Wyniki wyszukiwania - BazTech

1

A novel approach for segmentation and counting of overlapped leukocytes in microscopic blood images

Sudha K., Geetha P.

Biocybernetics and Biomedical Engineering

|

2020

|

Vol. 40, no. 2

639--648

EN

Leukocytes count in the blood smear images plays an important role in identifying the overall health of the patient. The major steps involved in leukocytes counting system are segmentation and counting. However, the counting accuracy is greatly affected due to the morphological diversity of cells, the presence of staining artifacts and the overlapped cells. Therefore, this paper introduces a new framework to segment and counting of leukocytes. To segment leukocytes, an edge strength-based Grabcut method has been proposed. Later, the leukocyte region including the overlapped cells was counted using the novel gradient circular hough transform (GCHT) method. The research work was performed on ALL-IDB and Cellavision datasets. The proposed segmentation method has yielded high precision, recall and f -measure compared to the state-of-the-art methods. Additionally, comparison analy-sis was performed between the region count obtained using the existing and the GCHT method. The overall experimental results of the work showed that the proposed framework produced more accuracy in counting the leukocytes.

2

Metoda mikroskopowa oraz zastosowanie systemu EasyCell - badania porównawcze rozdziału krwinek białych w rozmazach krwi obwodowej

Jasiewicz A., Roszniowska-Bury G., Haertle D., Czyżewska E.

Laboratorium Medyczne

|

2018

|

nr 1

18--20

PL

Celem pracy była ocena porównywalności wyników rozdziału krwinek białych, uzyskanych przy zastosowaniu EasyCell i metody mikroskopowej. Do badań wykorzystano preparaty krwi obwodowej pacjentów dorosłych (n = 90), dzieci (n = 52) i chorych hematologicznych (n = 110). Do analizy porównawczej uzyskanych wyników zastosowano test t-Studenta dla zmiennych niezależnych oraz analizę korelacji i regresji prostoliniowej. Wyniki rozdziału leukocytów uzyskane z systemu EasyCell wykazywały dobrą korelację z wynikami otrzymanymi z analizy mikroskopowej. Najwyższe współczynniki korelacji uzyskano w odniesieniu do populacji limfocytów, neutrofili i eozynofilii. System EasyCell może stanowić pomocne narzędzie wykorzystywane w różnicowaniu leukocytów w próbkach rutynowych i ewentualnie w monitorowaniu chorób rozrostowych.

EN

The aim of the study was to evaluate the comparability of white blood cell differential obtained from EasyCell and the microscopic method. The peripheral blood samples from adults (n = 90), children (n = 52) and haematological patients (n = 110) were used. Linear regression analysis and t-Student test were used to compare the obtained results. The results of blood leukocyte distribution from the EasyCell system showed a good correlation with the results obtained from the microscopic analysis. The highest correlation coefficients were obtained for the lymphocytes, neutrophils and eosinophiles. The EasyCell system can be a helpful tool for leukocyte differentiation in routine samples and possibly for the monitoring of proliferative diseases.

3

Peripheral blood smear analysis using image processing approach for diagnostic purposes: A review

Hegde R. B., Prasad K., Hebbar H., Sandhya I.

Biocybernetics and Biomedical Engineering

|

2018

|

Vol. 38, no. 3

467--480

EN

Peripheral blood smear analysis is a common practice to evaluate health status of a person. Many disorders such as malaria, anemia, leukemia, thrombocytopenia, sickle cell anemia etc., can be diagnosed by evaluating blood cells. Many groups have reported methods to automate blood smear analysis for detection of specific disorders for diagnostic purposes. In this paper,we have summarized the methods used to analyze peripheral blood smears using image processing techniques. We have categorized these methods into three groups based on approaches such as WBC analysis, RBC analysis and platelet analysis. We conclude that there is a need for a method of automation to match with human evaluation process and rule out any abnormality present in the blood smear. It is desirable for studies on automation of peripheral blood smear analysis to focus on development of robust method to handle illumination and color shade variations. Also, it is desirable to design a method which could collect all the abnormal regions from all views of a specimen to limit the manual evaluation to those regions making it more feasible for telemedicine applications.