LSUnetMix: Fuse channel feature information with long–short term memory
Abstract Medical image segmentation based on deep learning is becoming popular. To improve the segmentation accuracy of medical images such as cells and vessels, we propose the LSUnetMix model, which can effectively enhance the ability to extract channel information and capture image details better....
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-03-01
|
| Series: | IET Computer Vision |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/cvi2.12158 |
| Summary: | Abstract Medical image segmentation based on deep learning is becoming popular. To improve the segmentation accuracy of medical images such as cells and vessels, we propose the LSUnetMix model, which can effectively enhance the ability to extract channel information and capture image details better. It surpasses both traditional and latest models on medical datasets. This model is mainly based on Unet, and three modules have been added. The first is the Channel Information Transmission module, which uses long–short term memory to get the sequential features of layers and unidirectionally transfer the channel information of the upper layer to the lower layer, which combines multiple layers of information while avoiding information redundancy. The second is the Prospect Enhancement module, which activates the channel information of the image and enhances the ability to recognise the segmentation targets. The third is the Multiscale Dilated Convolution module, which uses multi‐scale dilated convolution to strengthen the ability and to extract the image details. After experiments, their model performs best on GlaS and MoNuseg datasets, which can segment image details better and avoid redundant information, and the Dice coefficient reaches 91.92% on GlaS and 81.8% on MoNuSeg. |
|---|---|
| ISSN: | 1751-9632 1751-9640 |