Walter Schubert

A neural classifier enabling high-throughput topological analysis of lymphocytes in tissue sections

A neural cell detection system (NCDS) for the automatic quantitation of fluorescent lymphocytes in tissue sections is presented in this paper. The system acquires visual knowledge from a set of training cell-image patches selected by a user. The trained system evaluates an image in 2 min calculating: the number, the positions, and the phenotypes of the fluorescent cells. For validation, the NCDS learning performance was tested by cross validation on digitized images of tissue sections obtained from inherently different types of tissue: diagnostic tissue sections across the human tonsil and across an inflammatory lymphocyte infiltrate of the human skeletal muscle. The NCDS detection results were compared with detection results from biomedical experts and were visually evaluated by our most experienced biomedical expert. Although the micrographs were noisy and the fluorescent cells varied in shape and size, the NCDS detected a minimum of 95% of the cells. In contrast, the cellular counts based on visual cell recognition of the experts were inconsistent and largely unreproducible for approximately 80% of the lymphocytes present in a visual field.

Human vs. machine: evaluation of fluorescence micrographs

To enable high-throughput screening of molecular phenotypes, multi-parameter fluorescence microscopy is applied. Object of our study is lymphocytes which invade human tissue. One important basis for our collaborative project is the development of methods for automatic and accurate evaluation of fluorescence micrographs. As a part of this, we focus on the question of how to measure the accuracy of microscope image interpretation, by human experts or a computer system. Following standard practice we use methods motivated by receiver operator characteristics to discuss the accuracies of human experts and of neural network-based algorithms. For images of good quality the algorithms achieve the accuracy of the medium-skilled experts. In images with increased noise, the classifiers are outperformed by some of the experts. Furthermore, the neural network-based cell detection is much faster than the human experts.

A Neural Network Architecture for Automatic Segmentation of Fluorescence Micrographs

Abstract A system for the automatic segmentation of fluorescence micrographs is presented. In the first step, positions of fluorescent cells are detected by a fast learning neural network, which acquires the visual knowledge from a set of training cell-image patches selected by the user. Guided by the detected cell positions the system extracts in the second step the contours of the cells. For contour extraction, a recurrent neural network model is used to approximate the cell shapes. Even though the micrographs are noisy and the fluorescent cells vary in shape and size, the system detects at minimum 95% of the cells.

Interlocking transcriptomics, proteomics and toponomics technologies for brain tissue analysis in murine hippocampus

We have correlated transcriptomics, proteomics and toponomics analyses of hippocampus tissue of inbred C57BL/6 mice to analyse the interrelationship of expressed genes and proteins at different levels of organization. We find that transcriptome and proteome levels of function as well as the topological organization of synaptic protein clusters, detected by toponomics at physiological sites of hippocampus CA3 region, are all largely conserved between different mice. While the number of different synaptic states, characterized by distinct synaptic protein clusters, is enormous (>155u2009000), these states together form synaptic networks defining distinct and mutually exclusive territories in the hippocampus tissue. The findings provide insight in the systems biology of gene expression on transcriptome, proteome and toponome levels of function in the same brain subregion. The approach will lay the ground for designing studies of neurodegeneration in mouse models and human brains.

Toponome imaging system in situ protein network mapping in normal and cancerous colon from the same patient reveals more than five-thousand cancer specific protein clusters and their subcellular annotation by using a three symbol code

In a proof of principle study, we have applied an automated fluorescence toponome imaging system (TIS) to examine whether TIS can find protein network structures, distinguishing cancerous from normal colon tissue present in a surgical sample from the same patient. By using a three symbol code and a power of combinatorial molecular discrimination (PCMD) of 2(21) per subcellular data point in one single tissue section, we demonstrate an in situ protein network structure, visualized as a mosaic of 6813 protein clusters (combinatorial molecular phenotype or CMPs), in the cancerous part of the colon. By contrast, in the histologically normal colon, TIS identifies nearly 5 times the number of protein clusters as compared to the cancerous part (32u2009009). By subcellular visualization procedures, we found that many cell surface membrane molecules were closely associated with the cell cytoskeleton as unique CMPs in the normal part of the colon, while the same molecules were disassembled in the cancerous part, suggesting the presence of dysfunctional cytoskeleton-membrane complexes. As expected, glandular and stromal cell signatures were found, but interestingly also found were potentially TIS signatures identifying a very restricted subset of cells expressing several putative stem cell markers, all restricted to the cancerous tissue. The detection of these signatures is based on the extreme searching depth, high degree of dimensionality, and subcellular resolution capacity of TIS. These findings provide the technological rationale for the feasibility of a complete colon cancer toponome to be established by massive parallel high throughput/high content TIS mapping.

Toponome mapping in prostate cancer: detection of 2000 cell surface protein clusters in a single tissue section and cell type specific annotation by using a three symbol code.

The toponome imaging technology MELC/TIS was applied to analyze prostate cancer tissue. By cyclical imaging procedures, we detected 2100 cell surface protein clusters in a single tissue section. This study provides the whole data set, a new kind of high dimensional data space, solely based on the structure-bound architecture of an in situ protein network, a putative fraction of the tissue code of prostate cancer. It is visualized as a colored mosaic composed of distinct protein clusters, together forming a motif expressed exclusively on the cell surface of neoplastic cells in prostate acini. Cell type specific expression of this motif, found in this preliminary study, suggests that high-throughput toponome analyses of a larger number of cases will provide insight into disease specific protein networks.

Automated detection and quantification of fluorescently labeled synapses in murine brain tissue sections for high throughput applications

The automated detection and quantification of fluorescently labeled synapses in the brain is a fundamental challenge in neurobiology. Here we have applied a framework, based on machine learning, to detect and quantify synapses in murine hippocampus tissue sections, fluorescently labeled for synaptophysin using a direct and indirect labeling method with FITC as fluorescent dye. In a pixel-wise application of the classifier, small neighborhoods around the image pixels are mapped to confidence values. Synapse positions are computed from these confidence values by evaluating the local confidence profiles and comparing the values with a chosen minimum confidence value, the so called confidence threshold. To avoid time-consuming hand-tuning of the confidence threshold we describe a protocol for deriving the threshold from a small set of images, in which an expert has marked punctuate synaptic fluorescence signals. We can show that it works with high accuracy for fully automated synapse detection in new sample images. The resulting patch-by-patch synapse screening system, referred to as i3S (intelligent synapse screening system), is able to detect several thousand synapses in an area of 768×512 pixels in approx. 20s. The software approach presented in this study provides a reliable basis for high throughput quantification of synapses in neural tissue.

On the origin of cell functions encoded in the toponome.

The fluorescence imaging technology TIS enables the investigator to locate and decipher functional protein networks (the toponome) in a single cell or tissue section. TIS permits optical resolution and simultaneous detection of thousands of protein clusters in situ, composed of different protein species, and their visualization as coloured mosaic structures. Access to this level of protein organization relies on the ability of TIS to break the spectral limit of fluorescence microscopy and co-map a quasi unlimited number of different proteins by using specific tag libraries. The present review outlines the principles of the TIS technology as a fundamental approach to the internal structure, the code and the semantics of any protein system in situ. The review focusses on the discovery of basic coding rules in the toponome, indicating that cells establish functional protein networks on the cell surface by interlocking protein clusters, in which highly dissimilar proteins are topologically assembled (dissimilarity rule), and each cluster exhibits a characteristic geometry on the submicrometer to micrometer scale (geometry rule). The network is hierarchically controlled by a lead protein, whose inhibition leads to disassembly of the network and loss of function. Use of TIS on a proteome-wide scale provides a new way to medical systems biology.

Automatic Recognition of Muscle-invasive T-lymphocytes Expressing Dipeptidyl-peptidase IV (CD26) and Analysis of the Associated Cell Surface Phenotypes

A neural cell detection system (NCDS) for the automatic quantitation of fluorescent lymphocytes in tissue sections was used to analyze CD26 expression in muscle-invasive T-cells. CD26 is a cell surface dipeptidyl-peptidase IV (DPP IV) involved in co-stimulatory activation of T-cells and also in adhesive events. The NCDS system acquires visual knowledge from a set of training cell image patches selected by a user. The trained system evaluates an image in 2 min calculating (i) the number, (ii) the positions and (iii) the phenotypes of the fluorescent cells. In the present study we have used the NCDS to identity DPP IV (CD26) expressing invasive lymphocytes in sarcoid myopathy and to analyze the associated cell surface phenotypes. We find highly unusual phenotypes characterized by differential combination of seven cell surface receptors usually involved in co-stimulatory events in T-lymphocytes. The data support a differential adhesive rather than a co-stimulatory role of CD26 in muscle-invasive cells. The adaptability of the NCDS algorithm to diverse types of cells should enable us to approach any invasion process, including invasion of malignant cells.

Interactive, Graph-based Visual Analysis of High-dimensional, Multi-parameter Fluorescence Microscopy Data in Toponomics

In Toponomics, the function protein pattern in cells or tissue (the toponome) is imaged and analyzed for applications in toxicology, new drug development and patient-drug-interaction. The most advanced imaging technique is robot-driven multi-parameter fluorescence microscopy. This technique is capable of co-mapping hundreds of proteins and their distribution and assembly in protein clusters across a cell or tissue sample by running cycles of fluorescence tagging with monoclonal antibodies or other affinity reagents, imaging, and bleaching in situ. The imaging results in complex multi-parameter data composed of one slice or a 3D volume per affinity reagent. Biologists are particularly interested in the localization of co-occurring proteins, the frequency of co-occurrence and the distribution of co-occurring proteins across the cell. We present an interactive visual analysis approach for the evaluation of multi-parameter fluorescence microscopy data in toponomics. Multiple, linked views facilitate the definition of features by brushing multiple dimensions. The feature specification result is linked to all views establishing a focus+context visualization in 3D. In a new attribute view, we integrate techniques from graph visualization. Each node in the graph represents an affinity reagent while each edge represents two co-occurring affinity reagent bindings. The graph visualization is enhanced by glyphs which encode specific properties of the binding. The graph view is equipped with brushing facilities. By brushing in the spatial and attribute domain, the biologist achieves a better understanding of the function protein patterns of a cell. Furthermore, an interactive table view is integrated which summarizes unique fluorescence patterns. We discuss our approach with respect to a cell probe containing lymphocytes and a prostate tissue section.