Tuncer Ergin

Automated segmentation of the injured spleen

PurposeTo develop a novel automated method for segmentation of the injured spleen using morphological properties following abdominal trauma. Average attenuation of a normal spleen in computed tomography (CT) does not vary significantly between subjects. However, in the case of solid organ injury, the shape and attenuation of the spleen on CT may vary depending on the time and severity of the injury. Timely assessment of the severity and extent of the injury is of vital importance in the setting of trauma.MethodsWe developed an automated computer-aided method for segmenting the injured spleen from CT scans of patients who had splenectomy due to abdominal trauma. We used ten subjects to train our computer-aided diagnosis (CAD) method. To validate the CAD method, we used twenty subjects in our testing group. Probabilistic atlases of the spleens were created using manually segmented data from ten CT scans. The organ location was modeled based on the position of the spleen with respect to the left side of the spine followed by the extraction of shape features. We performed the spleen segmentation in three steps. First, we created a mask of the spleen, and then we used this mask to segment the spleen. The third and final step was the estimation of the spleen edges in the presence of an injury such as laceration or hematoma.ResultsThe traumatized spleens were segmented with a high degree of agreement with the radiologist-drawn contours. The spleen quantification led to

Detection of injured kidney in computed tomography

86\pm 5\,\%

Assessment of similarity rates of liver images using geometric transformations

86±5% volume overlap,

Automatic segmentation of small intestine in computed tomography scans

92.5\pm 3.11\,\%

Automated segmentation of the injured liver

92.5±3.11% Dice similarity index,