Human vs. machine: evaluation of fluorescence micrographs

Nattkemper, Tim Wilhelm; Twellmann, Thorsten; Ritter, Helge; Schubert, Walter

doi:10.1016/s0010-4825(02)00060-4

Cited by 51 publications

(44 citation statements)

References 28 publications

(25 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A comprehensive study evaluating the performance of domain experts regarding the detection of lymphocytes is presented by [12]. In a best case, a medium-skilled expert needs on average one hour for analyzing a fluorescence micrograph.…”

Section: Expert Variability In Fluorescence Microscopymentioning

confidence: 99%

See 1 more Smart Citation

Computational pathology: Challenges and promises for tissue analysis

Fuchs

Buhmann

2011

Computerized Medical Imaging and Graphics

216

127

View full text Add to dashboard Cite

The histological assessment of human tissue has emerged as the key challenge for detection and treatment of cancer. A plethora of different data sources ranging from tissue microarray data to gene expression, proteomics or metabolomics data provide a detailed overview of the health status of a patient. Medical doctors need to assess these information sources and they rely on data driven automatic analysis tools. Methods for classification, grouping and segmentation of heterogeneous data sources as well as regression of noisy dependencies and estimation of survival probabilities enter the processing workflow of a pathology diagnosis system at various stages. This paper reports on state-of-the-art of the design and effectiveness of computational pathology workflows and it discusses future research directions in this emergent field of medical informatics and diagnostic machine learning.

show abstract

Section: Expert Variability In Fluorescence Microscopymentioning

confidence: 99%

“…Four exemplary micrographs were blindly evaluated by five experts. To evaluate the inter-observer variability nattkemper et al [12] define a gold standard comprising all cell positions in a micrograph that were detected by at least two experts.…”

Section: Expert Variability In Fluorescence Microscopymentioning

confidence: 99%

Computational pathology: Challenges and promises for tissue analysis

Fuchs

Buhmann

2011

Computerized Medical Imaging and Graphics

216

127

View full text Add to dashboard Cite

show abstract

“…Detection and classification of cells in microscopic images is a large area of research, with a long history within biomedical imaging (6)(7)(8). Commercially available software packages for cell counting and cell characterization are available for clinical and research use (9).…”

mentioning

confidence: 99%

Automated detection of tunneling nanotubes in 3D images

et al. 2006

View full text Add to dashboard Cite

Background: This paper presents an automated method for the identification of thin membrane tubes in 3D fluorescence images. These tubes, referred to as tunneling nanotubes (TNTs), are newly discovered intercellular structures that connect living cells through a membrane continuity. TNTs are 50-200 nm in diameter, crossing from one cell to another at their nearest distance. In microscopic images, they are seen as straight lines. It now emerges that the TNTs represent the underlying structure of a new type of cell-to-cell communication. Methods: Our approach for the identification of TNTs is based on a combination of biological cell markers and known image processing techniques. Watershed segmentation and edge detectors are used to find cell borders, TNTs, and image artifacts. Mathematical morphology is employed at several stages of the processing chain. Two image channels are used for the calculations to improve classification of watershed regions into cells and background. One image channel displays cell borders and TNTs, the second is used for cell classification and dis-

show abstract

“…In another classification study, on the problem of cell detection, it was observed that computers perform comparably to a medium-quality expert, but were still outperformed by an experienced expert. However, high variation between experts was observed [25].…”

Section: Supervised Classificationmentioning

confidence: 96%

Principles of Bioimage Informatics: Focus on Machine Learning of Cell Patterns

Coelho

Glory-Afshar

Kangas

et al. 2010

Linking Literature, Information, and Knowledge for Biology

View full text Add to dashboard Cite

Abstract. The field of bioimage informatics concerns the development and use of methods for computational analysis of biological images. Traditionally, analysis of such images has been done manually. Manual annotation is, however, slow, expensive, and often highly variable from one expert to another. Furthermore, with modern automated microscopes, hundreds to thousands of images can be collected per hour, making manual analysis infeasible.This field borrows from the pattern recognition and computer vision literature (which contain many techniques for image processing and recognition), but has its own unique challenges and tradeoffs.Fluorescence microscopy images represent perhaps the largest class of biological images for which automation is needed. For this modality, typical problems include cell segmentation, classification of phenotypical response, or decisions regarding differentiated responses (treatment vs. control setting). This overview focuses on the problem of subcellular location determination as a running example, but the techniques discussed are often applicable to other problems.

show abstract

Human vs. machine: evaluation of fluorescence micrographs

Cited by 51 publications

References 28 publications

Computational pathology: Challenges and promises for tissue analysis

Computational pathology: Challenges and promises for tissue analysis

Automated detection of tunneling nanotubes in 3D images

Principles of Bioimage Informatics: Focus on Machine Learning of Cell Patterns

Contact Info

Product

Resources

About