Multi-class probabilistic atlas-based whole heart segmentation method in cardiac CT and MRI

TL;DR

This paper introduces a novel multi-class whole heart segmentation method combining probabilistic atlas, non-rigid registration, and deep learning, achieving improved accuracy in cardiac CT and MRI images for clinical applications.

Contribution

It presents a new framework integrating probabilistic atlas, non-rigid registration, and deep neural networks for more accurate heart substructure segmentation.

Findings

Achieved a mean volume overlapping error of 14.5% for CT scans.

Outperformed state-of-the-art results by 1.3% in segmentation accuracy.

Validated on a public dataset with 20 MRI and 20 CT images.

Abstract

Accurate and robust whole heart substructure segmentation is crucial in developing clinical applications, such as computer-aided diagnosis and computer-aided surgery. However, segmentation of different heart substructures is challenging because of inadequate edge or boundary information, the complexity of the background and texture, and the diversity in different substructures' sizes and shapes. This article proposes a framework for multi-class whole heart segmentation employing non-rigid registration-based probabilistic atlas incorporating the Bayesian framework. We also propose a non-rigid registration pipeline utilizing a multi-resolution strategy for obtaining the highest attainable mutual information between the moving and fixed images. We further incorporate non-rigid registration into the expectation-maximization algorithm and implement different deep convolutional neural network-based encoder-decoder networks for ablation studies. All the extensive experiments are conducted utilizing the publicly available dataset for the whole heart segmentation containing 20 MRI and 20 CT cardiac images. The proposed approach exhibits an encouraging achievement, yielding a mean volume overlapping error of 14.5 % for CT scans exceeding the state-of-the-art results by a margin of 1.3 % in terms of the same metric. As the proposed approach provides better-results to delineate the different substructures of the heart, it can be a medical diagnostic aiding tool for helping experts with quicker and more accurate results.