Abstract
Decent whole-heart segmentation from computed tomography (CT) can greatly contribute to the diagnosis and treatment of cardiovascular diseases. However, due to the difficulties such as blurred boundaries between neighbouring tissues and a large number of background voxels in medical images, automated whole-heart segmentation is still a challenging task. In this paper, we proposed three modified attention models, including simple negative example mining (SNEM), attention gate (AG) and U-CliqueNet (UCNet), to lead the deep learning network to focus on more salient information. These three attention modules were further implemented into a deeply-supervised 3D UNET separately and jointly, showing different degrees of improvement on the whole-heart segmentation task. Our experiments advised that SNEM was the most simple and effective attention mechanism for medical image processing among the three and the UCNet could reach the best performance. The combination of the attention mechanisms cannot always synergistically increase the accuracy, but joint models would have a positive influence in most cases. Finally, our network achieved a Dice score of 0.9112, which was a substantially higher performance than most of the state-of-the-art methods.
Highlights
Cardiovascular diseases are the prominent cause of death globally [1]
Based on our previous study, we focus on the application of attention mechanism in medical image processing, trying to find out proper attention approaches that could reach higher segmentation accuracy
Our work can be summarized as follows: 1. We introduced a hard attention mechanism, named simple negative example mining (SNEM) approach, which can effectively suppress the influence of non-informative background and noise
Summary
Cardiovascular diseases are the prominent cause of death globally [1]. As one of the most powerful tools for the diagnosis and treatment of cardiovascular diseases, medical imaging technology has attracted great research interests. One of the critical applications of medical image processing is the whole-heart CT image segmentation, whose aim is to distinguish the size, location and morphology of all substructures of a heart. Good results of the segmentation can contribute to plenty of clinical applications. Ejection fraction can be calculated based on the computed volume of the heart, which is an important indicator for diagnosing heart failure [2]. Segmentation results can be utilized for reconstructing the 3D whole-heart model, which would be an excellent platform for investigating cardiac arrhythmia [3] and congenital cardiac diseases [4]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
