Image analysis – Applications – Biomedical applications
Reexamination Certificate
1999-02-19
2001-06-12
Johns, Andrew W. (Department: 2621)
Image analysis
Applications
Biomedical applications
Reexamination Certificate
active
06246785
ABSTRACT:
The present invention concerns a method for examining tissue samples or body fluids on a slide with an automatic microscope as well as a video system and an evaluation computer with neural networks. The details of the method follow from the claims
1
and
8
.
In the state of the art computer-aided image analysis systems are known for examining samples which comprise a microscope with a video camera coupled to a computer. The image recorded by the video camera is transferred with the aid of an image processing chip to the computer and displayed in a suitable manner on a screen using an imaging processing software. In the known procedure of the state of the art the user has to adjust and focus the microscope on the area to be examined. The sample is analysed on the basis of the image shown on the screen which can be optionally aided by the image processing software by changes in the contrast, colouration etc.
Instrumentation with a greater degree of automation is also known in the state of the art as for example described in WO 91/20048 and WO 92/13308. The devices disclosed in these documents have an automatic microscope with a camera and a computer-aided analysis system. Lens changes, focussing and sample movement are carried out automatically. The analysis is carried out by abstracting the background from the image information by special methods such as e.g. threshold methods.
Objects are located within the image and separated from one another. The located objects (usually cells) are focussed and morphometric and densitometric parameters are determined. These parameters are subsequently evaluated by rule-based or multivariate statistical methods. A requirement for this procedure is that cells in close proximity can be optically separated from one another since otherwise cells cannot be recognized on the basis of morphometric and densitometric parameters. Such a procedure is described in the article “Automated Cervical Smear Classification” (IEEE/9th Annual Conference of the Engineering in Medicine and Biological Society, page 1457). In this article it is proposed that the problem of overlapping cells can be solved by only staining the nuclei and carrying out the classification on the basis of this staining.
Furthermore mathematical optimization methods are known in the state of the art which attempt to separate the images of the objects from one another in a multivariable space by separation lines/separation areas. Rule-based and statistical methods have also been developed to solve the problem of object separation.
FIG. 1
shows the principal manner in which a neural network functions.
FIG. 2
shows an image of an object to be analysed which is located on a slide.
FIG. 3
shows an analysis of intensity distribution as described in Example 1.
FIG. 4
is a schematic representation of intensity distribution as described in Example 1.
FIG. 5
is a flow diagram of the present invention.
REFERENCES:
patent: 4965725 (1990-10-01), Rutenberg
patent: 5313532 (1994-05-01), Harvey et al.
patent: 5741213 (1998-04-01), Kouchi et al.
patent: 5830141 (1998-11-01), Makram-Ebeid et al.
patent: 5857030 (1999-01-01), Gaborski et al.
patent: WO 91/20048 (1991-12-01), None
“An integrated neural network systemfor histological image understanding”, By Refenes et al., proceeding of SPIE, The international society for optical engineering, Bd. 1386, 1990, pp. 62-74.*
“Integration of neural networks and decision tree classifiers for automated cytology screening”, By Shih-Jong Lee et al., IEEE International joint conference on neural networks, 1991, pp. I 257-I 261.*
“An automatic system for the classification of cellular categories in cytological images”, By Revenu et al., Proceedings of SPIE, 1993, pp. 32-43.*
A.N. Refenes et al., “An Integrated Neural Network System for Histological Image Understanding” SPIE vol. 1386 Machine Vision Systems Integration in Industry (1990) pp. 62-74.
Marinette Revenu et al. “An Automatic System for the Classification of Cellular Categories in Cytological Images” SPIE vol. 2055 Intelligent Robots and Computer Vision XII (1993) pp. 32-43.
Albert Winfried
Molnar Bela
Schafer Rainer
Amick Marilyn L.
Johns Andrew W.
Nakhjavan Shervin
Roche Diagnostics Corporation
Roche Diagnostics GmbH
LandOfFree
Automated, microscope-assisted examination process of tissue... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Automated, microscope-assisted examination process of tissue..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Automated, microscope-assisted examination process of tissue... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2503354