F-Net: Breast cancerous lesion region segmenta-tion based on improved U-Net
- Article
- Figures
- Metrics
- Preview PDF
- Reference
- Related
- Cited by
- Materials
Abstract:
In order to solve the challenge of breast cancer region segmentation, we improved the U-Net net-work. CBAM-PA and Dformer modules were designed to replace the convolutional layers at the encoding side in the base U-Net; the input logic of the U-Net network was improved by dynami-cally adjusting the input size of each layer; and the short connections in the U-Net network were replaced with cross-layer connections to enhance the image restoration capability at the decoding side. On the BUSI dataset, we obtain a Dice coefficient of 0.8031 and an IoU value of 0.7362. The experimental results show that the proposed enhancement method effectively improves the accura-cy and quality of breast cancer lesion region segmentation.
Keywords:
Project Supported:
The National Natural Science Foundation of China (General Program, Key Program, Major Research Plan)
Clc Number:
