DSB2017
DSB2017 copied to clipboard
lfz
I want to find the corresponding label for test.npy
I want to find the corresponding label for test.npy(DSB2017/training/detector/test.npy ) I see it in the paper.Because our detection module is designed to neglect the very small nodules during training, the LUNA16 evaluation system is not suitable for evaluating its performance. We evaluated the performance on the validation set of DSB. It contains data from 198 cases and there are 71 (7 nodules smaller than 6 mm are ruled out) nodules in total. The Free Response Operating Characteristic (FROC) curve is shown in Fig. 7a. The average recall at 1/8, 1/4, 1/2, 1, 2, 4, 8 false positive per scan is 0.8562.
I want to evaluate my model with the LUNA16 evaluation system. I would like to be able to upload a test.npy corresponding label, or send a message to [email protected], thank you very much
我不是很明白你的问题，你可以发中文
2018-01-30 11:43 GMT+08:00 yz275252130 [email protected]:
I want to find the corresponding label for test.npy(DSB2017/training/detector/test.npy ) I see it in the paper.Because our detection module is designed to neglect the very small nodules during training, the LUNA16 evaluation system is not suitable for evaluating its performance. We evaluated the performance on the validation set of DSB. It contains data from 198 cases and there are 71 (7 nodules smaller than 6 mm are ruled out) nodules in total. The Free Response Operating Characteristic (FROC) curve is shown in Fig. 7a. The average recall at 1/8, 1/4, 1/2, 1, 2, 4, 8 false positive per scan is 0.8562.
I want to evaluate my model with the LUNA16 evaluation system. I would like to be able to upload a test.npy corresponding label, or send a message to [email protected], thank you very much
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/lfz/DSB2017/issues/66, or mute the thread https://github.com/notifications/unsubscribe-auth/AIigQ65HjPb5OKp-yEkiLgQgVc2O8Tgcks5tPo_RgaJpZM4RxuGk .
-- 廖方舟 清华大学医学院 Liao Fangzhou School of Medicine Tsinghua University Beijing 100084 China
在该项目 对应的论文中 我看到如下描述：（论文地址https://arxiv.org/pdf/1711.08324.pdf） 由于我们的检测模块设计为在训练期间忽略非常小的结节，所以LUNA16评估系统不是适合评估其性能。我们评估了DSB验证集的性能。它包含198例病例的数据，总共有71个（小于6毫米的结节被排除）结节。自由响应操作特性（FROC）曲线如图7a所示。每次扫描的1/8，1 / 4,1 / 2,1,2,4,8假阳性的平均回忆是0.8562。
在项目代码中我找到了test.npy 文件（DSB2017 / training / detector / test.npy）这个应该就是论文中描述的对应的198例病例。我也想用这198个病例的数据 通过LUNA16评估系统来做FROC评估 我自己训练的模型。在使用LUNA16评估程序 时 需要 这198个病例的数据 对应的标签文件，但是我没找到。希望得到你的帮助，谢谢！
这个198个病例的数据可以从DSB原网站的数据栏目下载，另外，这个198个不是luna的，是kaggle的数据，里边的标签是我们自己打的，并不准
在 2018年1月30日 下午5:02，yz275252130 [email protected]写道：
在该项目 对应的论文中 我看到如下描述：（论文地址https://arxiv.org/pdf/1711.08324.pdf） 由于我们的检测模块设计为在训练期间忽略非常小的结节，所以LUNA16评估系统不是适合评估其性能。 我们评估了DSB验证集的性能。它包含198例病例的数据，总共有71个（小于6毫米的结节被排除）结节。 自由响应操作特性（FROC）曲线如图7a所示。每次扫描的1/8，1 / 4,1 / 2,1,2,4,8假阳性的平均回忆是0.8562。
在项目代码中我找到了test.npy 文件（DSB2017 / training / detector / test.npy） 这个应该就是论文中描述的对应的198例病例。我也想用这198个病例的数据 通过LUNA16评估系统来做FROC评估 我自己训练的模型。在使用LUNA16评估程序 时 需要 这198个病例的数据 对应的标签文件，但是我没找到。希望得到你的帮助，谢谢！
— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/lfz/DSB2017/issues/66#issuecomment-361522415, or mute the thread https://github.com/notifications/unsubscribe-auth/AIigQwTorPwfFHc9YB1grugH44qp3HrGks5tPtqggaJpZM4RxuGk .
-- 廖方舟 清华大学医学院 Liao Fangzhou School of Medicine Tsinghua University Beijing 100084 China
这些原始label数据全都在label文件夹那些表格文件里边
这个test npy 只适合这个crop和分辨率
在 2018年1月31日 上午10:40，yz275252130 [email protected]写道：
这个198个病例的数据 我已经下载了，希望你们能够把这198个病例对应的标签数据给我一份 谢谢了！
— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/lfz/DSB2017/issues/66#issuecomment-361805385, or mute the thread https://github.com/notifications/unsubscribe-auth/AIigQ0Lat6NVsdZ2NMI5WVbHGdSxFc3dks5tP9KMgaJpZM4RxuGk .
-- 廖方舟 清华大学医学院 Liao Fangzhou School of Medicine Tsinghua University Beijing 100084 China
你好 我也是研究这个问题的，我把test.npy看了我也那些id我查了下那些csv我也没有发现。我现在我就暂时用所有的LUNA16的data来evaluate的。
