patchlib

A library for working with N-D patches, also including several 2D and 3D examples to illustrate the library applicability.

See functions for a (non-exhaustive) list of functions.
See examples for a list of examples to get you started.
See papers section below for a list of academic papers in which we used this library

Installation

Do a git pull or download patchlib as a zip. Unzip the files, and add the folder to your MATLAB path:
>> addpath(genpath('PATH_TO_PATCHLIB'));

Then run setup script:
>> verifypatchlib.m;

Add each of the following toolboxes to your MATLAB path:

The following toolbox is required by all of the code:

The MRF-related methods (e.g. for spatial regularization):

If you find this library useful, please cite one of the following papers for which the library was initially built (download bib):

Medical Image Imputation from Image Collections
A.V. Dalca, K.L. Bouman, W.T. Freeman, M.R. Sabuncu, N.S. Rost, P. Golland
IEEE TMI: Transactions on Medical Imaging 38.2 (2019): 504-514. eprint arXiv:1808.05732
Population Based Image Imputation
A.V. Dalca, K.L. Bouman, W.T. Freeman, M.R. Sabuncu, N.S. Rost, P. Golland
In Proc. IPMI: International Conference on Information Processing and Medical Imaging. LNCS 10265, pp 1-13. 2017.
Patch-Based Discrete Registration of Clinical Brain Images
A.V. Dalca, A. Bobu, N.S. Rost, P. Golland
In Proc. MICCAI-PATCHMI Patch-based Techniques in Medical Imaging, LNCS 9993, pp 60-67, 2016.

Adrian Dalca (web | email)
Katie Bouman (web | email)

Contact Please let us know of any questions/suggestions by opening an issue or emailing us at {adalca,klbouman}@csail.mit.edu