Source Codes

Supervertex Clustering

S. Arslan, D. Rueckert, "Multi-level parcellation of the cerebral cortex using resting-state fMRI," Proceedings of MICCAI: International Conference on Medical Image Computing and Computer Assisted Intervention, vol. 9351 of LNCS. Springer, pp. 47-55, 2015.

Matlab implementation of the supervertex clustering algorithm that constitutes the first layer of our three-layer aproach presented in the given paper. This version has been tested on the Human Connectome Project (HCP) datasets. The code has a deep dependency with the HCP data structures. Simply run RUN_supervertex_clustering after setting the Path and updating directories the datasets will be read from.

Download Codes Github

Joint spectral decomposition

S. Arslan, S. Parisot, and D. Rueckert, "Joint spectral decomposition for the parcellation of the cerebral cortex using resting-state fMRI," Information Processing in Medical Imaging Lecture Notes in Computer Science, vol. 9123, pp. 85-97, 2015.

Matlab implementation of the joint spectral decomposition algorithm that constitutes a framework for cortical parcellation of the human brain, ideally for group-wise analysis, as presented in the given paper. This version has been tested on the Human Connectome Project (HCP) datasets. Please read the provided README before atempting to run the program and run the scripts in the following order:

1- Multi_layer_graph_generation
2- Joint_spectral_decomposition
3- Run_clustering_after_decomposition

Download Codes Github

White Blood Cell and Blast Segmentation

S. Arslan, E. Ozyurek, and C. Gunduz-Demir, "A color and shape based algorithm for segmentation of white blood cells in peripheral blood and bone marrow images," Cytometry Part A, vol. 85, no. 6, pp. 480-490, 2014.

Matlab implementation of the white blood cell segmentation algorithm based on color and shape features. Please read the provided README before running the program. Simply run test.m and follow instructions throughout the comments.

Download Codes Github

ARGraphs Cell Nucleus Segmentation

S. Arslan, T. Ersahin, R. Cetin-Atalay, and C. Gunduz-Demir, "Attributed relational graphs for cell nucleus segmentation in fluorescence microscopy images," IEEE Transactions on Medical Imaging, vol. 32, no. 6, pp. 1121-1131, 2013.

C implementation of the cell nucleus segmentation algorithm using attributed relation graphs. The program has two modes: cell nucleus localization (marker primitive definition) and region growing (flooding) boundary delineation. First, it should be run in the cell nucleus localization mode to roughly find cell nuclei and four types of primitives, which are then used in the second stage for segmentation of nuclei. The usage of the program and the parameters are briefly explained in Tutorial.

Tutorial Download Codes Github