Code developed throughout my PhD in order to automatically find the organs of a fetus in MR images:
- brain-detector [1,2]
- body-detector [3]
- commonlib contains code used in both projects, in particular fetal biometric measurements in
commonlib/fetal_anatomy.py
- external contains code that is not used in [1,2,3] but is relevant to automated detection in fetal MRI, such as the RIF features used in [4]
This code is based on python-irtk, a Python interface to IRTK, which can be installed through conda
:
conda install -c kevin-keraudren python-irtk
It uses OpenCV version 2 (note that SIFT features are not included by default in OpenCV 3 binaries).
cd body-detector && make
cd body-detector && ./demo.sh
Below is a screenshot of the detection results (detection_results/stack-1/prediction_2/final_seg.nii.gz
):
A demo focusing on the brain detection is available in the repository example-motion-correction.
[1] Keraudren, K., Kyriakopoulou, V., Rutherford, M., Hajnal, J.V., &
Rueckert, D.:
Localisation of the Brain in Fetal MRI Using Bundled SIFT
Features. MICCAI 2013.
PDF
video
poster
[2] Keraudren, K., Kuklisova-Murgasova, M., Kyriakopoulou, V., Malamateniou, C.,
Rutherford, M.A., Kainz, B., Hajnal, J.V., & Rueckert, D.:
Automated Fetal Brain Segmentation from 2D MRI Slices for Motion Correction.
NeuroImage, 2014.
PDF
demo
slides
[3] Keraudren, K., Kainz, B., Oktay, O., Kyriakopoulou, V., Rutherford,
M., Hajnal, J. V., & Rueckert, D.:
Automated Localization of Fetal Organs
in MRI Using Random Forests with Steerable Features. MICCAI 2015.
PDF
video
slides
[4] Kainz, B., Keraudren, K., Kyriakopoulou, V., Rutherford, M., Hajnal, J.,
& Rueckert, D.: "Fast Fully Automatic Brain Detection in Fetal MRI
Using Dense Rotation Invariant Image Descriptors". ISBI 2014.
PDF
video