METHODS: The proposed method uses a 2D contourlet transform and a set of texture features that are efficiently extracted from the transformed image. Then, the combination of a kernel discriminant analysis (KDA)-based feature reduction technique and analysis of variance (ANOVA)-based feature ranking technique was used, and the images were then classified into various stages of liver fibrosis.

RESULTS: Our 2D contourlet transform and texture feature analysis approach achieved a 91.46% accuracy using only four features input to the probabilistic neural network classifier, to classify the five stages of liver fibrosis. It also achieved a 92.16% sensitivity and 88.92% specificity for the same model. The evaluation was done on a database of 762 ultrasound images belonging to five different stages of liver fibrosis.

CASE PRESENTATION: A 23-year-old trauma patient with closed fracture of left femoral shaft and left humerus presented to our emergency department (ED). 11 h after admission to ED, patient became confused, hypoxic and hypotensive. He was then intubated for respiratory failure and mechanically ventilated. Transesophageal ultrasound revealed hyperdynamic heart, dilated right ventricle with no regional wall abnormalities and no major aorta injuries. Whole-body computed tomography was normal. During central venous cannulation of right internal jugular vein (IJV), we found free floating mobile hyperechoic spots, located at the anterior part of the vein. A diagnosis of fat embolism syndrome later was made based on the clinical presentation of long bone fractures and fat globulin in the blood. Despite aggressive fluid resuscitation, patient was a non-responder and needed vasopressor infusion for persistent shock. Blood aspirated during cannulation from the IJV revealed a fat globule. Patient underwent uneventful orthopedic procedures and was discharged well on day 5 of admission.