# PLU-Net: Extraction of multi-scale feature fusion

## TL;DR

PLU-Net enhances medical image segmentation by integrating multi-scale feature fusion modules like ASPP, SE, PS, and LS blocks into U-Net, achieving superior results with fewer parameters.

## Contribution

The paper introduces PLU-Net, a novel architecture combining multiple feature fusion modules to improve boundary detail preservation in medical segmentation.

## Key findings

- Outperforms existing models on three benchmark datasets.
- Uses fewer parameters and FLOPs than comparable methods.
- Achieves better boundary segmentation accuracy.

## Abstract

Deep learning algorithms have achieved remarkable results in medical image segmentation in recent years. These networks are unable to handle with image boundaries and details with enormous parameters, resulting in poor segmentation results. To address the issue, we develop atrous spatial pyramid pooling (ASPP) and combine it with the Squeeze-and-Excitation block (SE block), as well as present the PS module, which employs a broader and multi-scale receptive field at the network's bottom to obtain more detailed semantic information. We also propose the Local Guided block (LG block) and also its combination with the SE block to form the LS block, which can obtain more abundant local features in the feature map, so that more edge information can be retained in each down sampling process, thereby improving the performance of boundary segmentation. We propose PLU-Net and integrate our PS module and LS block into U-Net. We put our PLU-Net to the test on three benchmark datasets, and the results show that by fewer parameters and FLOPs, it outperforms on medical semantic segmentation tasks.