COVID-CTset
COVID-CTset copied to clipboard
Image
Hello,
Thank you for uploading such a great dataset! I was opening some of the images up, and for some reason, they look like this:
Additionally, when I try to use other .tif images with your code (the one for COVID-19 classification), it doesn't work. They look like this:
Do you know what may be the problem? I think you have a different format or something for your tif files versus mine, but I am not sure.
Hi;
Thank you for your interest in our work!
The original Images in our dataset are in TIFF format (16-bit uint type), which contain the same image data as the DICOM format and only do not include the patients metadata. But you can not visualize this TIFF format images with your monitor and they look like completely black images (because standard monitors can not show 16-bit images in uint type). So if you would like to convert these images to visualizable images you can use [This code.](https://github.com/mr7495/COVID-CTset/blob/master/Visualize.py)
My suggestion is to use the original images for training or testing the models in order to not lose any data.
Some of the images converted to visualizable format are:
vis_data.zip
Thank you for your prompt reply! I realized why my other tif images do not work with the code (as they are in float32 format, rather than uint16 format). Do you know a way to convert these images into the uint16 type?
Additionally, if I was to use the visualizer code, how can I convert the result back to the original image?
hi, thank you for your so excited work, have you tried convert these images to nii.gz format? that is commonly in medical image analysis, do you have some experience about this?
Hey, @latexers ya I asked that question a pretty long time back and I eventually figured out how to convert it to nii.gz, but thanks for your help!
Hello all, No, unfortunately, we did not convert the images to 3D NII format, but I think the code for converting the images to this format can be access through other websites.
Hey, @latexers ya I asked that question a pretty long time back and I eventually figured out how to convert it to nii.gz, but thanks for your help!
I found a tool for this convter: https://github.com/rordenlab/dcm2niix