Christian Münzenmayer

Characterizing mammographic images by using generic texture features

IntroductionAlthough mammographic density is an established risk factor for breast cancer, its use is limited in clinical practice because of a lack of automated and standardized measurement methods. The aims of this study were to evaluate a variety of automated texture features in mammograms as risk factors for breast cancer and to compare them with the percentage mammographic density (PMD) by using a case-control study design.MethodsA case-control study including 864 cases and 418 controls was analyzed automatically. Four hundred seventy features were explored as possible risk factors for breast cancer. These included statistical features, moment-based features, spectral-energy features, and form-based features. An elaborate variable selection process using logistic regression analyses was performed to identify those features that were associated with case-control status. In addition, PMD was assessed and included in the regression model.ResultsOf the 470 image-analysis features explored, 46 remained in the final logistic regression model. An area under the curve of 0.79, with an odds ratio per standard deviation change of 2.88 (95% CI, 2.28 to 3.65), was obtained with validation data. Adding the PMD did not improve the final model.ConclusionsUsing texture features to predict the risk of breast cancer appears feasible. PMD did not show any additional value in this study. With regard to the features assessed, most of the analysis tools appeared to reflect mammographic density, although some features did not correlate with PMD. It remains to be investigated in larger case-control studies whether these features can contribute to increased prediction accuracy.

Review of free software tools for image analysis of fluorescence cell micrographs.

An increasing number of free software tools have been made available for the evaluation of fluorescence cell micrographs. The main users are biologists and related life scientists with no or little knowledge of image processing. In this review, we give an overview of available tools and guidelines about which tools the users should use to segment fluorescence micrographs. We selected 15 free tools and divided them into stand‐alone, Matlab‐based, ImageJ‐based, free demo versions of commercial tools and data sharing tools. The review consists of two parts: First, we developed a criteria catalogue and rated the tools regarding structural requirements, functionality (flexibility, segmentation and image processing filters) and usability (documentation, data management, usability and visualization). Second, we performed an image processing case study with four representative fluorescence micrograph segmentation tasks with figure‐ground and cell separation. The tools display a wide range of functionality and usability. In the image processing case study, we were able to perform figure‐ground separation in all micrographs using mainly thresholding. Cell separation was not possible with most of the tools, because cell separation methods are provided only by a subset of the tools and are difficult to parametrize and to use. Most important is that the usability matches the functionality of a tool. To be usable, specialized tools with less functionality need to fulfill less usability criteria, whereas multipurpose tools need a well‐structured menu and intuitive graphical user interface.

Automatic Adaptive Enhancement for Images Obtained With Fiberscopic Endoscopes

Modern techniques for medical diagnostics and therapy in keyhole surgery scenarios as well as technical inspection make use of flexible endoscopes. Their characteristic bendable image conductor consists of a very limited number of coated fibers, which leads to so-called comb structure. This effect has a negative impact on further image processing steps such as feature tracking because these overlaid image structures are wrongly detected as image features. With respect to these tasks, we propose an automatic approach to generate optimal spectral filter masks for enhancement of fiberscopic images. We apply the Nyquist-Shannon sampling theorem to the spectrum of fiberscopically acquired images to obtain parameters for optimal filter mask calculation. This can be done automatically and independently of scale and resolution of the image conductor as well as type and resolution of the image sensor. We designed and verified simple rotation invariant masks as well as star-shaped rotation variant masks that contain information about orientation between the fiberscope and sensor. A subjective survey among experts between different modes of filtering certified the best results to the adapted star-shaped mask for high-quality glass fiberscopes. We furthermore define an objective metric to evaluate the results of different filter approaches, which verifies the results of the subjective survey. The proposed approach enables the automated reduction of fiberscopic comb structure. It is adaptive to arbitrary endoscope and sensor combinations. The results give the prospect of a large field of possible applications to reduce fiberscopic structure both for visual optimization in clinical environments and for further digital imaging tasks

Multispectral Texture Analysis Using Interplane Sum- and Difference-Histograms

In this paper we present a new approach for color texture classification which extends the gray level sum- and difference histogram features [8]. Intra- and inter-plane second order features capture the spatial correlations between color bands. A powerful set of features is obtained by non-linear color space conversion to HSV and thresholding operation to eliminate the influence of sensor noise on color information. We present an evaluation of classification performance using four different image sets.

Feature-based real-time endoscopic mosaicking

In the field of minimally invasive surgery one barrier in clinical practice is the limited field of view provided by endoscopic cameras. We propose an image mosaicking approach to extend the field of view for real-time visualization by stitching several video frames. The approach is based on feature tracking and a robust estimation of the image-to-image transformations. We compare its performance to that of a state-of-the-art approach. Our method shows superior accuracy at frame rates of 6.8 to 8.1 frames per second, which allows for real-time visualization of the extended field of view.

A graph-based approach for local and global panorama imaging in cystoscopy

Inspection of the urinary bladder with an endoscope (cystoscope) is the usual procedure for early detection of bladder cancer. The very limited field of view provided by the endoscope makes it challenging to ensure, that the interior bladder wall has been examined completely. Panorama imaging techniques can be used to assist the surgeon and provide a larger view field. Different approaches have been proposed, but generating a panorama image of the entire bladder from real patient data is still a challenging research topic. We propose a graph-based and hierarchical approach to assess this problem to first generate several local panorama images, followed by a global textured three-dimensional reconstruction of the organ. In this contribution, we address details of the first level of the approach including a graph-based algorithm to deal with the challenging condition of in-vivo data. This graph strategy gives rise to a robust relocalization strategy in case of tracking failure, an effective keyframe selection process as well as the concept of building locally optimized sub-maps, which lay the ground for a global optimization process. Our results show the successful application of the method to four in-vivo data sets.

A spectral color correction framework for medical applications

This paper presents a new spectral approach to color correction for medical image analysis applications. Linear estimation with regularization by a constrained principal eigenvector method is used for calibration of the camera system and estimation of the illumination spectrum while spectral surface reflectivities are determined by Wiener inverse estimation. Nonlinear devices are handled by piecewise linear interpolation and any linear color preprocessing inside the camera is explicitly modeled. All measurement and estimation processes are combined into a spectral calibration framework for practical application in computer-assisted image analysis. The novelty of our approach lies in the generalization of the image formation model allowing for linear preprocessing inside the camera system. Such transforms would lead to erroneous results with positivity constraint based algorithms or a monochromator based measurement. We provide experimental results from a comprehensive set of reference measurements acquired with a video endoscopy system for gastroscopic application.

Illumination invariant color texture analysis based on sum- and difference-histograms

Color texture algorithms have been under investigation for quite a few years now. However, the results of these algorithms are still under considerable influence of the illumination conditions under which the images were captured. It is strongly desireable to reduce the influence of illumination as much as possible to obtain stable and satisfying classification results even under difficult imaging conditions, as they can occur e.g. in medical applications like endoscopy. In this paper we present the analysis of a well-known texture analysis algorithm, namely the sum- and difference-histogram features, with respect to illumination changes. Based on this analysis, we propose a novel set of features factoring out the illumination influence from the majority of the original features. We conclude our paper with a quantitative, experimental evaluation on artificial and real image samples.

Laryngoscopic Image Stitching for View Enhancement and Documentation – First Experiences

One known problem within laryngoscopy is the spatially limited view onto the hypopharynx and the larynx through the endoscope. To examine the complete larynx and hypopharynx, the laryngoscope can be rotated about its main axis, and hence the physician obtains a complete view. If such examinations are captured using endoscopic video, the examination can be reviewed in detail at a later time. Nevertheless, in order to document the examination with a single representative image, a panorama image can be computed for archiving and enhanced documentation. Twenty patients with various clinical findings were examined with a 70 rigid laryngoscope, and the video sequences were digitally stored. The image sequence for each patient was then post-processed using an image stitching tool based on SIFT features, the RANSAC approach and blending. As a result, endoscopic panorama images of the larynx and pharynx were obtained for each video sequence. The proposed approach of image stitching for laryngoscopic video sequences offers a new tool for enhanced visual examination and documentation of morphologic characteristics of the larynx and the hypopharynx.

Automated morphological analysis of bone marrow cells in microscopic images for diagnosis of leukemia: nucleus-plasma separation and cell classification using a hierarchical tree model of hematopoesis

The morphological differentiation of bone marrow is fundamental for the diagnosis of leukemia. Currently, the counting and classification of the different types of bone marrow cells is done manually under the use of bright field microscopy. This is a time-consuming, subjective, tedious and error-prone process. Furthermore, repeated examinations of a slide may yield intra- and inter-observer variances. For that reason a computer assisted diagnosis system for bone marrow differentiation is pursued. In this work we focus (a) on a new method for the separation of nucleus and plasma parts and (b) on a knowledge-based hierarchical tree classifier for the differentiation of bone marrow cells in 16 different classes. Classification trees are easily interpretable and understandable and provide a classification together with an explanation. Using classification trees, expert knowledge (i.e. knowledge about similar classes and cell lines in the tree model of hematopoiesis) is integrated in the structure of the tree. The proposed segmentation method is evaluated with more than 10,000 manually segmented cells. For the evaluation of the proposed hierarchical classifier more than 140,000 automatically segmented bone marrow cells are used. Future automated solutions for the morphological analysis of bone marrow smears could potentially apply such an approach for the pre-classification of bone marrow cells and thereby shortening the examination time.