文件列表:
食管癌与危及器官的自监督学习及其不确定性量化分割【英文版】.pdf |
下载文档 |
资源简介
>
英文标题:Self-Supervised Learning for Organs At Risk and Tumor Segmentation with Uncertainty Quantification中文摘要:本研究旨在展示自我监督预训练模型在器官风险和肿瘤分割任务中相对于昂贵的全监督学习的影响,所提出的 MC-Swin-U 算法采用了蒙特卡罗变换器,与许多其他模型不同,其使用蒙特卡罗 Dropout 戳降低了不确定性,并在公共和私人数据集上进行了测试和验证, 相比大规模注释成本提供了附加收益,并且明显提高了分割评分。英文摘要:In this study, our goal is to show the impact of self-supervised pre-trainingof transformers for organ at risk (OAR) and tumor segmentation as compared tocostly fully-supervised learning. The proposed algorithm is called Monte Ca
加载中...
已阅读到文档的结尾了