Wyniki wyszukiwania - BazTech

1

Machine learning system for automated blood smear analysis

Grochowski Michał, Wąsowicz Michał, Mikołajczyk Agnieszka, Ficek Mateusz, Kulka Marek, Wróbel Maciej S., Jędrzejewska-Szczerska Małgorzata

Metrology and Measurement Systems

|

2019

|

Vol. 26, nr 1

81--93

EN

In this paper the authors propose a decision support system for automatic blood smear analysis based onmicroscopic images. The images are pre-processed in order to remove irrelevant elements and to enhancethe most important ones – the healthy blood cells (erythrocytes) and the pathologic ones (echinocytes). The separated blood cells are analysed in terms of their most important features by the eigenfaces method. The features are the basis for designing the neural network classifier, learned to distinguish between erythrocytes and echinocytes. As the result, the proposed system is able to analyse the smear blood images in a fully automatic way and to deliver information on the number and statistics of the red blood cells, both healthy and pathologic. The system was examined in two case studies, involving the canine and human blood, and then consulted with the experienced medicine specialists. The accuracy of classification of red blood cells into erythrocytes and echinocytes reaches 96%.

2

Ocena toksyczności wybranych pestycydów, ich metabolitów i zanieczyszczeń produkcyjnych w stosunku do białych i czerwonych krwinek człowieka

Huras B., Sosnowska B., Kwiatkowska B., Bukowska B.

Przemysł Chemiczny

|

2016

|

T. 95, nr 12

2418--2421

PL

Przedstawiono wyniki badań wpływu dwóch insektycydów (bromfenwinfos i chlorfenwinfos) oraz herbicydu glifosat, a także ich metabolitów oraz zawartych w preparatach pestycydowych potencjalnych zanieczyszczeń, na erytrocyty i jednojądrzaste komórki krwi człowieka (głównie limfocyty).

EN

Chem. and physiol. properties of bromfenvinphos, chlorfenvinphos and glyphosate were reviewed with 22 refs. Their metabolites and potential impurities were also taken into consideration.

3

Ultrastructural changes in blood cells in the hematopoietic organs of Lake Baikal fish exposed to phenol

Yakhnenko V., Klimenkov I., Belyshenko A.

Environmental Biotechnology

|

2014

|

Vol. 10, No. 2

73--79

EN

Baikal Lake fish: stone sculpin (Paracottus knerii), yellowfin (Cottocomephorus grewigkii) and perch (Perca fluviatilis) were exposed for 14 days to phenol (6mg˖L-1). The reaction of blood cells in all studied species had a similar character, whilst, also revealing distinctions. Fast activation of immune processes was found in the pelagic yellowfin. These changes were slower at the coastal stone sculpin. Quantitative changes of blood cells were minor in the coastal nonendemic perch. After four days of exposure, the cells of fish showed signs of destructive processes: strong vacuolization of cytoplasm and partial destruction of the cell membrane. In the cell nucleus the chromatin was condensed, the perinuclear space had expanded and the nuclear membrane had been partly destroyed. In another experiment, stone sculpin and perch were first exposed to phenol for 30 days and then they were kept for another 30 days in water without phenol. In the kidneys and spleen of stone sculpin the processes of lymphopoiesis were observed, whereas in perch the processes of lymphopoiesis and myelopoiesis occurred.

4

Technologie pomiarowe w diagnostyce hematologicznej. Odczynniki

Kotuła I.

Laboratorium - Przegląd Ogólnopolski

|

2012

|

nr 7-8

36--39

PL

W diagnostyce laboratoryjnej morfologia krwi należy do badań podstawowych, które w chwili obecnej zostały prawie całkowicie zautomatyzowane. Ostatnie pół wieku przyniosło ogromny postęp w badaniu komórek krwi, możliwy dzięki wprowadzeniu coraz nowszych metod pomiarowych oraz rozwojowi oprogramowania, które dostarcza coraz więcej informacji o każdej komórce znajdującej się w układzie krążenia.

EN

Complete blood count belongs to the panel of moste frequently requested blood tests. This test had been currently almost completely automated. Last 50 years brought a huge progress in examination of blood cells. It was possible mainly due to the application of new measurement techniques and software development witch jointly are able to provide limitless supply of information about each cell in blood stream.

5

Fourier analysis in classification of blood cells

Kocjan K., Kotarski W.

Journal of Medical Informatics & Technologies

|

2003

|

Vol. 5

MI61--66

EN

In the paper we present some results concerning the usage of Fourier analysis which we can successfully apply to distinguish between normal and pathological blood cells. We use special area function and different number of Fourier descriptors that are automatically calculated for all objects pointed out in an image. Calculations are performed with the help of the software made by the first author. Experiments performed on the same set of tested images as in [3] and [5] draw as to the same conclusions as there in [3] where the fractal analysis to shape has been used and in [5] where simple geometrical shape parameters have been applied. Other application of Fourier analysis one can find in [9].

6

Blood cells analysis based on simple geometrical shape descriptors

Kocjan K., Kotarski W., Widuch S.

Journal of Medical Informatics & Technologies

|

2002

|

Vol. 3

MI207--212

EN

In the paper we present some results concerning application of simple shape parameters that are successfully used to distinguish between normal and pathological blood cells. All descriptors are based on shape area and its perimeter. We use five parameters that are automatically calculated for objects pointed out in the analyzed image with the help of our software. The experiments performed on the same set of tested images as in [3] let us draw the same conclusions as those reported in [3] where fractal analysis to shape has been used.

7

Shape analysis of blood cells based on fractal dimension

Kotarski W., Widuch S.

Journal of Medical Informatics & Technologies

|

2001

|

Vol. 2, Part. 1

MI177--MI182

EN

The paper presents some results concerning application of the fractal approach to analysis of shape of blood cells. Using the software by Kindratenko [4] the fractal dimension and other simple geometrical parameters of normal and pathological blood cells have been calculated. The investigation aproved that the fractal dimension and the perimeter of abnormal blood cells differ significantly from normal ones.