Leandro A. Loss

Invariant Delineation of Nuclear Architecture in Glioblastoma Multiforme for Clinical and Molecular Association

Automated analysis of whole mount tissue sections can provide insights into tumor subtypes and the underlying molecular basis of neoplasm. However, since tumor sections are collected from different laboratories, inherent technical and biological variations impede analysis for very large datasets such as The Cancer Genome Atlas (TCGA). Our objective is to characterize tumor histopathology, through the delineation of the nuclear regions, from hematoxylin and eosin (H&E) stained tissue sections. Such a representation can then be mined for intrinsic subtypes across a large dataset for prediction and molecular association. Furthermore, nuclear segmentation is formulated within a multi-reference graph framework with geodesic constraints, which enables computation of multidimensional representations, on a cell-by-cell basis, for functional enrichment and bioinformatics analysis. Here, we present a novel method, multi-reference graph cut (MRGC), for nuclear segmentation that overcomes technical variations associated with sample preparation by incorporating prior knowledge from manually annotated reference images and local image features. The proposed approach has been validated on manually annotated samples and then applied to a dataset of 377 Glioblastoma Multiforme (GBM) whole slide images from 146 patients. For the GBM cohort, multidimensional representation of the nuclear features and their organization have identified 1) statistically significant subtypes based on several morphometric indexes, 2) whether each subtype can be predictive or not, and 3) that the molecular correlates of predictive subtypes are consistent with the literature. Data and intermediaries for a number of tumor types (GBM, low grade glial, and kidney renal clear carcinoma) are available at: http://tcga.lbl.gov for correlation with TCGA molecular data. The website also provides an interface for panning and zooming of whole mount tissue sections with/without overlaid segmentation results for quality control.

Iterative Tensor Voting for Perceptual Grouping of Ill-Defined Curvilinear Structures

In this paper, a novel approach is proposed for perceptual grouping and localization of ill-defined curvilinear structures. Our approach builds upon the tensor voting and the iterative voting frameworks. Its efficacy lies on iterative refinements of curvilinear structures by gradually shifting from an exploratory to an exploitative mode. Such a mode shifting is achieved by reducing the aperture of the tensor voting fields, which is shown to improve curve grouping and inference by enhancing the concentration of the votes over promising, salient structures. The proposed technique is validated on delineating adherens junctions that are imaged through fluorescence microscopy. However, the method is also applicable for screening other organisms based on characteristics of their cell wall structures. Adherens junctions maintain tissue structural integrity and cell-cell interactions. Visually, they exhibit fibrous patterns that may be diffused, heterogeneous in fluorescence intensity, or punctate and frequently perceptual. Besides the application to real data, the proposed method is compared to prior methods on synthetic and annotated real data, showing high precision rates.

Feature Fusion Hierarchies for gender classification

We present a hierarchical feature fusion model for image classification that is constructed by an evolutionary learning algorithm. The model has the ability to combine local patches whose location, width and height are automatically determined during learning. The representational framework takes the form of a two-level hierarchy which combines feature fusion and decision fusion into a unified model. The structure of the hierarchy itself is constructed automatically during learning to produce optimal local feature combinations. A comparative evaluation of different classifiers is provided on a challenging gender classification image database. It demonstrates the effectiveness of these Feature Fusion Hierarchies (FFH).

Comparison of sparse coding and kernel methods for histopathological classification of gliobastoma multiforme

This paper compares the performance of redundant representation and sparse coding against classical kernel methods for classifying histological sections. Sparse coding has been proven an effective technique for restoration, and has recently been extended to classification. The main issue with histology sections classification is inherent heterogeneity, which is a result of technical and biological variations. Technical variations originate from sample preparation, fixation, and staining from multiple laboratories, whereas biological variations originate from tissue content. Image patches are represented with invariant features at local and global scales, where local refers to responses measured with Laplacian of Gaussians, and global refers to measurements in the color space. Experiments are designed to learn dictionaries through sparse coding, and to train classifiers through kernel methods using normal, necrotic, apoptotic, and tumor regions with characteristics of high cellularity. Two different kernel methods, that of a support vector machine (SVM) and a kernel discriminant analysis (KDA), were used for comparative analysis. Preliminary investigation on the histological samples of Glioblastoma multiforme (GBM) indicates the kernel methods perform as good, if not better, than sparse coding with redundant representation.

Batch-invariant nuclear segmentation in whole mount histology sections

The Cancer Genome Atlas (TCGA) provides a rich repository of whole mount tumor sections that are collected from different laboratories. However, there are a significant amount of technical and biological variations that impede analysis. We have developed a novel approach for nuclear segmentation in histology sections, which addresses the problem of technical and biological variations by incorporating information from manually annotated reference patches with the local color space of the original image. Subsequently, the problem is formulated within a multi-reference graph cut with geodesic constraints. This approach has been validated on manually curated samples and then applied to a dataset of 440 whole mount tissue sections, originating from different laboratories, which are typically 40k-by-40k pixels or larger. Segmentation results, through a zoomable interface, and extracted morphometric data are available at: http://tcga.lbl.gov.

Perceptual grouping based on iterative multi-scale tensor voting

We propose a new approach for perceptual grouping of oriented segments in highly cluttered images based on tensor voting. Segments are represented as second-order tensors and communicate with each other through a voting scheme that incorporates the Gestalt principles of visual perception. An iterative scheme has been devised which removes noise segments in a conservative way using multi-scale analysis and re-voting. We have tested our approach on data sets composed of real objects in real backgrounds. Our experimental results indicate that our method can segment successfully objects in images with up to twenty times more noise segments than object ones.

An Automatic Framework for Figure-Ground Segmentation in Cluttered Backgrounds

This paper proposes an automatic framework for figure-ground segmentation of edged images in the presence of cluttered background. Our work employs perceptual grouping concepts to characterize image segments by means of their saliency, which is computed via tensor voting. The main innovation of our work is a case-based thresholding scheme which iteratively eliminates edge segments with low-saliency in multiple scales, preserving those that are more likely to belong to foreground. The key idea is classifying saliency histograms in several cases by considering the relative position of the modes of the figure/ground distributions and applying specific actions in each case. We have performed extensive experiments in order to evaluate our framework both quantitatively and qualitatively, including real images from the Berkeley dataset.

Tunable tensor voting improves grouping of membrane-bound macromolecules

Membrane-bound macromolecules are responsible for structural support and mediation of cell-cell adhesion in tissues. Quantitative analysis of these macromolecules provides morphological indices for damage or loss of tissue, for example as a result of exogenous stimuli. From an optical point of view, a membrane signal may have nonuniform intensity around the cell boundary, be punctate or diffused, and may even be perceptual at certain locations along the boundary. In this paper, a method for the detection and grouping of punctate, diffuse curvilinear signals is proposed. Our work builds upon the tensor voting and the iterative voting frameworks to propose an efficient method to detect and refine perceptually interesting curvilinear structures in images. The novelty of our method lies on the idea of iteratively tuning the tensor voting fields, which allows the concentration of the votes only over areas of interest. We validate the utility of our system with synthetic and annotated real data. The effectiveness of the tunable tensor voting is demonstrated on complex phenotypic signals that are representative of membrane-bound macromolecular structures.

Automatic segmentation and quantification of filamentous structures in electron tomography

Electron tomography is a promising technology for imaging ultrastructures at nanoscale resolutions. However, image and quantitative analyses are often hindered by high levels of noise, staining heterogeneity, and material damage either as a result of the electron beam or sample preparation. We have developed and built a framework that allows for automatic segmentation and quantification of filamentous objects in 3D electron tomography. Our approach consists of three steps: (i) local enhancement of filaments by Hessian filtering; (ii) detection and completion (e.g., gap filling) of filamentous structures through tensor voting; and (iii) delineation of the filamentous networks. Our approach allows for quantification of filamentous networks in terms of their compositional and morphological features. We first validate our approach using a set of specifically designed synthetic data. We then apply our segmentation framework to tomograms of plant cell walls that have undergone different chemical treatments for polysaccharide extraction. The subsequent compositional and morphological analyses of the plant cell walls reveal their organizational characteristics and the effects of the different chemical protocols on specific polysaccharides.

Tunable tensor voting for regularizing punctate patterns of membrane-bound protein signals

Membrane-bound protein, expressed in the basal-lateral region, is heterogeneous and an important endpoint for understanding biological processes. At the optical resolution, membrane-bound protein can be visualized as being diffused (e.g., E-cadherin), punctate (e.g., connexin), or simultaneously diffused and punctate as a result of sample preparation or conditioning. Furthermore, there is a signi..cant amount of heterogeneity as a result of technical and biological variations. This paper aims at enhancing membrane-bound proteins that are expressed between epithelial cells so that quantitative analysis can be enabled on a cell-by-cell basis. We propose a method to detect and enhance membrane-bound protein signal from noisy images. More precisely, we build upon the tensor voting framework in order to produce an ef..cient method to detect and re..ne perceptually interesting linear structures in images. The novelty of the proposed method is in its iterative tuning of the tensor voting fields, which allows the concentration of the votes only over areas of interest. The method is shown to produce high quality enhancements of membrane-bound protein signals with combined punctate and diffused characteristics. Experimental results demonstrate the benefits of using tunable tensor voting for enhancing and differentiating cell-cell adhesion mediated by integral cell membrane protein.