This package contains a software implementation for joint label fusion and corrective learning, which were applied in MICCAI 2012 Grand Challenge on Multi-Atlas Labeling and finished in the first place. Joint label fusion is for combining candidate segmentations produced by registering and warping multiple atlases for a target image. Corrective learning can be applied to further reduce systematic errors produced by joint label fusion. In general, corrective learning can be applied to correct systematic errors produced by other segmentation methods as well.
module spider PICSL to find out what environment modules are available for this application.
- HPC_PICSL_DIR - installation directory
- HPC_PICSL_BIN - executable directory
If you publish research that uses PICSL you have to cite it as follows:
 H. Wang, J. W. Suh, S. Das, J. Pluta, C. Craige, P. Yushkevich, "Multi-atlas segmentation with joint label fusion," IEEE Trans. on Pattern Analysis and Machine Intelligence, 35(3), 611-623, 2013
 H. Wang, S. R. Das, J. W. Suh, M. Altinay, J. Pluta, C. Craige, B. B. Avants, and P. A. Yushkevich, "A Learning-Based Wrapper Method to Correct Systematic Errors in Automatic Image Segmentation: Consistently Improved Performance in Hippocampus, Cortex and Brain," Neuroimage, vol. 55, iss. 3, pp. 968-985, 2011.