Linhao_Qu_FDUMICCAI

icon indicating a website link linhao-qu.github.io

icon company Digital Medical Research Center, Fudan University icon location Shanghai, China icon location My official account. Ph.D. student of BME in Fudan University. Research interests include medical image processing, information fusion and data mining.

Results 10 comments of Linhao_Qu_FDUMICCAI

关于测试

@huhaojin We recommend to use the sliding window strategy to fuse input images of arbitrary non-256 * 256 size, i.e., fusing images of 256 * 256 window size at a...

关于测试

@linqwn We recommend to use the sliding window strategy to fuse input images of arbitrary non-256 * 256 size, i.e., fusing images of 256 * 256 window size at a...

Problems about testing

@CBY-9527 We recommend to use the sliding window strategy to fuse input images of arbitrary non-256 * 256 size, i.e., fusing images of 256 * 256 window size at a...

about "input images"

@1900lxl We recommend to use the sliding window strategy to fuse input images of arbitrary non-256 * 256 size, i.e., fusing images of 256 * 256 window size at a...

关于“fusion_arbitary_size_TransMEF_gray.py”

Thanks for solving this issue!

Data split for all the few-shot experiments?

> Hi ,what's your data split for few-shot experiments? For example, in one-shot or two-shot setting, how to split training/validation set? Hello! Thanks for your attention. The data split for...

Data split for all the few-shot experiments?

> Hi, > > Thanks for your quick response~. I have diligently tried seeds 0, 128, 192, 111111, and 101012, but have found it challenging to replicate the high AUC...

Data split for all the few-shot experiments?

> The setting is not reasonable, because few-shot performance is highly related to the split. Repeat 5 times at different data split is much more standard instead of a fixed...

Data preprocessing

The guidance will be provided soon!

Cannot reproduce the scores reported in the paper

Thank you very much for your interest in our work! In our experiments, we used 20x magnification for the TCGA dataset, dividing it into 224x224 patches, and utilized CLIP for...