MFA-Net: Multi-Scale feature fusion attention network for liver tumor segmentation
This work addresses a domain-specific problem for medical imaging by improving segmentation accuracy, but it appears incremental as it builds on existing attention mechanisms for a known bottleneck.
The paper tackled the challenge of fusing multi-scale features for liver tumor segmentation in CT images by proposing MFA-Net, an attention-based framework, which achieved more precise segmentation compared to state-of-the-art methods on two datasets.
Segmentation of organs of interest in medical CT images is beneficial for diagnosis of diseases. Though recent methods based on Fully Convolutional Neural Networks (F-CNNs) have shown success in many segmentation tasks, fusing features from images with different scales is still a challenge: (1) Due to the lack of spatial awareness, F-CNNs share the same weights at different spatial locations. (2) F-CNNs can only obtain surrounding information through local receptive fields. To address the above challenge, we propose a new segmentation framework based on attention mechanisms, named MFA-Net (Multi-Scale Feature Fusion Attention Network). The proposed framework can learn more meaningful feature maps among multiple scales and result in more accurate automatic segmentation. We compare our proposed MFA-Net with SOTA methods on two 2D liver CT datasets. The experimental results show that our MFA-Net produces more precise segmentation on images with different scales.