A small library to extract supervoxels based on enhancement curves of perfusion images (such as DCE-MRI or pCT) using principal component analysis. This method extends the standard SLIC implementation of scitkit-image (http:https://scikit-image.org/docs/dev/api/skimage.segmentation.html).

For research purposes only.

References

Irving, B; Franklin, JM; Papiez, BW; Anderson, EM; Sharma, RA; Gleeson, FV; Brady, M; and Schnabel, JA. Pieces-of-parts for supervoxel segmentation with global context: Application to DCE-MRI tumour delineation. Journal of Medical Image Analysis 2016 (accepted). http:https://dx.doi.org/10.1016/j.media.2016.03.002

Irving, B; Cifor, A; Papiez, BW; Franklin, J; Anderson, EM; Brady, M; and Schnabel, JA. Automated colorectal tumour segmentation in DCE-MRI using supervoxel neighbourhood contrast characteristics. Proc MICCAI 2014, 8673, 609-616.

python 2.7 or python 3.4+

Python libraries:

• numpy
• nibabel
• matplotlib
• h5py
• scipy
• Cython
• scikit-image
• scikit-learn
• wheel

Option 1) Build the project in it's current location

Build Cython extensions of the library in the current location using:

python setup.py build_ext --inplace

Option 2) Install in your python directory

python setup.py bdist_wheel
pip install dist/perfusionslic-0.20-cp27-cp27mu-linux_x86_64.whl

Download the .mat example QIN breast DCE-MRI data from under releases and copy to the folder.

Run the demo script

python perfusion_slic_demo.py

Ouput showing the a cross section through a single slice and supervoxels:

QIN-Breast-DCE-MRI-BC10-V1.mat

From: https://wiki.cancerimagingarchive.net/display/Public/QIN+Breast+DCE-MRI

Licence: CC BY 3.0 (http:https://creativecommons.org/licenses/by/3.0/)

Reference: Huang W, Li X, Chen Y, Li X, Chang MC, Oborski MJ, Malyarenko DI, Muzi M, Jajamovich GH, Fedorov A, Tudorica A, Gupta SN, Laymon CM, Marro KI, Dyvorne HA, Miller JV, Barbodiak DP, Chenevert TL, Yankeelov TE, Mountz JM, Kinahan PE, Kikinis R, Taouli B, Fennessy F, Kalpathy-Cramer J. Variations of dynamic contrast-enhanced magnetic resonance imaging in evaluation of breast cancer therapy response: a multicenter data analysis challenge. Trans Oncol 2014;7:153-166. PubMed PMID: 24772219; PubMed Central PMCID: PMC3998693

• add missing files
• fix windows compatibility

1. Quite memory intensive for large volumes

Please contact me for any corrections or improvements

Benjamin Irving (20141124)