scholarly journals Strategies for Rare-Event Detection: An Approach for Automated Fetal Cell Detection in Maternal Blood

1998 ◽  
Vol 63 (6) ◽  
pp. 1783-1792 ◽  
Author(s):  
Jan C. Oosterwijk ◽  
Cecile F.H.M. Knepflé ◽  
Wilma E. Mesker ◽  
Hans Vrolijk ◽  
Willem C.R. Sloos ◽  
...  
Cytometry ◽  
1998 ◽  
Vol 32 (3) ◽  
pp. 178-185 ◽  
Author(s):  
Jan C. Oosterwijk ◽  
Wilma E. Mesker ◽  
Maria C.M. Ouwerkerk-van Velzen ◽  
Cecile F.H.M. Knepfl� ◽  
Karien C. Wiesmeijer ◽  
...  

Author(s):  
L. Serradell ◽  
J.-M. Dupont ◽  
F. Ferr� ◽  
D. Rabineau ◽  
P. Cornet

1998 ◽  
Vol 18 (10) ◽  
pp. 1014-1022 ◽  
Author(s):  
Beatrice Orsetti ◽  
Genevieve Lefort ◽  
Pierre Boulot ◽  
Brigitte Andreo ◽  
Franck Pellestor

2020 ◽  
Vol 39 (6) ◽  
pp. 8463-8475
Author(s):  
Palanivel Srinivasan ◽  
Manivannan Doraipandian

Rare event detections are performed using spatial domain and frequency domain-based procedures. Omnipresent surveillance camera footages are increasing exponentially due course the time. Monitoring all the events manually is an insignificant and more time-consuming process. Therefore, an automated rare event detection contrivance is required to make this process manageable. In this work, a Context-Free Grammar (CFG) is developed for detecting rare events from a video stream and Artificial Neural Network (ANN) is used to train CFG. A set of dedicated algorithms are used to perform frame split process, edge detection, background subtraction and convert the processed data into CFG. The developed CFG is converted into nodes and edges to form a graph. The graph is given to the input layer of an ANN to classify normal and rare event classes. Graph derived from CFG using input video stream is used to train ANN Further the performance of developed Artificial Neural Network Based Context-Free Grammar – Rare Event Detection (ACFG-RED) is compared with other existing techniques and performance metrics such as accuracy, precision, sensitivity, recall, average processing time and average processing power are used for performance estimation and analyzed. Better performance metrics values have been observed for the ANN-CFG model compared with other techniques. The developed model will provide a better solution in detecting rare events using video streams.


PLoS ONE ◽  
2018 ◽  
Vol 13 (12) ◽  
pp. e0208508 ◽  
Author(s):  
M. Rohan Fernando ◽  
Chao Jiang ◽  
Gary D. Krzyzanowski ◽  
Tifany Somer-Shely ◽  
Wayne L. Ryan

2000 ◽  
Vol 183 (2) ◽  
pp. 462-468 ◽  
Author(s):  
Ossie Geifman-Holtzman ◽  
Fadi Makhlouf ◽  
Lydia Kaufman ◽  
Nick J. Gonchoroff ◽  
Eli J. Holtzman

2002 ◽  
Vol 17 (2) ◽  
pp. 83-89 ◽  
Author(s):  
Ralph M. Bohmer ◽  
Helene P. Stroh ◽  
Kirby L. Johnson ◽  
Erik S. LeShane ◽  
Diana W. Bianchi

Blood ◽  
2010 ◽  
Vol 116 (21) ◽  
pp. 4406-4406
Author(s):  
Joyce Overfield, and Pei ◽  
Lun Karen Lim

Abstract Abstract 4406 Methods of quantification of foetal red cell in maternal blood samples are important to ensure the correct administration of prophylactic anti-D to prevent sensitisation of the mother which may result in haemolytic disease of the newborn and foetus in subsequent pregnancies. We aimed to assess the accuracy of 3 methods: a gel card technique using anti-D and 2 acid-elution techniques, foetal cell detection kit (FCD, Inverclyde Biologicals Lanarkshire, Scotland) and a kit from Clin-Tech Limited (Guildford, England) based on the Kleihauer-Betke foetal stain technique (KBT), to quantifiy foetal red cells in maternal samples. The sensitivity of the gel method was also assessed. A total of 63 maternal blood samples and 30 man-made control blood samples were analysed, with only 57 maternal samples confirmed to be Rh D negative. Rh D positive samples were excluded. All samples were run concurrently with the 3 methods, according to manufacturers’ instructions. Mann Whitney test was used to compare the results. The gel technique was recorded in terms of grading of agglutination while the acid-elution kits were recorded by degree of FMH (mL). Column agglutination was also used to assess sensitivity. Results showed only 3 maternal samples were positive for FMH using the acid-elution method but not the gel technique. Statistically there was no significant difference between the techniques (Mann-Whitney test). Sensitivity of the gel method showed that it has the ability to detected FMH of more than 3mL whilst the 2 kits were able to detect FMH of 1mL. The study showed that gel technique required little skill to perform but it was not considered suitable for accurate quantification of FMH and consequently for the correct administration of prophylactic anti-D. The foetal cell detection kit (Inverclyde Biologicals) showed a similar ability to detect and quantify FMH when compared to the Kleihauer –Betke kit (Clin-Tech) with better overall staining intensity. The Kleihauer-Betke test from Clin-Tech and the foetal cell detection kit from Inverclyde Biologicals showed no significant difference (p = 0.98), thus there is no statistical significant difference between the 2 methods. However, the sensitivity of the column agglutination method was lower, as significant agglutination could only be observed with FMH of more than 3mL. The expected values were plotted based on Gomez-Arbones et al (2002), who cited significant agglutination seen when FMH is 0.1% or about 2.5mL. Sensitivity was found to be less than expected as a higher amount of bleed is required to observed significant agglutination. The FMH sample representing 1–6mL was repeated and similar findings were recorded, as significant agglutination was only observed when FMH was 4mL. The column agglutination method is not suitable as a quantitative measurement of FMH as it only allows qualitative analysis, thus if it is incorporated into a clinical setting, it must be accompanied by a quantitative test. The foetal cell detection kit has similar staining capabilities to detect foetal cells and compared to Clin-Tech was easier to use as there is no need to prepare eluting solution unlike the latter. However, fixing solution was not provided and hence need to be prepared. Results showed that only 3 maternal samples were positive for the presence of FMH and thus using a semi-quatitative acid-elution technique should be sufficient in FMH quantification unless FMH using the acid-elution technique exceeds 2mL, as recommende,d by the BCSH guidelines (2009), then the sample should be analysed using flow cytometry. Acknowledgments: Central Manchester Hospitals Transfusion Laboratory for the provision of blood samples. Performed as part of MSc Biomedical Science project, funded by Mancheste Metropolitan University. Disclosures: No relevant conflicts of interest to declare.


Sign in / Sign up

Export Citation Format

Share Document