Sequential Monte Carlo tracking of the marginal artery by multiple cue fusion and random forest regression

• We formulate vessel detection on contrast-enhanced computed tomography angiogram images as a Bayesian tracking problem.
• A new vessel detection method by fusing multiple cues extracted from CT images.
• Use of colon atlas and random forest to prune tracking results and reduce false positives.
• Our proposed method showed a significant increase in the F1 score when compared to the traditional Hessian vesselness method.

Given the potential importance of marginal artery localization in automated registration in computed tomography colonography (CTC), we have devised a semi-automated method of marginal vessel detection employing sequential Monte Carlo tracking (also known as particle filtering tracking) by multiple cue fusion based on intensity, vesselness, organ detection, and minimum spanning tree information for poorly enhanced vessel segments. We then employed a random forest algorithm for intelligent cue fusion and decision making which achieved high sensitivity and robustness. After applying a vessel pruning procedure to the tracking results, we achieved statistically significantly improved precision compared to a baseline Hessian detection method (2.7% versus 75.2%, p < 0.001). This method also showed statistically significantly improved recall rate compared to a 2-cue baseline method using fewer vessel cues (30.7% versus 67.7%, p < 0.001). These results demonstrate that marginal artery localization on CTC is feasible by combining a discriminative classifier (i.e., random forest) with a sequential Monte Carlo tracking mechanism. In so doing, we present the effective application of an anatomical probability map to vessel pruning as well as a supplementary spatial coordinate system for colonic segmentation and registration when this task has been confounded by colon lumen collapse.

Figure optionsDownload high-quality image (101 K)Download as PowerPoint slide