Signed-off-by: Yiheng Wang [email protected]

Fixes #4258 .

Description

This PR is used to:

1. add TciaDataset, which is able to download and data from TCIA.
2. enhance PydicomReader to support load dicom data with modality "SEG"

Dataset download and load images

I've tested with the following collections with seg_type = "SEG":

• LIDC-IDRI
• C4KC-KiTS
• NSCLC Radiogenomics
• NSCLC-Radiomics
• NSCLC-Radiomics-Interobserver1
• PROSTATEx
• QIN LUNG CT
• QIN-PROSTATE-Repeatability
• RIDER Lung CT

Also tested with the following collections with seg_type = "RTSTRUCT":

• Pancreatic-CT-CBCT-SEG
• Pediatric-CT-SEG
• LCTSC
• 4D-Lung

load "SEG" data

For collections that contain modality "SEG", if tag "PerFrameFunctionalGroupsSequence" exists for each frame of the dicom file, the reader is able to load the data (this method refers to: Highdicom ). Therefore, for the collections with seg_type = "SEG" mentioned above, some of them cannot be recognized:

• LIDC-IDRI
• NSCLC Radiogenomics
• QIN LUNG CT
• RIDER Lung CT

Status

Ready

progresses:

• Implement TciaDataset

Types of changes

• Non-breaking change (fix or new feature that would not break existing functionality).
• Breaking change (fix or new feature that would cause existing functionality to change).
• New tests added to cover the changes.
• Integration tests passed locally by running ./runtests.sh -f -u --net --coverage.
• Quick tests passed locally by running ./runtests.sh --quick --unittests --disttests.
• In-line docstrings updated.
• Documentation updated, tested make html command in the docs/ folder.