This pipeline is also available from the web on the CBICA Image Processing Portal. Please see the experiment on the portal for details.

REQUIREMENTS:

4 structural MRI images (T1, T1CE, T2, FLAIR), preferably in NIfTI format
- For DICOM images, please pass the first image in each of the series as input, not the folder.

USAGE:

This CLI-only application takes 4 structural brain MRIs as input and performs the following steps [1-3]:

Re-orientation to LPS/RAI
Image registration to SRI-24 Atlas [4] which includes the following steps
1. N4 Bias correction (This is a TEMPORARY STEP, and is not applied in the final co-registered output images. It is only use to facilitate optimal registration.)
2. Rigid Registration of T1, T2, FLAIR to T1CE
3. Rigid Registration of T1CE to SRI-24 atlas [4]
4. Applying transformation to the reoriented images
OPTIONAL: Deep-Learning based Skull-stripping [5]
OPTIONAL: Deep-Learning based Tumor Segmentation [6]

Example command:

${CaPTk_InstallDir}/bin/BraTSPipeline.exe -t1 C:/test/t1.nii.gz -t1c C:/test/t1ce.nii.gz -t2 C:/test/t2.nii.gz -fl C:/test/flair.nii.gz -o C:/test/outputDir

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

Explanation of output files:

Final co-registered images:

T1_to_SRI.nii.gz : Co-registered T1 image
T1CE_to_SRI.nii.gz: Co-registered T1CE image
T2_to_SRI.nii.gz: Co-registered T2 image
FL_to_SRI.nii.gz: Co-registered FLAIR image

(Optional) Deep Learning based masks:

brainMask_SRI.nii.gz
brainTumorMask_SRI.nii.gz

(Optional) Co-registered images, with brain mask applied:

T1_to_SRI_brain.nii.gz
T1CE_to_SRI_brain.nii.gz
T2_to_SRI_brain.nii.gz
FL_to_SRI_brain.nii.gz

(Optional) Intermediate files (similar for T1CE, T2, FLAIR):

T1_raw.nii.gz : NifTi file converted from input DICOM, or copy of input NifTI file
T1_rai.nii.gz : Image re-oriented to LPS/RAI
T1_rai_n4.nii.gz : Image with N4 bias correction applied to T1_rai.nii.gz
T1_to_T1CE.mat : transformation matrix of Rigid registration, T1 to T1CE
T1CE_to_SRI.mat : transformation matrix of Rigid registration, T1CE to SRI

Reference:

B. H. Menze, A. Jakab, S. Bauer, J. Kalpathy-Cramer, K. Farahani, J. Kirby, et al. "The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)", IEEE Transactions on Medical Imaging 34(10), 1993-2024 (2015) DOI:10.1109/TMI.2014.2377694
S. Bakas, H. Akbari, A. Sotiras, M. Bilello, M. Rozycki, J.S. Kirby, et al., "Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features", Nature Scientific Data, 4:170117 (2017) DOI:10.1038/sdata.2017.117
S. Bakas, M. Reyes, A. Jakab, S. Bauer, M. Rempfler, A. Crimi, et al., "Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge", arXiv preprint arXiv:1811.02629 (2018)
T.Rohlfing, N.M.Zahr, E.V.Sullivan, A.Pfefferbaum, "The SRI24 multichannel atlas of normal adult human brain structure", Human Brain Mapping, 31(5):798-819, 2010, DOI:10.1002/hbm.20906
S.Thakur, J.Doshi, S.Pati, S.Rathore, C.Sako, M.Bilello, S.M.Ha, G.Shukla, A.Flanders, A.Kotrotsou, M.Milchenko, S.Liem, G.S.Alexander, J.Lombardo, J.D.Palmer, P.LaMontagne, A.Nazeri, S.Talbar, U.Kulkarni, D.Marcus, R.Colen, C.Davatzikos, G.Erus, S.Bakas, "Brain Extraction on MRI Scans in Presence of Diffuse Glioma: Multi-institutional Performance Evaluation of Deep Learning Methods and Robust Modality-Agnostic Training, NeuroImage, Epub-ahead-of-print, 2020. -# K.Kamnitsas, C.Ledig, V.F.J.Newcombe, J.P.Simpson, A.D.Kane, D.K.Menon, D.Rueckert, B.Glocker, "Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation", Medical Image Analysis, 2016.