An Adaptive Multi-channel Feature-fusion Model for Polyp Classification

Extracting effective texture features from computed tomographic colonography (CTC) and merging them to form a much powerful descriptor are two critical challenges in computer-aided detection (CADe) and diagnosis (CADx). In this paper, we introduce multi-scaling analysis into grey level co-occurrence matrix (GLCM) to construct texture features from different image domains, i.e. intensity, gradient and curvature. Thus, nine texture descriptors are generated and form a descriptor pool sorted by AUC (area under the curve of receiver operating characteristics) scores. Then an adaptive feature merging method is designed and implemented in a binary tree framework where every layer consists of two nodes, i.e. the baseline descriptor and its complement which are always the first two descriptors in the descriptor pool. Their merging will be performed using forward stepwise method where some complementary variables with gains in classification are preserved. After feature merging, the descriptor pool will be updated by removing the two candidates and adding the new baseline descriptor. This procedure will be performed iteratively until the final descriptor is obtained. Obviously, this is a greedy procedure which guarantees the monotonicity of the classification. Experimental outcomes testify the effectiveness of this method and the proposed method outperforms the pre-merging descriptor over 4% by AUC scores.