Абстрактный

Vector Field Convolution for Segmentation and Measurement of Pleural Effusion

B.S.Lijin, S. Malathi, G. Arun Kumar, S.ManiKandan

Pleural effusion is a vital biomarker for the diagnosis of many diseases. A pleural effusion is an anomalous amount of fluid around the lung that can result from many medical conditions. In this paper, an improved automated method is implemented to evaluate pleural effusion on CT scan and prohibitively time consuming when performed manually. The proposed method is based on parietal pleura extraction and visceral pleura extraction and active contour external force using vector field convolution for image segmentation along with region growing and Bezier surface fitting and deformable surface modeling .Twelve CT scans with three manual segmentation were used to evaluate the automatic segmentation method. The visceral assessment estimated 85% cases with negligible or small segmentation errors 13% with medium errors and 2% with large errors.