Failed to reproduce c-index of 0.58 for LUAD

[wangbo00129]

Hello, when I've successfully reproduced the c-indices in BRCA, UCEC and BLCA. However, when it came to LUAD, I got 0.529072 ± 0.057346, which is much lower than 0.585 ± 0.012 which you mentioned in your article. I repeated multiple times using the same paramters in your code and the results are similar to 0.53. Could you please help me out?

[XiaoXueShengwangrui]

Hello, when I've successfully reproduced the c-indices in BRCA, UCEC and BLCA. However, when it came to LUAD, I got 0.529072 ± 0.057346, which is much lower than 0.585 ± 0.012 which you mentioned in your article. I repeated multiple times using the same paramters in your code and the results are similar to 0.53. Could you please help me out?

你好，请问你解决了吗？我也是在复现LUAD的时候，结果大概在0.52-0.53左右，我根据作者以及issue中提到的技巧进行多次的尝试，还是无法得到论文中的结果。
其中包括：在x20倍率下采集256256大小的patch，提取resnet50特征，随后得到4个交叉验证的平均结果在0.52左右。随后，我在x40倍率下采集512512大小的patch，在提取resnet50特征是，将--custom_downsample 2 设置为2 ，同样得到了相似的结果。
如果你已经复现出与文章相近的结果，是否能告诉我是如何做的？非常感谢

[wangbo00129]

我印象里作者代码里有一个关于patch数量的过滤，太多patch的样本会被忽略，应该是个整数，搜一下000应该可以定位到

…

---- Replied Message ---- | From | ***@***.***> | | Date | 08/05/2024 23:27 | | To | ***@***.***> | | Cc | ***@***.***>***@***.***> | | Subject | Re: [mahmoodlab/Patch-GCN] Failed to reproduce c-index of 0.58 for LUAD (Issue #33) | Hello, when I've successfully reproduced the c-indices in BRCA, UCEC and BLCA. However, when it came to LUAD, I got 0.529072 ± 0.057346, which is much lower than 0.585 ± 0.012 which you mentioned in your article. I repeated multiple times using the same paramters in your code and the results are similar to 0.53. Could you please help me out? 你好，请问你解决了吗？我也是在复现LUAD的时候，结果大概在0.52-0.53左右，我根据作者以及issue中提到的技巧进行多次的尝试，还是无法得到论文中的结果。 其中包括：在x20倍率下采集256256大小的patch，提取resnet50特征，随后得到4个交叉验证的平均结果在0.52左右。随后，我在x40倍率下采集512512大小的patch，在提取resnet50特征是，将--custom_downsample 2 设置为2 ，同样得到了相似的结果。 如果你已经复现出与文章相近的结果，是否能告诉我是如何做的？非常感谢 — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: ***@***.***>

[XiaoXueShengwangrui]

我印象里作者代码里有一个关于patch数量的过滤，太多patch的样本会被忽略，应该是个整数，搜一下000应该可以定位到
…
---- Replied Message ---- | From | @.> | | Date | 08/05/2024 23:27 | | To | @.> | | Cc | @.>@.> | | Subject | Re: [mahmoodlab/Patch-GCN] Failed to reproduce c-index of 0.58 for LUAD (Issue #33) | Hello, when I've successfully reproduced the c-indices in BRCA, UCEC and BLCA. However, when it came to LUAD, I got 0.529072 ± 0.057346, which is much lower than 0.585 ± 0.012 which you mentioned in your article. I repeated multiple times using the same paramters in your code and the results are similar to 0.53. Could you please help me out? 你好，请问你解决了吗？我也是在复现LUAD的时候，结果大概在0.52-0.53左右，我根据作者以及issue中提到的技巧进行多次的尝试，还是无法得到论文中的结果。 其中包括：在x20倍率下采集256256大小的patch，提取resnet50特征，随后得到4个交叉验证的平均结果在0.52左右。随后，我在x40倍率下采集512512大小的patch，在提取resnet50特征是，将--custom_downsample 2 设置为2 ，同样得到了相似的结果。 如果你已经复现出与文章相近的结果，是否能告诉我是如何做的？非常感谢 — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

好的，感谢！