Learning-based segmentation framework for tissue images containing gene expression data

A chicken embryo cardiac outflow tract atlas for registering changes due to abnormal blood flow

Subdivision-based image registration has previously been applied to co-localize digital information extracted from rigid structures in biological specimens, such as the brain. Here, we describe and demonstrate the creation and application of a two-dimensional subdivision-based atlas representing a dynamic structure: the outflow tract of the developing chicken heart. The atlas is designed to segment three different anatomical layers of the outflow tract, and is demonstrated on the characterization of collagen XIV in both control and induced abnormal flow specimens. Abnormal blood flow in the embryonic developing heart can lead to congenital heart disease. Comparing local cellular and sub-cellular changes that are caused by abnormal flow can assist in understanding the molecular pathways involved in maladaptations of the heart and congenital defects. This study demonstrates the approach and potential for more extensive applications of the subdivision-based atlas for the embryonic chicken heart.

PDM-ENLOR for segmentation of mouse brain gene expression images

Statistical shape models, such as Active Shape Models (ASMs), suffer from their inability to represent a large range of variations of a complex shape and to account for the large errors in detection of (point) landmarks. We propose a method, PDM-ENLOR (Point Distribution Model-based ENsemble of LOcal Regressors), that overcomes these limitations by locating each landmark individually using an ensemble of local regression models and appearance cues from selected landmarks. We first detect a set of reference landmarks which were selected based on their saliency during training. For each landmark, an ensemble of regressors is built. From the locations of the detected reference landmarks, each regressor infers a candidate location for that landmark using local geometric constraints, encoded by a point distribution model (PDM). The final location of that point is determined as a weighted linear combination, whose coefficients are learned from the training data, of candidates proposed by its ensemble's component regressors. We use multiple subsets of reference landmarks as explanatory variables for the component regressors to provide varying degrees of locality for the models in each ensemble. This helps our ensemble model to capture a larger range of shape variations as compared to a single PDM. We demonstrate the advantages of our method on the challenging problem of segmenting gene expression images of mouse brain. The overall mean and standard deviation of the Dice coefficient overlap over all 14 anatomical regions and all 100 test images were (88.1 ± 9.5)%.

Automated, foot-bone registration using subdivision-embedded atlases for spatial mapping of bone mineral density

We present an atlas-based registration method for bones segmented from quantitative computed tomography (QCT) scans, with the goal of mapping their interior bone mineral densities (BMDs) volumetrically. We introduce a new type of deformable atlas, called subdivision-embedded atlas, which consists of a control grid represented as a tetrahedral subdivision mesh and a template bone surface embedded within the grid. Compared to a typical lattice-based deformation grid, the subdivision control grid possesses a relatively small degree of freedom tailored to the shape of the bone, which allows efficient fitting onto subjects. Compared with previous subdivision atlases, the novelty of our atlas lies in the addition of the embedded template surface, which further increases the accuracy of the fitting. Using this new atlas representation, we developed an efficient and fully automated pipeline for registering atlases of 12 tarsal and metatarsal bones to a segmented QCT scan of a human foot. Our evaluation shows that the mapping of BMD enabled by the registration is consistent for bones in repeated scans, and the regional BMD automatically computed from the mapping is not significantly different from expert annotations. The results suggest that our improved subdivision-based registration method is a reliable, efficient way to replace manual labor for measuring regional BMD in foot bones in QCT scans.

Segmentation of zebrafish embryonic images using a geometric atlas deformation

Transgenic zebrafish expressing fluorescent proteins in specific tissues or organs are promising models for studies of normal developmental processes, or perturbations of these. However, for widespread use, reliable quantification of the observed effects is necessary. Therefore, accurate and automatic analysis of images obtained by fluorescent microscopy and depicting zebrafish embryos becomes crucial. In this paper, a segmentation approach for such images is proposed. The segmentation is achieved by fitting a species-specific 2D atlas to the zebrafish data depicted in the images. Experiments performed in a set of 50 images have provided promising results.

Similarity-based appearance-prior for fitting a subdivision mesh in gene expression images

Automated segmentation of multi-part anatomical objects in images is a challenging task. In this paper, we propose a similarity-based appearance-prior to fit a compartmental geometric atlas of the mouse brain in gene expression images. A subdivision mesh which is used to model the geometry is deformed using a Markov random field (MRF) framework. The proposed appearance-prior is computed as a function of the similarity between local patches at corresponding atlas locations from two images. In addition, we introduce a similarity-saliency score to select the mesh points that are relevant for the computation of the proposed prior. Our method significantly improves the accuracy of the atlas fitting, especially in the regions that are influenced by the selected similarity-salient points, and outperforms the previous subdivision mesh fitting methods for gene expression images.

Markov Random Field-based Fitting of a Subdivision-based Geometric Atlas

An accurate labeling of a multi-part, complex anatomical structure (e.g., brain) is required in order to compare data across images for spatial analysis. It can be achieved by fitting an object-specific geometric atlas that is constructed using a partitioned, high-resolution deformable mesh and tagging each of its polygons with a region label. Subdivision meshes have been used to construct such an atlas because they can provide a compact representation of a partitioned, multi-resolution, object-specific mesh structure using only a few control points. However, automated fitting of a subdivision mesh-based geometric atlas to an anatomical structure in an image is a difficult problem and has not been sufficiently addressed. In this paper, we propose a novel Markov Random Field-based method for fitting a planar, multi-part subdivision mesh to anatomical data. The optimal fitting of the atlas is obtained by determining the optimal locations of the control points. We also tackle the problem of landmark matching in tandem with atlas fitting by constructing a single graphical model to impose pose-invariant, landmark-based geometric constraints on atlas deformation. The atlas deformation is also governed by additional constraints imposed by the mesh's geometric properties and the object boundary. We demonstrate the potential of the proposed method on the difficult problem of segmenting a mouse brain and its interior regions in gene expression images which exhibit large intensity and shape variability. We obtain promising results when compared with manual annotations and prior methods.

Landmark/Image-based Deformable Registration of Gene Expression Data

Analysis of gene expression patterns in brain images obtained from high-throughput in situ hybridization requires accurate and consistent annotations of anatomical regions/subregions. Such annotations are obtained by mapping an anatomical atlas onto the gene expression images through intensity- and/or landmark-based registration methods or deformable model-based segmentation methods. Due to the complex appearance of the gene expression images, these approaches require a pre-processing step to determine landmark correspondences in order to incorporate landmark-based geometric constraints. In this paper, we propose a novel method for landmark-constrained, intensity-based registration without determining landmark correspondences a priori. The proposed method performs dense image registration and identifies the landmark correspondences, simultaneously, using a single higher-order Markov Random Field model. In addition, a machine learning technique is used to improve the discriminating properties of local descriptors for landmark matching by projecting them in a Hamming space of lower dimension. We qualitatively show that our method achieves promising results and also compares well, quantitatively, with the expert's annotations, outperforming previous methods.

Semi-automated atlas-based analysis of brain histological sections

Quantifying the location and/or number of features in a histological section of the brain currently requires one to first, manually register a corresponding section from a tissue atlas onto the experimental section and second, count the features. No automated method exists for the first process (registering), and most automated methods for the second process (feature counting) operate reliably only in a high signal-to-noise regime. To reduce experimenter bias and inconsistencies and increase the speed of these analyses, we developed Atlas Fitter, a semi-automated, open-source MatLab-based software package that assists in rapidly registering atlas panels onto histological sections. We also developed CellCounter, a novel fully automated cell counting algorithm that is designed to operate on images with non-uniform background intensities and low signal-to-noise ratios.

A semiautomated approach for artefact removal in serial tissue cryosections

Thinly sliced serial tissue sections of an organ can be imaged using optical microscopy at a resolution detailing individual cells. When the tissue sections are first subjected to in situ hybridization or immunohistochemistry, these data sets can be analysed for changes in gene expression and gene products. Such spatial information is important for understanding the functional effects of experimental or environmental challenges to the organism. However, a critical step in analysing these data sets is mitigating artefacts that result from the preparation of the tissue sections. In this paper, we describe an automated method with manual validation tools that together enable detecting and addressing artefacts including dust particles and air bubbles.

Fluid-Structure Interactions of the Mitral Valve and Left Heart: Comprehensive Strategies, Past, Present and Future

The remodeling that occurs after a posterolateral myocardial infarction can alter mitral valve function by creating conformational abnormalities in the mitral annulus and in the posteromedial papillary muscle, leading to mitral regurgitation (MR). It is generally assumed that this remodeling is caused by a volume load and is mediated by an increase in diastolic wall stress. Thus, mitral regurgitation can be both the cause and effect of an abnormal cardiac stress environment. Computational modeling of ischemic MR and its surgical correction is attractive because it enables an examination of whether a given intervention addresses the correction of regurgitation (fluid-flow) at the cost of abnormal tissue stress. This is significant because the negative effects of an increased wall stress due to the intervention will only be evident over time. However, a meaningful fluid-structure interaction model of the left heart is not trivial; it requires a careful characterization of the in-vivo cardiac geometry, tissue parameterization though inverse analysis, a robust coupled solver that handles collapsing Lagrangian interfaces, automatic grid-generation algorithms that are capable of accurately discretizing the cardiac geometry, innovations in image analysis, competent and efficient constitutive models and an understanding of the spatial organization of tissue microstructure. In this manuscript, we profile our work toward a comprehensive fluid-structure interaction model of the left heart by reviewing our early work, presenting our current work and laying out our future work in four broad categories: data collection, geometry, fluid-structure interaction and validation.

Automated pipeline for atlas-based annotation of gene expression patterns: application to postnatal day 7 mouse brain

Massive amounts of image data have been collected and continue to be generated for representing cellular gene expression throughout the mouse brain. Critical to exploiting this key effort of the post-genomic era is the ability to place these data into a common spatial reference that enables rapid interactive queries, analysis, data sharing, and visualization. In this paper, we present a set of automated protocols for generating and annotating gene expression patterns suitable for the establishment of a database. The steps include imaging tissue slices, detecting cellular gene expression levels, spatial registration with an atlas, and textual annotation. Using high-throughput in situ hybridization to generate serial sets of tissues displaying gene expression, this process was applied toward the establishment of a database representing over 200 genes in the postnatal day 7 mouse brain. These data using this protocol are now well-suited for interactive comparisons, analysis, queries, and visualization.

Subdivision meshes for organizing spatial biomedical data

As biomedical images and volumes are being collected at an increasing speed, there is a growing demand for efficient means to organize spatial information for comparative analysis. In many scenarios, such as determining gene expression patterns by in situ hybridization, the images are collected from multiple subjects over a common anatomical region, such as the brain. A fundamental challenge in comparing spatial data from different images is how to account for the shape variations among subjects, which make direct image-to-image comparisons meaningless. In this paper, we describe subdivision meshes as a geometric means to efficiently organize 2D images and 3D volumes collected from different subjects for comparison. The key advantages of a subdivision mesh for this purpose are its light-weight geometric structure and its explicit modeling of anatomical boundaries, which enable efficient and accurate registration. The multi-resolution structure of a subdivision mesh also allows development of fast comparison algorithms among registered images and volumes.