TransClaw U-Net: Claw U-Net with Transformers for Medical Image Segmentation
This is an incremental improvement for medical image segmentation, addressing a known bottleneck in convolutional neural networks for computer-aided diagnosis.
The paper tackles the problem of inaccurate long-term spatial feature extraction in medical image segmentation by proposing TransClaw U-Net, which combines convolution and transformer operations, and reports better performance than other network structures on the Synapse Multi-organ Segmentation Datasets.
In recent years, computer-aided diagnosis has become an increasingly popular topic. Methods based on convolutional neural networks have achieved good performance in medical image segmentation and classification. Due to the limitations of the convolution operation, the long-term spatial features are often not accurately obtained. Hence, we propose a TransClaw U-Net network structure, which combines the convolution operation with the transformer operation in the encoding part. The convolution part is applied for extracting the shallow spatial features to facilitate the recovery of the image resolution after upsampling. The transformer part is used to encode the patches, and the self-attention mechanism is used to obtain global information between sequences. The decoding part retains the bottom upsampling structure for better detail segmentation performance. The experimental results on Synapse Multi-organ Segmentation Datasets show that the performance of TransClaw U-Net is better than other network structures. The ablation experiments also prove the generalization performance of TransClaw U-Net.