SAGAN icon indicating copy to clipboard operation
SAGAN copied to clipboard

FAQ regarding the usage of the dataset

Open xinario opened this issue 5 years ago • 12 comments

  1. Which are the 850 images mentioned in your paper? Inside each experiment folder (SE0, SE1....SE28), there are 906 images. So to get the exact 850 images, you need to, first, reordering the image sequence according to the [SliceLocation] field of the Dicom image (sort in ascending order) and you will get images arranged from pelvis to head. Then just keeping slice 21 to 870 and discard the rest which has almost no content.

  2. What is the train/test split? After obtaining the 850 ordered images, test images were selected at an interval of 6, i.e. slice 1, 7, 13 … 847.

  3. How do you compute the PSNR and SSIM for the simulated and real dataset? For the simulated data, the generated noisy image was converted to uint8 using the abdomen window (center: 40, width: 400). The training and evaluation were all conducted using these narrow range 8 bit images. For the piglet data, the original 16 bit value was used. The training and evaluation was on 16 bit images.

  4. What should I do when my test dicom data is not uint16? In this case, the correct way to convert the data in preprocess.py is ([Hounsfield units]+1024)*22

xinario avatar Jan 22 '19 22:01 xinario

I have been searching for the datasets, would you send me the datasets? Thank you very much!

JackChan666 avatar Apr 09 '19 16:04 JackChan666

You can download the dataset from the below link: https://docs.google.com/forms/d/e/1FAIpQLSdnIxHU-hX_fDC4FSqnTe_BbvF3MR4N1hkIMT0T5SHwcmqP0Q/viewform

xinario avatar Apr 09 '19 20:04 xinario

Thank you very much!

JackChan666 avatar Apr 10 '19 05:04 JackChan666

But how to reorder the image sequence according to the [SliceLocation] field of the Dicom image,could u give more detailed information,cuz when i try to preprocess,the code cant detect the dicom file

stefenmax avatar May 03 '20 12:05 stefenmax

That info is in the dicom header. It can be extracted using package like pydicom. I would suggest you to review some dicom basics before proceeding.

xinario avatar May 07 '20 21:05 xinario

You can download the dataset from the below link: https://docs.google.com/forms/d/e/1FAIpQLSdnIxHU-hX_fDC4FSqnTe_BbvF3MR4N1hkIMT0T5SHwcmqP0Q/viewform

i downloaded this link from onedrive. but it didnt unzip correctly. can you help me?

alexxony avatar Jul 22 '20 01:07 alexxony

Can you just try to redownload? I haven't get any issue like this before.

xinario avatar Jul 22 '20 21:07 xinario

Can you just try to redownload? I have get any issue like this before.

i tried to unzip in both windows and ubuntu.

But when in windows. it failed to start unzip

when in ubuntu. it failed to unzip during process.

  • another question.

i tried to install torch7 in ubuntu 20.04. but it failed to install and tf didnt work.

can i use pytorch instead of torch7?

alexxony avatar Jul 25 '20 14:07 alexxony

I would like to use this data set. However, when I jump to the link, the image does not exist.

yuta0511 avatar Mar 07 '22 06:03 yuta0511

You can download the dataset from the below link: https://docs.google.com/forms/d/e/1FAIpQLSdnIxHU-hX_fDC4FSqnTe_BbvF3MR4N1hkIMT0T5SHwcmqP0Q/viewform

image when I try to download using this link this happened ..please help me in getting the data

Tihetna1891 avatar Apr 11 '22 18:04 Tihetna1891

I want to get the dataset. but, the warning happened ... please help me in getting the data

sunyoungIT avatar May 23 '22 07:05 sunyoungIT