Abstract
Segmentation of echocardiographic images is an essential step for assessing the cardiac functionality and providing indicative clinical measures, and all further heart analysis relies on the accuracy of this process. However, the fuzzy nature of echocardiographic images degraded by distortion and speckle noise poses some challenges on the manual segmentation task. In this paper, we propose a fully automated left ventricle segmentation method that can overcome those challenges. Our method performs accurate delineation for the ventricle boundaries despite the ill-defined borders and shape variability of the left ventricle. The well-known deep learning segmentation model, known as the U-net, has addressed some of these challenges with outstanding performance. However, it still ignores the contribution of all semantic information through the segmentation process. Here we propose a novel deep learning segmentation method based on U-net, named ResDUnet. It incorporates feature extraction at different scales through the integration of cascaded dilated convolution. To ease the training process, residual blocks are deployed instead of the basic U-net blocks. Each residual block is enriched with a squeeze and excitation unit for channel-wise attention and adaptive feature re-calibration. The performance of the method is evaluated on a dataset of 2000 images acquired from 500 patients with large variability in quality and patient pathology. ResDUnet outperforms state-of-the-art methods with a Dice similarity increase of 8.4% and 1.2% compared to deeplabv3 and U-net, respectively. Furthermore, to demonstrate the impact of each proposed sub-module, several experiments have been carried out with different designs and variations of the integrated sub-modules. We also describe and discuss all technical elements of a deep-learning model via a step-by-step explanation of parameters and methods, while using our left ventricle segmentation as a case study, to explain the application of AI to echocardiographic imaging.
Highlights
C ARDIOVASCULAR diseases (CVDs) are the number one cause of death worldwide, causing the death of millions of people each year [1]
When this basic U-net model was applied on CAMUS dataset in [5], it has outperformed U-net++ by 1.2%, Stacked Hourglasses method (SHG) by 0.5% and anatomically constrained neural network (ACNN) by 0.7%
It has offered the best compromise between the network size and performance for the task of 2D echocardiographic image segmentation, requiring less parameters than SHG and U-Net++ methods and less training time than ACNN
Summary
C ARDIOVASCULAR diseases (CVDs) are the number one cause of death worldwide, causing the death of millions of people each year [1]. CVD scans are performed using magnetic resonance imaging (MRI), computed tomography (CT) and echocardiography. A physician ideally performs segmentation of the left ventricle (LV) to examine the cardiac anatomy and provide several clinical measures which illustrate the proper functionality of the heart such as the end-diastolic (ED) and end-systolic (ES) volumes, ejection fraction, LV mass, etc. Those measures are manually obtained by delineating the LV borders at ED and ES of each cardiac cycle.
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.
