Automatic segmentation and analysis of the main pulmonary artery on standard post-contrast CT studies using iterative erosion and dilation

Abstract

Purpose

To describe an algorithm for the accurate segmentation of the main pulmonary artery (MPA) and determining its length, mid-cross-sectional area and mid-circumferential perimeter. This will help with accurate, rapid and reproducible MPA measurements which can be used to detect diseases that cause raised pulmonary arterial pressure, and allow standardized serial measurements to assess progression or response to treatment.

Method

We perform MPA segmentation using a novel approach based on erosion and dilation. A centerline is then determined by skeletonization, graph construction and spline fitting. MPA cross sections perpendicular to the centerline are analyzed in order to determine MPA length, and mid-cross-sectional area and perimeter. The technique was developed using four normal chest CT data sets and then tested on twenty normal post-contrast chest CT studies. Results are compared to manual segmentation and measurement by a thoracic radiologist.

Results

The mean MPA length, mid-cross-sectional area and mid-circumferential perimeter of the twenty test data sets, calculated by our algorithm, are 43.6 $\pm$ 9.2 mm, 552.9 $\pm$ 132.4$\hbox { mm}^{2}$ and $86.0 \pm 10.5\hbox { mm}$, respectively, compared with $41.3 \pm 5.9\hbox { mm}, 574.1 \pm 124.2\hbox { mm}^{2}$ and $99.7 \pm 12.1\hbox { mm}$ obtained manually by the radiologist. Our technique shows high correlation with the manually determined parameters for both mid- cross-sectional area ($R = 0.96$) and length ($R = 0.93$), and good correlation for mid-circumferential perimeter ($R = 0.87$).

Conclusion

Our algorithm is a robust accurate automated method for obtaining measurements of the MPA. This allows a more standardized method for determining length, and mid- cross-sectional area/perimeter and therefore allows more accurate comparison of MPA measurements.