Dual contrastive learning for incomplete multiview clustering on enhanced liver tumor CT diagnosis

Incomplete multi-view clustering (IMVC) for liver tumor CT images provide common and complementary information, that essential to support liver tumor diagnosis of without labeling. These IMVC techniques still have two problems, though: 1) they only heed the following to the resemblance between the same samples of different views, ignoring the resemblance between different samples of the same view, which can provide more information for liver tumor diagnose; 2) most of the existing diagnostic processes are staged, greatly increasing the cost of time. We suggest a solution to these problems by a dual contrastive learning framework to learning mutual information from cross-view contrast learning and intra-view contrast learning at the same time. On this basis, the cosine similarity between views is constructed using positive and negative samples from these dual contrastive learning, and the whole process is carried out synchronously. In this paper, two multi-view liver tumor data sets are compared with 4 methods in recent years, indicating that this method is the most advanced.