Strategies for tackling the class imbalance problem of oropharyngeal primary tumor segmentation on magnetic resonance imaging
Physics and Imaging in Radiation Oncology(2022)
摘要
•Loss functions that account for class imbalance may not improve the segmentations.•Our two-stage segmentation approach can outperform the 3D U-Net.•A fully-automatic two-stage approach can perform comparably to a semi-automatic approach.
更多查看译文
关键词
Oropharyngeal cancer,Convolutional neural network,Segmentation,Class imbalance, MRI,Two-stage approach
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要