CMU-Net: A Strong ConvMixer-based Medical Ultrasound Image Segmentation Network
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913564174843904 |
|---|---|
| author | Tang, Fenghe Wang, Lingtao Ning, Chunping Xian, Min Ding, Jianrui |
| author_facet | Tang, Fenghe Wang, Lingtao Ning, Chunping Xian, Min Ding, Jianrui |
| contents | U-Net and its extensions have achieved great success in medical image segmentation. However, due to the inherent local characteristics of ordinary convolution operations, U-Net encoder cannot effectively extract global context information. In addition, simple skip connections cannot capture salient features. In this work, we propose a fully convolutional segmentation network (CMU-Net) which incorporates hybrid convolutions and multi-scale attention gate. The ConvMixer module extracts global context information by mixing features at distant spatial locations. Moreover, the multi-scale attention gate emphasizes valuable features and achieves efficient skip connections. We evaluate the proposed method using both breast ultrasound datasets and a thyroid ultrasound image dataset; and CMU-Net achieves average Intersection over Union (IoU) values of 73.27% and 84.75%, and F1 scores of 84.81% and 91.71%. The code is available at https://github.com/FengheTan9/CMU-Net. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2210_13012 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | CMU-Net: A Strong ConvMixer-based Medical Ultrasound Image Segmentation Network Tang, Fenghe Wang, Lingtao Ning, Chunping Xian, Min Ding, Jianrui Image and Video Processing Computer Vision and Pattern Recognition U-Net and its extensions have achieved great success in medical image segmentation. However, due to the inherent local characteristics of ordinary convolution operations, U-Net encoder cannot effectively extract global context information. In addition, simple skip connections cannot capture salient features. In this work, we propose a fully convolutional segmentation network (CMU-Net) which incorporates hybrid convolutions and multi-scale attention gate. The ConvMixer module extracts global context information by mixing features at distant spatial locations. Moreover, the multi-scale attention gate emphasizes valuable features and achieves efficient skip connections. We evaluate the proposed method using both breast ultrasound datasets and a thyroid ultrasound image dataset; and CMU-Net achieves average Intersection over Union (IoU) values of 73.27% and 84.75%, and F1 scores of 84.81% and 91.71%. The code is available at https://github.com/FengheTan9/CMU-Net. |
| title | CMU-Net: A Strong ConvMixer-based Medical Ultrasound Image Segmentation Network |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2210.13012 |