An Ensemble of U-Net Models for Kidney Tumor Segmentation With CT Images.
An Ensemble of U-Net Models for Kidney Tumor Segmentation With CT Images.
复制标题
DOI：
10.1109/tcbb.2021.3085608
复制
发表时间：
2022-05
期刊：
影响因子：
--
通讯作者：
中科院分区：
文献类型：
--
作者：
我们在此介绍 2019 年肾肿瘤分割挑战赛 (KiTS19) 的阿肯色州 AI-Campus 解决方案。我们的阿肯色州 AI-Campus 团队于 2019 年 3 月至 7 月参加了为期四个月的 KiTS19 挑战赛。本文总结了我们针对这一生物医学成像分析重大挑战的方法、培训、测试和验证结果。我们的深度学习模型是在测试许多模型变体后开发的 U-Net 模型的集合。我们的模型在本地测试数据集和最终竞争独立测试数据集上具有一致的性能。该模型在肾脏和肿瘤分割方面获得了 0.949 的本地测试 Dice 分数，在肿瘤分割方面获得了 0.601 的本地测试 Dice 分数，最终竞赛测试的 Dice 分数分别为 0.9470 和 0.6099。阿肯色州AI-Campus团队解决方案综合DICE得分为0.7784，最终在KiTS19竞赛中排名全球前五十，美国团队前五。
We present here the Arkansas AI-Campus solution method for the 2019 Kidney Tumor Segmentation Challenge (KiTS19). Our Arkansas AI-Campus team participated the KiTS19 Challenge for four months, from March to July of 2019. This paper provides a summary of our methods, training, testing and validation results for this grand challenge in biomedical imaging analysis. Our deep learning model is an ensemble of U-Net models developed after testing many model variations. Our model has consistent performance on the local test dataset and the final competition independent test dataset. The model achieved local test Dice scores of 0.949 for kidney and tumor segmentation, and 0.601 for tumor segmentation, and the final competition test earned Dice scores 0.9470 and 0.6099 respectively. The Arkansas AI-Campus team solution with a composite DICE score of 0.7784 has achieved a final ranking of top fifty worldwide, and top five among the United States teams in the KiTS19 Competition.