Introduction
Pulmonary tree supplying the lungs with air and blood and consists of three main structures: the bronchial tree, the pulmonary artery (PA) tree, and pulmonary vein (PV) tree. Bronchial tree supplies the lungs with air, but starting from the trachea, main bronchus divides into left and right. PA tree supplying the left lung and right with oxygen-poor blood. Tree PV carry oxygen-rich blood from the capillaries in the lungs back to the heart.
Pulmonary embolism (PE) is a condition where one or more of the pulmonary artery has been (partially) blocked. This occlusion is usually caused by blood clots, also known as thrombi, originating either from the venous circulation or the right side of the heart, but can also be caused by a tumor that attacks the circulatory system, or other foreign sub-stance.
Lung Anatomy
(Shows the bronchial tree, the PA tree, and trees PV)
The immediate result is partial or complete obstruction of blood flow to the lungs. Blockade results in the sector of the ventilated lung, but not perfusion. If a large embolus occludes pulmonary artery, the patient suffered from acute respiratory distress and may die within a few minutes; sized embolus may block the artery where the blood supply to bronchopulmonary segment produces thrombotic infarction (area of dead tissue).
CT image slices showing embolus
in the pulmonary artery trunk
Latest standard for diagnosing PE is a multi-detector computed tomographic angiography (CTA). With this technique, pulmonary vascular tree is imaged using computed tomography (CT) in combination with iodinated contrast agent. This makes the PA tree is clearly distinguished from its surroundings. PE A later characterized as a dark spot on a sunny boat.
Thesis Statement
Although CTA has been shown to improve accuracy of diagnosis of PE, also introduce new problems. Because radiologists are faced with a large amount of anatomical information, analyzing data from both time consuming and subject to human error.
In literature, several methods for automatic (computer-CAD) detection of PE has been proposed. This method uses the fact that in an occlusive arterial CTA data will be marked with dark spots in the arteries clear.
Recently, a quantification method was developed by ED Qanadli et al. [1] evaluated by a.s. Wu et al. [2] by connecting it with the death of patients in PE settings. We decided to follow this approach, because this is the only clinical method for the quantification was evaluated at the time of PE. Also, semi-automatic quantification of PE seems to be a field that is relatively not examined at this time.
Index quantification by E.D. Qanadli combine stenosis severity of the pulmonary artery and the relative position of the PA tree. To automate this process so we need two types of information:
Size occlusion
because of the thrombus.
The position of thrombus in the PA tree.
To come up with this type of information, PA must first segmented tree. From the segmented tree volume, the bifurcations can be detected so that the tree model can be built. Also, the PE should be detected. Because research has been done in a particular field (eg [5]), we chose to pay attention to it and less rough implement measures in the first period project.
A standard PA model tree
shows the congestion area
Thesis Project
Quantification of PE in CT data is currently carried out by visual inspection and is associated with significant analysis time and prone to human error. To realize the automatic quantification of PE according to the index Qanadli, automatic extraction of the location of the 20 arterial segments is needed. In this research project, we propose to come up with a tool, which automatically extracts the location of this segment has a model of segmented binary tree as input.
Summary of the proposed method
Because the anatomical knowledge about the segmented branches needed to calculate the number of subsegments affected, we propose to take this position using the procedure in accordance with the standard model.






