Knowledge-based segmentation of pediatric kidneys in CT for measurement ofparenchymal volume

Purpose: The purpose of this work was to develop an automated method for se gmenting pediatric kidneys in helical CT images and measuring their volume. Method: An automated system was developed to segment the kidneys. Parametri c Features of anatomic structures were used to guide segmentation and label ing of image regions. Kidney volumes were calculated by summing included vo xels. For validation, the kidney volumes of four swine were calculated usin g our approach and compared with the "true" volumes measured after harvesti ng the kidneys. Automated volume calculations were also performed in a coho rt of nine children. Results: The mean difference between the calculated and measured values in the swine kidneys was 1.38 mi. For the pediatric cases, calculated volumes ranged from 41.7 to 252.1 ml/kidney, and the mean ratio of right to left ki dney volume was 0.96. Conclusion: These results demonstrate the accuracy of a volumetric techniqu e that may in the future provide an objective assessment of renal damage.