No abstract

In this study, a novel computer-aided detection (CAD) method is introduced to detect pulmonary embolism (PE) in computed tomography angiography (CTA) images. This method consists of lung vessel segmentation, PE candidate detection, feature extraction, feature selection and classification of PE. PE candidates are determined in lung vessel tree. Then, feature extraction is carried out based on morphological properties of PEs. Stepwise feature selection method is used to find the best set of the features. Artificial neural network (ANN), k-nearest neighbours (KNN) and support vector machines (SVM) are used as classifiers. The CAD system is evaluated for 33 CTA datasets with 10 fold cross-validation. The sensitivities of these classifiers are obtained as 98.3 %, 57.3 % and 73 % at 10.2, 5.7 and 8.2 false positives per dataset respectively.

Our CAD method robustly segments the spleen in the presence of morphological changes such as laceration, contusion, pseudoaneurysm, active bleeding, periorgan and parenchymal hematoma, including subcapsular hematoma due to abdominal trauma. CAD of the splenic injury due to abdominal trauma can assist in rapid diagnosis and assessment and guide clinical management. Our segmentation method is a general framework that can be adapted to segment other injured solid abdominal organs.

To the best of our knowledge, the novel polyp candidate detection system which determines polyp candidates with LoG filters is one of the main contributions. We also propose a new 2D projection image calculation scheme to determine the distinctive features. We believe that our CAD system is highly effective for assisting radiologist interpreting CT.

No abstract