DenseNet and U-Net outputs for precise mitral valve shape extraction, outperforming previous methods without probability maps.

Findings

Mean shape extraction error is 0.88 mm.

Inclusion of existence probability maps improves accuracy.

Method is validated on 1585 CT images from 204 patients.

Abstract

Accurate extraction of mitral valve shape from clinical tomographic images acquired in patients has proven useful for planning surgical and interventional mitral valve treatments. However, manual extraction of the mitral valve shape is laborious, and the existing automatic extraction methods have not been sufficiently accurate. In this paper, we propose a fully automated method of extracting mitral valve shape from computed tomography (CT) images for the all phases of the cardiac cycle. This method extracts the mitral valve shape based on DenseNet using both the original CT image and the existence probability maps of the mitral valve area inferred by U-Net as input. A total of 1585 CT images from 204 patients with various cardiac diseases including mitral regurgitation (MR) were collected and manually annotated for mitral valve region. The proposed method was trained and evaluated by 10-fold cross validation using the collected data and was compared with the method without the existence probability maps. The mean error of shape extraction error in the proposed method is 0.88 mm, which is an improvement of 0.32 mm compared with the method without the existence probability maps.