Characterization and featuring of histological section images

doi:10.1016/0167-8655(88)90109-2

Pattern Recognition Letters

Volume 7, Issue 4, April 1988, Pages 245-252

https://doi.org/10.1016/0167-8655(88)90109-2 Get rights and content

Abstract

Image analysis of the structural organization of cells in histological sections has been shown to be useful for the quantitative characterization of tissue. The organization may be expressed in the form of a tree or a graph structure. Features derived from the graph along with the cell features can be used effectively for case classification and diagnosis. The paper describes techniques of generating the tree and graph as well as deriving features from them. Results of applying the techniques to cervical tissue section specimen images are also presented.

References (18)

C. Arcelli et al.
Computing Voronoi diagrams in digital pictures
Pattern Recognition Letters
(1986)
G. Burger et al.
Specimen classification in cytometry: An intercomparison of various means of decision making
K. Preston
Tissue section analysis: Feature selection and image Processing
Pattern Recognition
(1981)
O. Eriksson et al.
Tuning of an interactive software system for image analysis to quantitative microscopy
P. Gais et al.
Lokale logische Algorithmen für Binärbilder
T.S. Huang et al.
A fast 2-dimensional median filter algorithm
K. Kayser et al.
Pattern recognition in histopathology by orders of textures
Medical Inform.
(1984)
Oberholzer, M. (1986). Private...
J.F. O'Callaghan
An alternative definition for ‘Neighbourhood of a point’
IEEE Trans. Computer
(1975)

There are more references available in the full text version of this article.

Cited by (20)

Image analysis of tissue sections
1996, Computers in Biology and Medicine
A knowledge acquisition tool in analytical pathology based on multi-media relational database
1994, Computer Methods and Programs in Biomedicine
The need for a knowledge based expert system for efficient decision making in the field of pathology has been well accepted. To build the knowledge-base for such an expert system is a painstaking task. This work is an attempt to provide the pathologists a powerful and user-friendly tool that will help them in the process of building the knowledge-base for medical diagnosis by closely looking at the specimen images and their extracted feature values. The tool is based on multi-media relational database and software like VAX Rally (4GL), ILIAD and SAS to provide a wide-range comparative study between feature data and image data; and also their statistical analysis.
A new software tool for image segmentation based on an interactive device
1993, Chemometrics and Intelligent Laboratory Systems
A new software tool for the development of an image segmentation technique has been designed, implemented and tested on a number of real application cases. It is created as a highly interactive software system by means of a standard computer device mouse and interpolation techniques. An entirely connected edge map of microscopic images of biological objects can be created. The method is simple and gives reproducible results in reasonable time.
Cytometry in histological sections of colon carcinoma
1992, Pathology Research and Practice
A short description of a project of cytometry in histological sections of colon carcinoma is given with emphasis on the methodical aspects. Possible strategies of cytometric measurement and problems related to it (focus, overlap, segmentation of objects) are described. The main effort concerns interactive selection of tumor cells and the segmentation in cases of densely distributed and overlapping nuclei. All other succeeding processing steps are performed fully automatically.
The resulting quantitative features are stored together with the original images on an optical disk for further examinations and reexaminations, allowing the direct relation of feature values to visual image content. The evaluation of the features as well as their interpretation is only at the beginning. Especially the problem of relating section information with true 3-dimensional information is not described here and necessitates further research.
In a first investigation only a few tumors without and with metastases were analyzed. The preliminary results correspond with findings of Kunze et al.^3,4.
Quantification of tissue sections. Graph theory and topology as modelling tools
1990, Pattern Recognition Letters
Tissue sections consist of distributed objects, the nuclear profiles. A methodological tool box is presented, based on graph theory and topology, to describe formally the arrangement of such objects, to define agglomerations of objects in a hierarchical manner and to compute quantitative features for every object. For a set of tissue sections (conisates) from the cervix uteri, a model description and an evaluation are given.
Analysis of food processing crystal images
2023, IS and T International Symposium on Electronic Imaging Science and Technology

View all citing articles on Scopus

^∗: Guest Scientist from: Electronics and Communication Sciences Unit, Indian Statistical Institute, Calcutta, India.

View full text

Characterization and featuring of histological section images

Abstract

Pattern Recognition Letters

Pattern Recognition

Tuning of an interactive software system for image analysis to quantitative microscopy

Lokale logische Algorithmen für Binärbilder

A fast 2-dimensional median filter algorithm

Pattern recognition in histopathology by orders of textures

Medical Inform.

An alternative definition for ‘Neighbourhood of a point’

IEEE Trans. Computer