Segmentation Of Sonicated Blood Cells And Ultrasound Contrast Agent Microbubbles From Time-lapse Microscopic Images

Biomedical Engineering Project Topics

Get the Complete Project Materials Now! »

Blood cells and ultrasound contrast agent microbubbles behave strangely when subjected tornan ultrasound field. They migrate towards the nodes of the ultrasound wave and form circularrnpatterns. However, differentiation between blood cells and ultrasound contrast agentrnmicrobubbles can be easily determined via time-lapse analysis of the pattern formation. Ultrasoundrncontrast agent microbubbles migrate towards the wave nodes very quickly andrnform tightly packed clusters. In contrast, formation of tightly packed clusters in the case ofrnblood cells is unlikely based on the sonophore model theory of cells. Moreover, the interactionrnof the microbubbles with the blood cells and the surrounding medium is not fully understood.rnTo study the behavior and interaction of sonicated blood cells and microbubblesrnon the time-lapse microscopic images, there is a need to define a contour around the cellsrnand the microbubbles. To do so, first, the microbubbles and the cells should be segmentedrnfrom the rest of image content. In this regard, this thesis devised a scheme that combines featuresrnof the Laplacian of the Gaussian detector and a modified form of the Contrast LimitedrnAdaptive Histogram Equalization (CLAHE) technique for effective analysis of time-lapsernmicroscopic images. The scheme is tested on three datasets (one synthetic and two real) andrnits subjective and objective performance is found quite pleasing. Absence of ground truthrnfor the real datasets makes the evaluation of the segmentation scheme merely subjective.rnObjective evaluation is only performed on the computer-simulated time-lapse images. Thernaverage segmentation sensitivity, specificity and accuracy of the proposed algorithm are valuedrnaround 0.96, 0.91 and 0.95 on the synthetic dataset out of a unit scale, respectively. Thernresult generated could be a crucial input for effective particle tracking and sizing studies.

Get Full Work

Report copyright infringement or plagiarism

Be the First to Share On Social



1GB data
1GB data

RELATED TOPICS

1GB data
1GB data
Segmentation Of Sonicated Blood Cells And Ultrasound Contrast Agent Microbubbles From Time-lapse Microscopic Images

216