Title | ||
---|---|---|
A dual meta-learning framework based on idle data for enhancing segmentation of pancreatic cancer |
Abstract | ||
---|---|---|
•A novel dual meta-learning framework based on idle multi-parametric MRIs is developed to enhance the segmentation performance of CT pancreatic cancer, one to explore commonalities in idle multi-parametric MRIs, and the other to obtain salient knowledge of CT images.•Intermediate modalities are used to smoothly fill the gap between different modalities, providing abundant intermediate representations to boost the performance of our meta-learning scheme.•This approach is an effective pancreatic cancer segmentation framework, which can be easily integrated into other segmentation networks.•This method is a potential paradigm for leveraging idle data to mitigate the challenge of data scarcity. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1016/j.media.2021.102342 | Medical Image Analysis |
Keywords | DocType | Volume |
Pancreatic cancer segmentation,Idle data,Dual meta-learning,Random style transfer | Journal | 78 |
ISSN | Citations | PageRank |
1361-8415 | 0 | 0.34 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jun Li | 1 | 747 | 90.31 |
Liang Qi | 2 | 0 | 0.34 |
Qingzhong Chen | 3 | 0 | 0.34 |
Yu-Dong Zhang | 4 | 0 | 1.35 |
Xiaohua Qian | 5 | 4 | 3.78 |