Level Set-based Liver Image Segmentation with Watershed and ANN Classiﬁer
I. Ghali, Neveen
Hassanien, Aboul Ella
MetadataShow full item record
The objective of this paper is to evaluate a new com- bined approach intended for reliable CT liver image segmentation to separate the liver from other organs and segment the liver into set of regions of interest (ROIs). The approach combines the level set with watershed approach used as post segmentation step to produce a reliable segmentation result. Features of ﬁrst order statistics and grey-level co-occurrence matrix, are calculated and passed to an artiﬁcial neural network to be trained and classify lesion ROIs. Filtering is used before the segmentation approach to enhance contrast, remove noise and emphasize certain features as well as connecting ribs around the liver. To evaluate the performance of presented approach, we present tests on different CT liver images. The experimental results obtained, show that the overall accuracy offered by the proposed approach is 0.921% in segmenting CT liver images into set of regions even with noise, and 0.889% average accuracy for neural network classiﬁcation.
- Articles