Difference between revisions of "Projects:CardiacAblation"

From NAMIC Wiki
Jump to: navigation, search
Line 20: Line 20:
  
 
[[File:Mdepa_MRA_seg_2D_comparison.png|800px|thumb|center|Figure 2: Example segmentations of four different subjects: (a) expert manual segmentation (MS), (b) weighted voting label fusion (WV), (c) majority voting label fusion (MV), (d) parametric atlas thresholding (AT) and (e) EM-segmentation using the parametric atlas as a spatial prior (EM).]]
 
[[File:Mdepa_MRA_seg_2D_comparison.png|800px|thumb|center|Figure 2: Example segmentations of four different subjects: (a) expert manual segmentation (MS), (b) weighted voting label fusion (WV), (c) majority voting label fusion (MV), (d) parametric atlas thresholding (AT) and (e) EM-segmentation using the parametric atlas as a spatial prior (EM).]]
 +
 +
Figure 3 reports the segmentation accuracy for each method, as measured by the volume overlap Dice scores. We also report the differences in segmentation accuracy between our method and the benchmark algorithms. To compute the difference between two methods, we subtract the Dice score of the second method from the score of the first for each subject. Our approach clearly outperforms other algorithms (WV vs. MV: p < 10−9, WV vs. AT: p < 0.002, WV vs. EM: p < 0.003; single-sided paired t-test). To focus the evaluation on the critical part of the structure, we manually isolate the pulmonary veins in each of the manual and automatic segmentations, and compare the Dice scores for these limited label maps. Again, we observe consistent improvements offered by our approach (WV vs. MV: p < 10−7, WV vs. AT: p < 10−7, WV vs. EM: p < 0.03; single-sided paired t-test). Since atlas-based EM-segmentation is an intensity based method, it performs relatively well in segmenting pulmonary veins, but suffers from numerous false positives in other areas, which lower its overall Dice scores.
 +
 +
[[File:Mdepa_MRA_seg_Dices.png|800px|thumb|center|Figure 3: Dice scores of results for weighted voting label fusion (WV), majority voting la- bel fusion (MV), parametric atlas thresholding (AT) and atlas-based EM-segmentation (EM). For each box plot, the central red line indicates the median, the boxes extend to the 25th and 75th percentiles, and the whiskers extend to the most extreme values not considered outliers, which are plotted as red crosses. Stars indicate that the weighted label fusion method achieves significantly more accurate segmentation than the baseline method (single-sided paired t-test, ∗: p < 0.05, ∗∗: p < 0.01).]]
  
 
= Cardiac ablation scar visualization =
 
= Cardiac ablation scar visualization =

Revision as of 22:34, 30 March 2011

Home < Projects:CardiacAblation
Back to NA-MIC Collaborations, MIT Algorithms,

Left atrium segmentation

The high anatomical variability of the heart’s left atrium makes its segmentation a particularly difficult problem. Specifically, the shape of the left atrium cavity, as well as the number and locations of the pulmonary veins connecting to it, vary substantially across subjects. We propose and demonstrate a robust atlas-based method for automatic segmentation of the left atrium in contrast-enhanced magnetic resonance angiography (MRA) images.

Description

We perform the segmentation via a label fusion algorithm [1] that uses a training set of MRA images of different patients with corresponding manual segmentations. We first align the training images to the test subject image to be segmented and apply the resulting deformations to the corresponding manual segmentation label maps to yield a set of left atrium segmentations in the coordinate space of the test subject. These form a non-parametric subject-specific statistical atlas. We then use a weighted voting algorithm to assign every voxel to the left atrium or to the background. The weighted label fusion scheme assigns higher weights to voxels in training segmentations that are located deeper within the structure of interest and that have similar intensities in training and test images. We also handle varying intensity distributions between images by incorporating iterative intensity equalization in a variant of the demons registration algorithm [2] used for the registration of the training images to the novel test image.

Results

We show in Figure 1 below a qualitative comparison between manual left atrium segmentations and automatic segmentations produced by our approach.

Figure 1: Qualitative evaluation of left atrium segmentations in three different subjects. First row shows expert manual segmentations. The corresponding automatic segmentations produced by our method are in the second row.

We compare our method of weighed voting (WV) label fusion to three alternative automatic atlas-based approaches: majority voting (MV) label fusion, parametric atlas thresholding (AT) and atlas-based EM-segmentation (EM). The majority voting label fusion is similar to weighted voting, except it assigns each voxel to the label that occurs most frequently in the registered training set at that voxel. We also construct a parametric atlas that summarizes all 16 subjects in a single template image and a probabilistic label map by performing groupwise registration to an average space. After registering this new atlas to the test subject, we segment the left atrium using two different approaches. In atlas thresholding, we simply threshold the warped probabilistic label map at 0.5 to obtain the segmentation. This baseline method is analogous to majority voting in the parametric atlas setting. We also use the parametric atlas as a spatial prior in a traditional model-based EM-segmentation. Note that this construction favors the baseline algorithms as it includes the test image in the registration of all subjects into the common coordinate frame.

In Figure 2 below, we show example segmentations comparing the automatic segmentations produced by these methods and expert manual segmentations.

Figure 2: Example segmentations of four different subjects: (a) expert manual segmentation (MS), (b) weighted voting label fusion (WV), (c) majority voting label fusion (MV), (d) parametric atlas thresholding (AT) and (e) EM-segmentation using the parametric atlas as a spatial prior (EM).

Figure 3 reports the segmentation accuracy for each method, as measured by the volume overlap Dice scores. We also report the differences in segmentation accuracy between our method and the benchmark algorithms. To compute the difference between two methods, we subtract the Dice score of the second method from the score of the first for each subject. Our approach clearly outperforms other algorithms (WV vs. MV: p < 10−9, WV vs. AT: p < 0.002, WV vs. EM: p < 0.003; single-sided paired t-test). To focus the evaluation on the critical part of the structure, we manually isolate the pulmonary veins in each of the manual and automatic segmentations, and compare the Dice scores for these limited label maps. Again, we observe consistent improvements offered by our approach (WV vs. MV: p < 10−7, WV vs. AT: p < 10−7, WV vs. EM: p < 0.03; single-sided paired t-test). Since atlas-based EM-segmentation is an intensity based method, it performs relatively well in segmenting pulmonary veins, but suffers from numerous false positives in other areas, which lower its overall Dice scores.

Figure 3: Dice scores of results for weighted voting label fusion (WV), majority voting la- bel fusion (MV), parametric atlas thresholding (AT) and atlas-based EM-segmentation (EM). For each box plot, the central red line indicates the median, the boxes extend to the 25th and 75th percentiles, and the whiskers extend to the most extreme values not considered outliers, which are plotted as red crosses. Stars indicate that the weighted label fusion method achieves significantly more accurate segmentation than the baseline method (single-sided paired t-test, ∗: p < 0.05, ∗∗: p < 0.01).

Cardiac ablation scar visualization

Atrial fibrillation is one of the most common heart conditions and can have very serious consequences such as stroke and heart failure. A technique called catheter radio-frequency (RF) ablation has recently emerged as a treatment. It involves burning the cardiac tissue that is responsible for the fibrillation. Even though this technique has been shown to work fairly well on atrial fibrillation patients, repeat procedures are often needed to fully correct the condition because surgeons lack the necessary tools to quickly evaluate the success of the procedure.

We propose a method to automatically segment the scar created by RF ablation in delayed enhancement MR images acquired after the procedure. This will provide surgeons with a visualization showing the size, shape and location of the scar, which is information central to evaluating the outcome of the procedure.

Description

We work with two types of images for each patient: MR angiography (MRA) images where the blood pool has a higher intensity than surrounding tissue and post-procedure delayed enhancement MR images (DE-MRI) where a contrast agent has been injected into the patient to enhance the ablation scar. Our approach is to first segment the left atrium in the MRA images using the label fusion algorithm described in [1]. We then transfer this segmentation to the DE-MRI image of the same patient by registering the two images.

Since the ablation scar we are trying to segment is known to be located on the left atrium myocardium, we use this spatial prior information to reduce the search space for the ablation scar to only a small vicinity of the left atrium surface. This avoids many false positives caused by the noise in the DE-MRI images. We will be exploring different segmentation methods in this ongoing work.

Results

Here we present results we have obtained for one subject using our methods. In the following images, we show the left atrium segmentation in the MRA image as an outline in one slice as well as a 3D model.

Mdepa MRA seg.png Mdepa MRA seg 3D.png


We then align the MRA and DE-MRI images of the same patient, which allows us to transfer the left atrium segmentation using the resulting deformation field. This is shown in the following figures.

Mdepa MRA MDE registration.png Mdepa MDE la segmentation.png


Finally, we show some preliminary results of our cardiac ablation scar segmentation obtained using this spatial prior knowledge and intensity thresholding. The figure on the right also shows an expert manual segmentation of the scar alongside our result.

Mdepa MDE scar segmentation.png Mdepa MDE scar seg 3D.png

Literature

[1] Nonparametric Mixture Models for Supervised Image Parcellation, M.R. Sabuncu, B.T.T. Yeo, K. Van Leemput, B. Fischl, and P. Golland. PMMIA Workshop at MICCAI 2009. [2] Diffeomorphic demons: Efficient non-parametric image registration. Vercauteren, T., Pennec, X., Perchant, A., Ayache, N. NeuroImage 45(1), S61–S72 (2009)

Key Investigators

  • BWH: Ehud Schmidt and Ron Kikinis

Publications

NA-MIC Publications Database on Segmentation and Visualization for Cardiac Ablation Procedures