|
|
Topology Correction of Segmented Medical Images
|
Overview
|
|
|
The
topological properties of objects are often very simple, regardless of
their geometric complexity. Human anatomy follows this rule, even for
extremely convoluted shapes like the cerebral cortex or the
vasculature. We present here a new method for correcting the topology
of objects segmented from medical images. Whereas previous techniques
alter a surface obtained from a binary segmentation of the object, our
technique can be applied directly to the image intensities of a
probabilistic or fuzzy segmentation, thereby propagating the topology
for all isosurfaces of the object.
|
|
|
Introduction
|
|
The topological properties of 2D
and 3D objects are often very simple, regardless of the complexity of
the geometric object. The cortex of the human brain is a striking
example; despite its intricate folds, it is considered to have the
topology of a sphere, without any hole or handle-like junction. Most
organs and sub-structures found in the human body also have a simple
topology.
Ideally, segmentation algorithms
that extract objects from images should respect the object topology. A
major problem is that topology is a global property of the
object, whereas most extraction techniques operate locally on the
pixels of an image. Two approaches to addressing this issue are to
correct the extracted object to obtain the desired topology, or to
start from a template object, with the correct topology, and deform it
with topology-preserving deformations.
Algorithms for topology
correction typically operate on a binary volume extracted from the
classification of the image data, using graph-based analysis, distance
function processing, or surface mesh flattening. In places where
changes are needed to enforce the spherical topology, these methods
decide how to cut a handle or fill a hole based solely on the geometry
of the original surface, whereas a membership or probability function
is often available and can dictate different choices (see below).
We proposed a new topology
correction algorithm that can act directly on the membership or
probability function instead of the binary segmentation. The method
propagates exact topological constraints on scalar 2D and 3D functions,
even in the presence of noise in the function. The topology of the
entire image is corrected with a single computation of a modified fast
marching method. All isosurfaces extracted from the image data will
have the same topology, and we can even enforce non-spherical
topologies, given an appropriate initialization.
|
| Application |
|
We applied the algorithm to
correcting the topology of the white matter (WM)/ gray matter (GM)
boudnary in MR brain images. The brains were first stripped of
extra-cranial tissues, then segmented into gray matter, white matter
and cerebro-spinal fluid (CSF). Finally, the white matter memberships
were further edited to fill the sub-cortical area. We performed the
topology correction on the edited white matter memberships. Changes in
the membership values are minimal, and hardly noticeable. The extracted
isocontours all have spherical topology, and are of the same level of
accuracy as the 0.5 isocontour processed with a state-of-the-art
graph-based topology correction method (GTCA, Han et al.).
|
| Software |
The method has been released as a Mipav plug-in in the Download section of this
site.
The software is multi-platform, should not require more than a few
hundred MB of memory, and usually runs under a minute (both depending
on the processed image size).
|
| Publications |
- P.-L.
Bazin, D.L. Pham, "Topology Correction
of
Segmented Medical Images using a Fast Marching Algorithm," Computer
Methods and Programs in Biomedicine, 88:2,
182-190, 2007.
- P.-L. Bazin and D.L. Pham, ``Topology correction
using fast marching methods and its application to brain segmentation,''
Proceedings of MICCAI 2005.
|
© Copyright 2005-2009 | All Rights Reserved |
Johns Hopkins University & Laboratory of Medical Image Computing
|
