Abstract
Segmentation is one of the most important parts of medical image processing. Manual segmentation is very cumbersome and time-consuming. Fully automatic segmentation approaches require a large amount of labeled training data and may fail in difficult cases. In this paper, we propose a new method for 2-D segmentation and 3-D interpolation. The Smart Brush functionality quickly segments the ROI in a few 2-D slices. Given these annotated slices, our adapted formulation of Hermite Radial Basis Functions reconstructs the 3-D surface. Effective interactions with less number of equations accelerate the performance and therefore, a real-time and an intuitive, interactive segmentation can be supported effectively. The proposed method was evaluated on 12 clinical 3-D MRI data sets from individual patients and were compared to gold standard annotations of the left ventricle from a clinical expert. The 2-D Smart Brush resulted in an average Dice coefficient of \(0.88\pm 0.09\) for individual slices. For the 3-D interpolation using Hermite Radial Basis Functions an average Dice coefficient of \(0.94\pm 0.02\) was achieved.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call