Warped Atlas Research Articles

Patch spaces and fusion strategies in patch-based label fusion

In the field of multi-atlas segmentation, patch-based approaches have shown promising results in the segmentation of biomedical images. In the most common approach, registration is used to warp the atlases to the target space and then the warped atlas labelmaps are fused into a consensus segmentation based on local appearance information encoded in form of patches. The registration step establishes spatial correspondence, which is important to obtain anatomical priors. Patch-based label fusion in the target space has shown to produce very accurate segmentations although at the expense of registering all atlases to each target image. Moreover, appearance (i.e., patches) and label information used by label fusion is extracted from the warped atlases, which are subject to interpolation errors. In this work, we revisit and extend the patch-based label fusion framework, exploring the role of extracting this information from the native space of both atlases and target images, thus avoiding interpolation artifacts, but at the same time, we do it in a way that it does not sacrifice the anatomical priors derived by registration. We further propose a common formulation for two widely-used label fusion strategies, i.e., similarity-based and a particular type of learning-based label fusion. The proposed framework is evaluated on subcortical structure segmentation in adult brains and tissue segmentation in fetal brain MRI. Our results indicate that using atlas patches in their native space yields superior performance than warping the atlases to the target image. The learning-based approach tends to outperform the similarity-based approach, with the particularity that using patches in native space lessens the computational requirements of learning. As conclusion, the combination of learning-based label fusion and native atlas patches yields the best performance with reduced test times than conventional similarity-based approaches.

Warping an atlas derived from serial histology to 5 high-resolution MRIs

Previous work from our group demonstrated the use of multiple input atlases to a modified multi-atlas framework (MAGeT-Brain) to improve subject-based segmentation accuracy. Currently, segmentation of the striatum, globus pallidus and thalamus are generated from a single high-resolution and -contrast MRI atlas derived from annotated serial histological sections. Here, we warp this atlas to five high-resolution MRI templates to create five de novo atlases. The overall goal of this work is to use these newly warped atlases as input to MAGeT-Brain in an effort to consolidate and improve the workflow presented in previous manuscripts from our group, allowing for simultaneous multi-structure segmentation. The work presented details the methodology used for the creation of the atlases using a technique previously proposed, where atlas labels are modified to mimic the intensity and contrast profile of MRI to facilitate atlas-to-template nonlinear transformation estimation. Dice’s Kappa metric was used to demonstrate high quality registration and segmentation accuracy of the atlases. The final atlases are available at https://github.com/CobraLab/atlases/tree/master/5-atlas-subcortical.

Nonlocal atlas-guided multi-channel forest learning for human brain labeling.

It is important for many quantitative brain studies to label meaningful anatomical regions in MR brain images. However, due to high complexity of brain structures and ambiguous boundaries between different anatomical regions, the anatomical labeling of MR brain images is still quite a challenging task. In many existing label fusion methods, appearance information is widely used. However, since local anatomy in the human brain is often complex, the appearance information alone is limited in characterizing each image point, especially for identifying the same anatomical structure across different subjects. Recent progress in computer vision suggests that the context features can be very useful in identifying an object from a complex scene. In light of this, the authors propose a novel learning-based label fusion method by using both low-level appearance features (computed from the target image) and high-level context features (computed from warped atlases or tentative labeling maps of the target image). In particular, the authors employ a multi-channel random forest to learn the nonlinear relationship between these hybrid features and target labels (i.e., corresponding to certain anatomical structures). Specifically, at each of the iterations, the random forest will output tentative labeling maps of the target image, from which the authors compute spatial label context features and then use in combination with original appearance features of the target image to refine the labeling. Moreover, to accommodate the high inter-subject variations, the authors further extend their learning-based label fusion to a multi-atlas scenario, i.e., they train a random forest for each atlas and then obtain the final labeling result according to the consensus of results from all atlases. The authors have comprehensively evaluated their method on both public LONI_LBPA40 and IXI datasets. To quantitatively evaluate the labeling accuracy, the authors use the dice similarity coefficient to measure the overlap degree. Their method achieves average overlaps of 82.56% on 54 regions of interest (ROIs) and 79.78% on 80 ROIs, respectively, which significantly outperform the baseline method (random forests), with the average overlaps of 72.48% on 54 ROIs and 72.09% on 80 ROIs, respectively. The proposed methods have achieved the highest labeling accuracy, compared to several state-of-the-art methods in the literature.

Brain atlas deformation in the presence of small and large space-occupying tumors.

Brain atlases contain a wealth of information that could be used in radiation therapy or neurosurgical planning. Until now, however, when large space-occupying tumors and lesions drastically alter the shape of brain structures and substructures, atlas-based methods have been of limited use. In this work, we present a new technique that permits a brain atlas to be warped onto image volumes in which large lesions are present. First we show that a method previously used for atlas-based segmentation of normal brains can also be used for brains with small lesions. We then present an extension of this technique for brains with large lesions. This involves several steps: a global registration to bring the two volumes into approximate correspondence; a local registration to warp the atlas onto the patient volume; the seeding of the warped atlas with a tumor model derived from patient data; and the deformation of the seeded atlas. Global registration is performed using a mutual information criterion. The method we have used for atlas warping is derived from optical flow principles. Preliminary results obtained on real patient images are presented. These results indicate that the proposed method can be used to automatically segment structures of interest in brains with gross deformation. Potential areas of application for this method include automatic labeling of critical structures for radiation therapy and presurgical planning.

Brain Atlas Deformation in the Presence of Small and Large Space-Occupying Tumors

Brain atlases contain a wealth of information that could be used in radiation therapy or neurosurgical planning. Until now, however, when large space-occupying tumors and lesions drastically alter the shape of brain structures and substructures, atlas-based methods have been of limited use. In this work, we present a new technique that permits a brain atlas to be warped onto image volumes in which large lesions are present. First we show that a method previously used for atlas-based segmentation of normal brains can also be used for brains with small lesions. We then present an extension of this technique for brains with large lesions. This involves several steps: a global registration to bring the two volumes into approximate correspondence; a local registration to warp the atlas onto the patient volume; the seeding of the warped atlas with a tumor model derived from patient data; and the deformation of the seeded atlas. Global registration is performed using a mutual information criterion. The method we have used for atlas warping is derived from optical flow principles. Preliminary results obtained on real patient images are presented. These results indicate that the proposed method can be used to automatically segment structures of interest in brains with gross deformation. Potential areas of application for this method include automatic labeling of critical structures for radiation therapy and presurgical planning.