Search

Recently, the optimal surface finding (OSF) and layered optimal graph image segmentation of multiple objects and surfaces (LOGISMOS) approaches have been reported with applications to medical image segmentation tasks. While providing high levels of performance, these approaches may locally fail in the presence of pathology or other local challenges. Due to the image data variability, finding a suitable cost function that would be applicable to all image locations may not be feasible. This paper presents a new interactive refinement approach for correcting local segmentation errors in the automated OSF-based segmentation. A hybrid desktop/virtual reality user interface was developed for efficient interaction with the segmentations utilizing state-of-the-art stereoscopic visualization technology and advanced interaction techniques. The user interface allows a natural and interactive manipulation of 3-D surfaces. The approach was evaluated on 30 test cases from 18 CT lung datasets, which showed local segmentation errors after employing an automated OSF-based lung segmentation. The performed experiments exhibited significant increase in performance in terms of mean absolute surface distance errors (2.54±0.75mm prior to refinement vs. 1.11±0.43mm post-refinement, p ≪0.001). Speed of the interactions is one of the most important aspects leading to the acceptance or rejection of the approach by users expecting real-time interaction experience. The average algorithm computing time per refinement iteration was 150ms, and the average total user interaction time required for reaching complete operator satisfaction was about 2min per case. This time was mostly spent on human-controlled manipulation of the object to identify whether additional refinement was necessary and to approve the final segmentation result. The reported principle is generally applicable to segmentation problems beyond lung segmentation in CT scans as long as the underlying segmentation utilizes the OSF framework. The two reported segmentation refinement tools were optimized for lung segmentation and might need some adaptation for other application domains.

We present a highly automated approach to obtain detailed structural models of airway trees from ex vivo porcine lung tissue imaged with a high resolution micro-CT scanner. Such information is an important prerequisite to systematically study models of lung disease that affect airway morphology. The method initially identifies all tubular airway-like structures in the lung. In a second processing step, these structures are grouped into a connected airway tree by utilizing prior knowledge about the airway trees branching pattern. The method was evaluated on 12 micro-CT scans from four tracheal lobes of piglets imaged at three different inflation levels. For this study, two control piglets and two cystic fibrosis piglets were used. For systematic validation of our approach, an airway nomenclature was developed for the pig airway tree. Out of more than 3500 airway tree segments assessed during evaluation, 88.45% were correctly identified by the method. No false positive airway branches were found. A detailed performance analysis for different airway tree hierarchy levels, lung inflation levels and piglets with/without cystic fibrosis is presented in the paper.