ResDUnet: Residual Dilated UNet for Left Ventricle Segmentation from Echocardiographic Images

Amer, Alyaa, Ye, Xujiong, Zolgharni, Massoud and Janan, Faraz (2020) ResDUnet: Residual Dilated UNet for Left Ventricle Segmentation from Echocardiographic Images. In: 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 20-24 July 2020, Montreal Canada.

Full content URL: https://doi.org/10.1109/EMBC44109.2020.9175436

Documents
ResDUnet: Residual Dilated UNet for Left Ventricle Segmentation from Echocardiographic Images
Accepted Manuscript
[img]
[Download]
[img]
Preview
PDF
ResDUnet Paper Final.pdf - Whole Document

4MB
Item Type:Conference or Workshop contribution (Paper)
Item Status:Live Archive

Abstract

Echocardiography is the modality of choice for the assessment of left ventricle function. Left ventricle is responsible for pumping blood rich in oxygen to all body parts. Segmentation of this chamber from echocardiographic images is a challenging task, due to the ambiguous boundary and inhomogeneous intensity distribution. In this paper we propose a novel deep learning model named ResDUnet. The model is based on U-net incorporated with dilated convolution, where residual blocks are employed instead of the basic U-net units to ease the training process. Each block is enriched with squeeze and excitation unit for channel-wise attention and adaptive feature re-calibration. To tackle the problem of left ventricle shape and size variability, we chose to enrich the process of feature concatenation in U-net by integrating feature maps generated by cascaded dilation. Cascaded dilation broadens the receptive field size in comparison with traditional convolution, which allows the generation of multi-scale information which in turn results in a more robust segmentation. Performance measures were evaluated on a publicly available dataset of 500 patients with large variability in terms of quality and patients pathology. The proposed model shows a dice similarity increase of 8.4% when compared to deeplabv3 and 1.2% when compared to the basic U-net architecture. Experimental results demonstrate the potential use in clinical domain.

Keywords:Deep learning, Echocardiography, image segmentation, left ventricle, UNet, ResDUnet
Subjects:G Mathematical and Computer Sciences > G740 Computer Vision
H Engineering > H130 Computer-Aided Engineering
Divisions:College of Science > School of Computer Science
ID Code:42450
Deposited On:29 Oct 2020 13:45

Repository Staff Only: item control page