Wyniki wyszukiwania - BazTech

1

Application of a Pathomorphological Image Database in Computer-Aided Cytological Examinations

Piętka B. D., Dulewicz A., Jaszczak P., Kupis P.

Machine Graphics and Vision

|

2010

|

Vol. 19, No. 3

321-337

EN

The paper deals with the problem of early detection of bladder cancer based on non-invasive, voided urine cytological investigations. In spite of the diagnostic potential of the method for discovering malignancy associated changes in cells before they start to form a tumour, cytological tests seem to be underestimated by physicians, as there is a common view that their sensitivity, especially in early stages of the cancer, is relatively low. We depict here just one, but significant, direction of our work that aims to support the cytopathologist in making the diagnosis more accurate and reliable. The key idea relies on classification of adaptive smear objects by searching for similar patterns in a flexible pathomorphological image database using content-based image retrieval technology (CBIR).

2

Removing artefacts from microscopic images of cytological smears

Piętka B. D., Dulewicz A., Jaszczak P.

Machine Graphics and Vision

|

2008

|

Vol. 17, No. 1/2

131-152

EN

This paper gives an overview of authors' attempts to design a computer-assisted urine smear screening system, focusing on the nastiest issues hampering its successful practical implementation. There are many valuable works concerning more or less sophisticated image processing and data mining algorithms which are capable of automatically detecting pathological morphology of cytological objects and distinguishing them from normal ones. Unfortunately, most of the attempts to implement those smart ideas in real world are likely to fail because of one but fundamental obstacle - artefacts. If not properly identified and removed from the analysis, they tend to generate so many false-positive warnings that the automated support is going to be useless because of its dramatically low specificity. Our paper addresses this neglected problem, trying to point out some general rules and implementation details that should be followed to reduce the influence of artefacts on overall system performance.

3

A method of image information selection in the process of automatic scanning of microscopic specimens

Dulewicz A., Piętka D., Jaszczak P., Nechay A.

Journal of Applied Computer Science

|

2003

|

Vol. 11, nr 2

7-18

EN

Examination of a large number of microscopic preparations as well as carrying out clinical and screening tests can be done only with the help of acquisition of images in the process of automatic scanning of microscopic preparations. However, the time of precise scanning performed field by field is very long when using big enlargements of the microscope. At the same time, an accurate specimen inspection is necessary when we analyse smears, searching for rear events. An application, developed by the authors, for performing fast and exact scanning is presented. Possibility to combine speed with precision was achieved due to the evaluating contents of the scene by the analysis of a live camera signal and quick microscopic stage movement when empty smear regions were encountered. Many technical problems had to be solved, trying to implement this idea. The application was developed in Borland C++ Builder and Delphi environment and is intended for Windows based systems. The paper presents in details some common problems related to automatic scanning in screening projects.

4

A trial of a new approach to computer analysis of urothelial nuclei for cancer detection

Dulewicz A., Piętka D., Jaszczak P.

Image Processing & Communications

|

2003

|

Vol. 9, no 3-4

11-18

EN

The objective of this work is a new approach to computer-based analysis of Feulgen-stained urinary bladder cell nuclei to identify neoplastic nuclei. 56 patients were taken under consideration. Among them 20 cases were controls and 36 cases were cancer of two grades of malignancy. The cytological smears were obtained by "bladder washing" technique. Image analysis was carried out by means of digital image processing system designed by the authors. At the first step of the process slides were automatically scanned and 80 images were registered. Then image processing began performing image normalization, objects (nuclei) extraction and measuring of features describing nuclei. A multistage classifier was constructed to identify positive and negative cases. The results of this study yielded a 90% correct classification rate in the control group, while an 80,5% rate was obtained among the cancer patients. The sensitivity of the method was 91% and the specificity was 84%.

5

Extending DIPS software package for research and routine investigations of biomedical images

Piętka D., Dulewicz A., Jaszczak P., Nechay A.

Machine Graphics and Vision

|

1998

|

Vol. 7, No. 4

711-723

EN

The paper introduces DIPS (Digital Images Procesing System), a new, original software package, developed to meet specific requirements of image analysis in scientific environment. Without gooing deeply into programming details, key features of the system are highlighted: flexibility when designing new picture processing schemes and simplicity when performing routine tasks.