Thomas Walter

Phenotypic profiling of the human genome by time-lapse microscopy reveals cell division genes.

Despite our rapidly growing knowledge about the human genome, we do not know all of the genes required for some of the most basic functions of life. To start to fill this gap we developed a high-throughput phenotypic screening platform combining potent gene silencing by RNA interference, time-lapse microscopy and computational image processing. We carried out a genome-wide phenotypic profiling of each of the ∼21,000 human protein-coding genes by two-day live imaging of fluorescently labelled chromosomes. Phenotypes were scored quantitatively by computational image processing, which allowed us to identify hundreds of human genes involved in diverse biological functions including cell division, migration and survival. As part of the Mitocheck consortium, this study provides an in-depth analysis of cell division phenotypes and makes the entire high-content data set available as a resource to the community.

A contribution of image processing to the diagnosis of diabetic retinopathy-detection of exudates in color fundus images of the human retina

In the framework of computer assisted diagnosis of diabetic retinopathy, a new algorithm for detection of exudates is presented and discussed. The presence of exudates within the macular region is a main hallmark of diabetic macular edema and allows its detection with a high sensitivity. Hence, detection of exudates is an important diagnostic task, in which computer assistance may play a major role. Exudates are found using their high grey level variation, and their contours are determined by means of morphological reconstruction techniques. The detection of the optic disc is indispensable for this approach. We detect the optic disc by means of morphological filtering techniques and the watershed transformation. The algorithm has been tested on a small image data base and compared with the performance of a human grader. As a result, we obtain a mean sensitivity of 92.8% and a mean predictive value of 92.4%. Robustness with respect to changes of the parameters of the algorithm has been evaluated.

Automatic detection of microaneurysms in color fundus images

This paper addresses the automatic detection of microaneurysms in color fundus images, which plays a key role in computer assisted diagnosis of diabetic retinopathy, a serious and frequent eye disease. The algorithm can be divided into four steps. The first step consists in image enhancement, shade correction and image normalization of the green channel. The second step aims at detecting candidates, i.e. all patterns possibly corresponding to MA, which is achieved by diameter closing and an automatic threshold scheme. Then, features are extracted, which are used in the last step to automatically classify candidates into real MA and other objects; the classification relies on kernel density estimation with variable bandwidth. A database of 21 annotated images has been used to train the algorithm. The algorithm was compared to manually obtained gradings of 94 images; sensitivity was 88.5% at an average number of 2.13 false positives per image.

CellCognition: time-resolved phenotype annotation in high-throughput live cell imaging

Fluorescence time-lapse imaging has become a powerful tool to investigate complex dynamic processes such as cell division or intracellular trafficking. Automated microscopes generate time-resolved imaging data at high throughput, yet tools for quantification of large-scale movie data are largely missing. Here we present CellCognition, a computational framework to annotate complex cellular dynamics. We developed a machine-learning method that combines state-of-the-art classification with hidden Markov modeling for annotation of the progression through morphologically distinct biological states. Incorporation of time information into the annotation scheme was essential to suppress classification noise at state transitions and confusion between different functional states with similar morphology. We demonstrate generic applicability in different assays and perturbation conditions, including a candidate-based RNA interference screen for regulators of mitotic exit in human cells. CellCognition is published as open source software, enabling live-cell imaging–based screening with assays that directly score cellular dynamics.

Visualization of image data from cells to organisms

Advances in imaging techniques and high-throughput technologies are providing scientists with unprecedented possibilities to visualize internal structures of cells, organs and organisms and to collect systematic image data characterizing genes and proteins on a large scale. To make the best use of these increasingly complex and large image data resources, the scientific community must be provided with methods to query, analyze and crosslink these resources to give an intuitive visual representation of the data. This review gives an overview of existing methods and tools for this purpose and highlights some of their limitations and challenges.

Segmentation of Color Fundus Images of the Human Retina: Detection of the Optic Disc and the Vascular Tree Using Morphological Techniques

This paper presents new algorithms based on mathematical morphology for the detection of the optic disc and the vascular tree in noisy low contrast color fundus photographs. Both features - vessels and optic disc - deliver landmarks for image registration and are indispensable to the understanding of retinal fundus images. For the detection of the optic disc, we first find the position approximately. Then we find the exact contours by means of the watershed transformation. The algorithm for vessel detection consists in contrast enhancement, application of the morphological top-hat-transform and a post-filtering step in order to distinguish the vessels from other blood containing features.

Assessment of algorithms for mitosis detection in breast cancer histopathology images.

The proliferative activity of breast tumors, which is routinely estimated by counting of mitotic figures in hematoxylin and eosin stained histology sections, is considered to be one of the most important prognostic markers. However, mitosis counting is laborious, subjective and may suffer from low inter-observer agreement. With the wider acceptance of whole slide images in pathology labs, automatic image analysis has been proposed as a potential solution for these issues. In this paper, the results from the Assessment of Mitosis Detection Algorithms 2013 (AMIDA13) challenge are described. The challenge was based on a data set consisting of 12 training and 11 testing subjects, with more than one thousand annotated mitotic figures by multiple observers. Short descriptions and results from the evaluation of eleven methods are presented. The top performing method has an error rate that is comparable to the inter-observer agreement among pathologists.

Visualizing biological data-now and in the future.

Methods and tools for visualizing biological data have improved considerably over the last decades, but they are still inadequate for some high-throughput data sets. For most users, a key challenge is to benefit from the deluge of data without being overwhelmed by it. This challenge is still largely unfulfilled and will require the development of truly integrated and highly useable tools.

Evaluation of automated fundus photograph analysis algorithms for detecting microaneurysms, haemorrhages and exudates, and of a computer-assisted diagnostic system for grading diabetic retinopathy.

AIMS This study aimed to evaluate automated fundus photograph analysis algorithms for the detection of primary lesions and a computer-assisted diagnostic system for grading diabetic retinopathy (DR) and the risk of macular edema (ME). METHODS Two prospective analyses were conducted on fundus images from diabetic patients. Automated detection of microaneurysms and exudates was applied to two small image databases on which these lesions were manually marked. A computer-assisted diagnostic system for the detection and grading of DR and the risk of ME was then developed and evaluated, using a large database containing both normal and pathological images, and compared with manual grading. RESULTS The algorithm for the automated detection of microaneurysms demonstrated a sensitivity of 88.5%, with an average number of 2.13 false positives per image. The pixel-based evaluation of the algorithm for automated detection of exudates had a sensitivity of 92.8% and a positive predictive value of 92.4%. Combined automated grading of DR and risk of ME was performed on 761 images from a large database. For DR detection, the sensitivity and specificity of the algorithm were 83.9% and 72.7%, respectively, and, for detection of the risk of ME, the sensitivity and specificity were 72.8% and 70.8%, respectively. CONCLUSION This study shows that previously published algorithms for computer-aided diagnosis is a reliable alternative to time-consuming manual analysis of fundus photographs when screening for DR. The use of this system would allow considerable timesavings for physicians and, therefore, alleviate the time spent on a mass-screening programme.

Automatic Detection of Microaneurysms in Color Fundus Images of the Human Retina by Means of the Bounding Box Closing

In this paper we propose a new algorithm for the detection of microaneurysms in color fundus images of the human retina. Microaneurysms are the first unequivocal indication of Diabetic Retinopathy (DR), a severe and wide-spread eye disease. Their automatic detection may play a major role in computer assisted diagnosis of DR. We propose an algorithm that can be divided into four steps. The first step is an image enhancement technique that comprises normalization and noise reduction. The second step ist the extraction of small details that fulfill a certain criterion: This leads to the definition of the bounding box closing. Then, an automatic threshold depending on image quality is calculated. In the last step false positives are eliminated.