Abstract:
Automatic liver tumor segmentation is a highly important application for diagnosing and treating liver tumors. Due to the diversity of tumor shape and intensity alteration, it has become an extremely challenging procedure. Automatic liver tumor segmentation has the potential to establish a diagnostic standard for providing important radiological information to physicians.
Recently, deep convolutional neural networks have shown numerous benefits in feature extraction and learning in terms of medical image segmentation. However, the model can be inconsistent in imitating visual attention as well as awareness of radiological expertise for tumor recognition and segmentation tasks due to multi-layer dense feature stacking. Attention mechanisms for optimized feature selection have evolved to bridge that gap in visual attention capabilities.
In this research, we propose a novel network called Multi Attention Network (MANet) as a fusion of attention techniques to learn and emphasize significant features while suppressing irrelevant features for liver tumor segmentation. The proposed deep learning network is based on the U-Net architecture. Furthermore, the encoder has a residual mechanism. The convolutional block attention module (CBAM) has been divided into channel attention and spatial attention modules to be implemented in the encoder and decoder separately. The spatial attention mechanism in Attention U-Net has been integrated into the proposed network to capture low-level features to combine with high-level ones. The constructed deep learning architecture is trained and evaluated using multiple evaluation metrics using the publically available MICCAI 2017 Liver Tumor Segmentation (LiTS17) dataset and 3DIRCADb dataset. MANet produced promising results when compared to state-of-the-art methods with relatively low parameter overhead.
