Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

LM-UNet Architecture.

The encoder and decoder of LM-UNet consist of PV-Mamba+EMA, with skip connections formed by EFF and MMSC. EFE is employed to fuse edge features from different levels of encoder layers and .

More »

Fig 1 Expand

Fig 2.

Parallel PV-Mamba Architecture.

More »

Fig 2 Expand

Fig 3.

Efficient Multi-scale Attention.

More »

Fig 3 Expand

Fig 4.

The Edge Feature Extraction Architecture.

More »

Fig 4 Expand

Fig 5.

The Edge Feature Fusion Architecture.

More »

Fig 5 Expand

Fig 6.

Multi-stage Multi-level Skip Connections.

More »

Fig 6 Expand

Table 1.

Detailed Comparison of LM-UNet and UVM-UNet.

More »

Table 1 Expand

Table 2.

Detailed Information on Data Collection for Each Center.

More »

Table 2 Expand

Table 3.

LM-UNet encoder input and output dimensions.

More »

Table 3 Expand

Table 4.

Performance comparison of different methods.

More »

Table 4 Expand

Fig 7.

Segmentation Results of Different Segmentation Methods on PROMISE12 Dataset.

More »

Fig 7 Expand

Fig 8.

Bar Chart of Evaluation Metrics for Different Segmentation Methods.

More »

Fig 8 Expand

Table 5.

Ablation experiments of different components.

More »

Table 5 Expand

Table 6.

Complexity analysis of different methods.

More »

Table 6 Expand

Fig 9.

Complexity analysis of different methods.

More »

Fig 9 Expand