{ "id": 267818, "title": "Question about scripts used to create Nifti images for both tasks. ", "url": "/competitions/rsna-miccai-brain-tumor-radiogenomic-classification/discussion/267818", "author_name": "", "post_date": "2021-08-24T19:57:02.664003300Z", "votes": 7, "comment_count": 4, "views": 0, "content": "

Hi @ujjwalbaid !
\nfirst thanks for all your work in putting this competition together.

\n

I was reading your paper about the data-sets: https://arxiv.org/abs/2107.02314
\nI saw the following paragraph:

\n

\"pre-processing has been applied to all the BraTS mpMRI scans.
\nSpecifically, the applied pre-processing routines include conversion of the DI-
\nCOM files to the NIFTI \ffile format [16], re-orientation to a common orientation
\nsystem (i.e., RAI), co-registration to the same anatomical template (SRI24) [17],
\nresampling to a uniform isotropic resolution (1mm3), and finally skull-stripping.
\nThe preprocessing pipeline is publicly available through the Cancer Imaging Phe-
\nnomics Toolkit (CaPTk) [18] and Federated Tumor Segmentation (FeTS) tool\"

\n

We see that co-registration to same anatomical template and resampling has already been done by your group.

\n

Now many participants are re-doing this in the competition.
\nWould it be possible to release the pre-processing scripts that you describe in the paper ?

\n

this way we could focus more on the classification rather than the pre-processing steps.
\nthanks
\nMehul

", "messages": [ { "id": "1489230", "postDate": "08/24/2021 19:57:02", "content": "

Hi @ujjwalbaid !
\nfirst thanks for all your work in putting this competition together.

\n

I was reading your paper about the data-sets: https://arxiv.org/abs/2107.02314
\nI saw the following paragraph:

\n

\"pre-processing has been applied to all the BraTS mpMRI scans.
\nSpecifically, the applied pre-processing routines include conversion of the DI-
\nCOM files to the NIFTI \ffile format [16], re-orientation to a common orientation
\nsystem (i.e., RAI), co-registration to the same anatomical template (SRI24) [17],
\nresampling to a uniform isotropic resolution (1mm3), and finally skull-stripping.
\nThe preprocessing pipeline is publicly available through the Cancer Imaging Phe-
\nnomics Toolkit (CaPTk) [18] and Federated Tumor Segmentation (FeTS) tool\"

\n

We see that co-registration to same anatomical template and resampling has already been done by your group.

\n

Now many participants are re-doing this in the competition.
\nWould it be possible to release the pre-processing scripts that you describe in the paper ?

\n

this way we could focus more on the classification rather than the pre-processing steps.
\nthanks
\nMehul

", "rawMarkdown": "Hi @ujjwalbaid ! \nfirst thanks for all your work in putting this competition together. \n\nI was reading your paper about the data-sets: https://arxiv.org/abs/2107.02314\nI saw the following paragraph:\n\n\"pre-processing has been applied to all the BraTS mpMRI scans.\nSpecifically, the applied pre-processing routines include conversion of the DI-\nCOM files to the NIFTI \ffile format [16], re-orientation to a common orientation\nsystem (i.e., RAI), co-registration to the same anatomical template (SRI24) [17],\nresampling to a uniform isotropic resolution (1mm3), and finally skull-stripping.\nThe preprocessing pipeline is publicly available through the Cancer Imaging Phe-\nnomics Toolkit (CaPTk) [18] and Federated Tumor Segmentation (FeTS) tool\"\n\nWe see that co-registration to same anatomical template and resampling has already been done by your group. \n\nNow many participants are re-doing this in the competition. \nWould it be possible to release the pre-processing scripts that you describe in the paper ? \n\nthis way we could focus more on the classification rather than the pre-processing steps. \nthanks\nMehul", "votes": null }, { "id": "1489241", "postDate": "08/24/2021 20:12:58", "content": "

Hi @ujjwalbaid !
\nI found this link: https://cbica.github.io/CaPTk/preprocessing_brats.html
\ncan we use binaries form this link for pre-processing ?

", "rawMarkdown": "Hi @ujjwalbaid ! \nI found this link: https://cbica.github.io/CaPTk/preprocessing_brats.html\ncan we use binaries form this link for pre-processing ?", "votes": null }, { "id": "1489536", "postDate": "08/25/2021 04:40:08", "content": "

This tool is slow and cannot be applied to the processing of the private test-set.
\nIs there a faster and better alternative? (Or the official can provide both dicom and Nifti format data, train & test)

", "rawMarkdown": "This tool is slow and cannot be applied to the processing of the private test-set. \nIs there a faster and better alternative? (Or the official can provide both dicom and Nifti format data, train & test)", "votes": null }, { "id": "1531289", "postDate": "10/01/2021 19:45:25", "content": "

@mpsampat from the page:

\n
\n

NOTE: This applications takes ~30 minutes to finish on an 8-core Intel i7 with 16GB of RAM.

\n
\n

that doesnt look like can be used for our inferernce

", "rawMarkdown": "mpsampat from the page:\n>NOTE: This applications takes ~30 minutes to finish on an 8-core Intel i7 with 16GB of RAM.\n\nthat doesnt look like can be used for our inferernce", "votes": null }, { "id": "1531290", "postDate": "10/01/2021 19:47:44", "content": "

@zzy990106 did you get any luck?

", "rawMarkdown": "zzy990106 did you get any luck?", "votes": null } ], "comments": [ { "id": 1489241, "author_name": "mpsampat", "author_url": "", "post_date": "08/24/2021 20:12:58", "content": "

Hi @ujjwalbaid !
\nI found this link: https://cbica.github.io/CaPTk/preprocessing_brats.html
\ncan we use binaries form this link for pre-processing ?

", "votes": null, "replies": [ { "id": 1531289, "author_name": "samshipengs", "author_url": "", "post_date": "10/01/2021 19:45:25", "content": "

@mpsampat from the page:

\n
\n

NOTE: This applications takes ~30 minutes to finish on an 8-core Intel i7 with 16GB of RAM.

\n
\n

that doesnt look like can be used for our inferernce

", "votes": null, "replies": [] } ] }, { "id": 1489536, "author_name": "zzy990106", "author_url": "", "post_date": "08/25/2021 04:40:08", "content": "

This tool is slow and cannot be applied to the processing of the private test-set.
\nIs there a faster and better alternative? (Or the official can provide both dicom and Nifti format data, train & test)

", "votes": null, "replies": [ { "id": 1531290, "author_name": "samshipengs", "author_url": "", "post_date": "10/01/2021 19:47:44", "content": "

@zzy990106 did you get any luck?

", "votes": null, "replies": [] } ] } ], "raw_markdown_by_id": { "1489230": "Hi @ujjwalbaid ! \nfirst thanks for all your work in putting this competition together. \n\nI was reading your paper about the data-sets: https://arxiv.org/abs/2107.02314\nI saw the following paragraph:\n\n\"pre-processing has been applied to all the BraTS mpMRI scans.\nSpecifically, the applied pre-processing routines include conversion of the DI-\nCOM files to the NIFTI \ffile format [16], re-orientation to a common orientation\nsystem (i.e., RAI), co-registration to the same anatomical template (SRI24) [17],\nresampling to a uniform isotropic resolution (1mm3), and finally skull-stripping.\nThe preprocessing pipeline is publicly available through the Cancer Imaging Phe-\nnomics Toolkit (CaPTk) [18] and Federated Tumor Segmentation (FeTS) tool\"\n\nWe see that co-registration to same anatomical template and resampling has already been done by your group. \n\nNow many participants are re-doing this in the competition. \nWould it be possible to release the pre-processing scripts that you describe in the paper ? \n\nthis way we could focus more on the classification rather than the pre-processing steps. \nthanks\nMehul", "1489241": "Hi @ujjwalbaid ! \nI found this link: https://cbica.github.io/CaPTk/preprocessing_brats.html\ncan we use binaries form this link for pre-processing ?", "1489536": "This tool is slow and cannot be applied to the processing of the private test-set. \nIs there a faster and better alternative? (Or the official can provide both dicom and Nifti format data, train & test)", "1531289": "mpsampat from the page:\n>NOTE: This applications takes ~30 minutes to finish on an 8-core Intel i7 with 16GB of RAM.\n\nthat doesnt look like can be used for our inferernce", "1531290": "zzy990106 did you get any luck?" }, "source": "meta" }