Focal-UNet: UNet-like Focal Modulation for Medical Image Segmentation

TL;DR

Focal-UNet introduces a focal modulation mechanism into a U-shaped architecture to enhance medical image segmentation, effectively combining local and global features to outperform existing transformer-based models.

Contribution

It proposes a novel Focal-UNet architecture with asymmetric encoder-decoder depths that leverages focal modulation to improve segmentation accuracy over transformer-based models.

Findings

Achieved 1.68% higher DICE score on Synapse dataset.

Improved HD metric by 0.89 on Synapse dataset.

Outperformed Swin-UNet in segmentation tasks.

Abstract

Recently, many attempts have been made to construct a transformer base U-shaped architecture, and new methods have been proposed that outperformed CNN-based rivals. However, serious problems such as blockiness and cropped edges in predicted masks remain because of transformers' patch partitioning operations. In this work, we propose a new U-shaped architecture for medical image segmentation with the help of the newly introduced focal modulation mechanism. The proposed architecture has asymmetric depths for the encoder and decoder. Due to the ability of the focal module to aggregate local and global features, our model could simultaneously benefit the wide receptive field of transformers and local viewing of CNNs. This helps the proposed method balance the local and global feature usage to outperform one of the most powerful transformer-based U-shaped models called Swin-UNet. We achieved a 1.68% higher DICE score and a 0.89 better HD metric on the Synapse dataset. Also, with extremely limited data, we had a 4.25% higher DICE score on the NeoPolyp dataset. Our implementations are available at: https://github.com/givkashi/Focal-UNet