Bi-DCNet: Bilateral Network with Dilated Convolutions for Left Ventricle Segmentation

• Published in: Life (Basel, Switzerland) Vol. 13; no. 4; p. 1040
• Main Authors: Ye, Zi, Kumar, Yogan Jaya, Song, Fengyan, Li, Guanxi, Zhang, Suyu
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 01-04-2023; MDPI
• Subjects: Artificial neural networks; Automation; bilateral network; Cardiac function; Computer architecture; convolutional neural network; Datasets; Deep learning; Diagnostic imaging; dilated convolution; Echocardiography; Evaluation; Exploitation; Feature extraction; Heart; Image segmentation; left ventricle segmentation; Left ventricular function; Machine learning; Medical imaging; Medical imaging equipment; Methods; Mortality; Neural networks; Receptive field; Semantics; Ultrasonic imaging; Ventricle; China; left ventricle segmentation; bilateral network; dilated convolution; convolutional neural network
• ISSN: 2075-1729; 2075-1729
• DOI: 10.3390/life13041040

Left ventricular segmentation is a vital and necessary procedure for assessing cardiac systolic and diastolic function, while echocardiography is an indispensable diagnostic technique that enables cardiac functionality assessment. However, manually labeling the left ventricular region on echocardiography images is time consuming and leads to observer bias. Recent research has demonstrated that deep learning has the capability to employ the segmentation process automatically. However, on the downside, it still ignores the contribution of all semantic information through the segmentation process. This study proposes a deep neural network architecture based on BiSeNet, named Bi-DCNet. This model comprises a spatial path and a context path, with the former responsible for spatial feature (low-level) acquisition and the latter responsible for contextual semantic feature (high-level) exploitation. Moreover, it incorporates feature extraction through the integration of dilated convolutions to achieve a larger receptive field to capture multi-scale information. The EchoNet-Dynamic dataset was utilized to assess the proposed model, and this is the first bilateral-structured network implemented on this large clinical video dataset for accomplishing the segmentation of the left ventricle. As demonstrated by the experimental outcomes, our method obtained 0.9228 and 0.8576 in DSC and IoU, respectively, proving the structure's effectiveness.