Figure 2.23: Tissue characterization results: (b), (d), and (f) White labels soft plaque, dark gray areas are displayed where calcium plaques are located, and light gray areas labels hard plaque. (a), (c), and (e) Original images.

accumulation local moments are good descriptors of the different kind of plaque tissues. However, local binary patterns and accumulation local moments are also fast, in terms of low-time processing. On the other hand, the classification of the feature data is a critical step. Different approaches to the classification problem are described and proposed as candidates in our framework. We proved that k-nearest neighbor method gives the best performance as a classifier. But, ML and methods based on an ensemble of classifiers have high discrimination rate and lower classification time. Therefore, two real-time or near-real-time approaches are proposed: The first method combines local binary patterns with ML methods. The second method uses accumulation local moments and boosting techniques.

In conclusion, we have presented a general fully automatic and real-time or near-real-time framework with high accuracy plaque recognition rate for tissue characterization in IVUS images.

0 0

Post a comment