CBAR-UNet: A novel methodology for segmentation of cardiac magnetic resonance images using block attention-based deep residual neural network

• Published in: Multimedia tools and applications 2024-11, Vol.83 (37), p.85047-85063
• Main Authors: Kumar, Rakesh, Gupta, Meenu, Agarwal, Aman, Nayyar, Anand
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Computer Communication Networks; Computer Science; Data Structures and Information Theory; Datasets; Image contrast; Image segmentation; Magnetic resonance imaging; Medical imaging; Multimedia Information Systems; Network computers; Neural networks; Special Purpose and Application-Based Systems; Stacks; Track 2: Medical Applications of Multimedia
• ISSN: 1573-7721; 1380-7501; 1573-7721
• DOI: 10.1007/s11042-024-19432-0

Computer-aided Medical Image Segmentation (MIS) plays a leading role in diagnosing diseases automatically. MIS is used extensively in diagnosing medical ailments to obtain clinically relevant information of the shapes and volumes of the target organs and tissues. In order to facilitate accurate segmentation, a Block Attention Based Deep Residual Neural Network, i.e., CBAR-UNet model, is proposed to perform cardiac image segmentation on short axis Magnetic Resonance Images (MRI) stacks from top to bottom slice. The Automated Cardiac Diagnosis Challenge (ACDC) dataset is used in the proposed work, which comprise of a 3D MRI of 100 patients (i.e., 200 MRI stacks). Further, 3D MRIs are converted into 2D by slicing each image to train the model, and Contrast Limited Adaptive Histogram Equalization (CLAHE) is performed on the 2D dataset. Residual connections are introduced that aid in training deeper models. Convolutional Block Attention Module (CBAM) is also added in the proposed network, which consists of Spatial and Channel attention that enhances the spatial and channel-wise features in the image by providing information like ‘what’ and ‘where’ to pay attention respectively. To test and validate the proposed methodology, extensive experimentations were conducted and it was observed that proposed image segmentation model delivers better results by 2.47% when compared to both 2D and 3D State-Of-The-Art (SOTA) methods with a Dice Score of 0.9428.