View source for Projects:LeftAtriumSegmentation

Back to [[Algorithm:BU|Boston University Algorithms]]
__NOTOC__
= Automatic Segmentation of Left Atrium using Variational Region Growing=

= Description =
Automatic segmentation of the left atrium (LA) from MRI data is a challenging but major task in medical imaging
analysis. An important application is concerned with the treatment of left atrial fibrillation [1]. Atrial fibrillation is a cardiac
arrhythmia characterized by unsynchronized electrical activity in the atrial chambers of the heart. One of the treatments
for such arrhythmia is the catheter ablation, which targets specific parts of the LA for radio-frequency ablation using
an intracardiac catheter [2]. Application of radio-frequency energy to the cardiac tissue causes thermal injury, which in
turn results into scar tissue. Successful ablation can eliminate, or isolate, the problematic sources of electrical activity and
effectively cure atrial fibrillation. In order to perform such ablation, the extraction of the LA from the late gadolinium
enhancement MR (LGE-MR) images is required and is often performed manually, which is a very time-consuming task.
However, automatic LA segmentation is challenging due to the following factors: 1) the LA sized is relatively small as
compared to the left ventricle (LV) or lungs in cardiac MRI images; 2) boundaries are not clearly defined when the blood
pool goes into the pulmonary veins from the LA; 3) the shape variability of LA is large across subjects.

We propose an automatic approach for segmenting the left atrium from magnetic resonance imagery
(MRI). The segmentation problem is formulated as a problem in variational region growing. In particular, the method starts
locally by searching for a seed region of the left atrium from a given MR slice. A global constraint is imposed by applying a
shape prior to the left atrium represented by Zernike moments. The overall growing process is guided by the robust statistics of
intensities from the seed region along with the shape prior to capture the whole atrial region.

The proposed method consists of two key steps: (1) search for a seed region of the LA from an image slice in the axial
view. (2) explore the LA region using a variational region-growing process. A shape prior is employed to drive the
growing process towards atrium-like shapes.

= Results =
*[[File:Image-LASegWithMomentsPrior.png|800px]]
Region-growing process driven by robust statistics and Zernike moments shape prior.

*[[File:LASegRG2Atlas.png|800px]]
Comparison of the worst results obtained using the proposed method (first column) and the atlas-based method (second column) . From top to bottom:
the LA returned using the proposed method (red) and atlas-based method (green) in axial, coronal, and sagittal views, respectively.

= Key Investigators =
*Georgia Tech: Liangjia Zhu and Anthony Yezzi
*BWH: Yi Gao
*Boston University: Allen Tannenbaum

= Publications =
L. Zhu, Y. Gao, A. Yezzi, A. Tannenbaum. Automatic Left Atrial Segmentation from MRI images using Variational Region Growing with a Shape Prior, IEEE Transaction on Medical Imaging(TMI), in submission.

= References = 
1. C. J. McGann, E. G. Kholmovski, R. S. Oakes, J. E. Blauer, Segerson N. M. Daccarett, M., K. J. Airey, N. Akoum, E. N. Fish, T. J. Badger,
E. V. R. DiBella, D. Parker, R. S. MacLeod, and N. F. Marrouche. New magnetic resonance imaging based method to define extent of left atrial wall injury after the ablation of atrial fibrillation. Journal of the American College of Cardiology, 2008.

2. P. Jais, R. Weerasooriya, D.C. Shah, M. Hocini, L. Macle, K.J. Choi, C. Scavee, M. Ha ̈ssaguerre, and J. Clementy. Ablation therapy for atrial fibrillation (AF). Cardiovascular research, 54(2):337–346, 2002.