wassname/PROSTATEx_masks
1
0
Fork 0
mirror of https://github.com/wassname/PROSTATEx_masks.git synced 2026-09-09 11:15:16 +08:00
Code Issues Packages Projects Releases Wiki Activity

Updated readme.

Browse Source
This commit is contained in:
r.cuocolo
2021-04-29 12:31:41 +02:00
parent 2a9cc1aba6
commit af20144ccb
1 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+3 -1
View File
@@ -11,7 +11,7 @@ We encourage the use of this data for radiomics and machine learning investigati
### Lesion masks
The files are in compressed NIFTI (.nii.gz) format and collected in separate folders for T2 and ADC images (n = 299 lesions) within the "lesions/Masks" directory. Each filename contains the following information (separated by underscores):
The files are in compressed NIFTI (.nii.gz) format and collected in separate folders for T2 and ADC images (n = 299 lesions) within the "Files/lesions/Masks/For_original_DICOMs" directory. Each filename contains the following information (separated by underscores):
- "PROSTATEx Patient ID" + "Finding ID" + "Sequence name" + "ROI"
@@ -30,6 +30,8 @@ Patients who were classified as PI-RADS score = 2 did not undergo biopsy and the
Full exam DICOM files are retrievable through the Cancer Imaging Archive at: [https://wiki.cancerimagingarchive.net/display/Public/SPIE-AAPM-NCI+PROSTATEx+Challenges](https://wiki.cancerimagingarchive.net/display/Public/SPIE-AAPM-NCI+PROSTATEx+Challenges)
The same set of masks is also available matching the coordinates of the PROSTATEx DICOM files after conversion in NIFTI files using [dcm2niix](https://github.com/rordenlab/dcm2niix). These are located in the "Files/lesions/Masks/For_dcm2niix_files" directory. As there is a known [issue](https://github.com/rcuocolo/PROSTATEx_masks/issues/9) with ADC masks, these should be preferable for the moment.
### Original coordinate markers
These 3x3 masks are centered on the original lesion coordinates provided in the PROSTATEx dataset and were employed for the quality control assessment and as the basis for successive whole-lesion segmentation. For the sake of transparency, they are also included in the dataset in the same format as the lesion masks in the "Original_coordinate_markers" folder. This file set includes lesion markers for all axial T2 and ADC images included for each patient.