U-Net

Qi He1, Xianghao Cui1, Qingjing Fei1

  • 1National Key Laboratory of Wireless Communications, University of Electronic Science and Technology of China, Chengdu, 611731, China.

Scientific reports
|August 28, 2025
PubMed
概括

这项研究引入了面具自主监督预训,以提高超声波图像细分的U-Net性能,特别是有限的标记数据. 新的MS-UNet模型提高了准确性,同时大大降低了计算成本.