Automated Cancer Subtyping via Vector Quantization Mutual Information Maximization. (arXiv:2206.10801v1 [cs.LG])

Web: http://arxiv.org/abs/2206.10801

Cancer subtyping is crucial for understanding the nature of tumors and
providing suitable therapy. However, existing labelling methods are medically
controversial, and have driven the process of subtyping away from teaching
signals. Moreover, cancer genetic expression profiles are high-dimensional,
scarce, and have complicated dependence, thereby posing a serious challenge to
existing subtyping models for outputting sensible clustering. In this study, we
propose a novel clustering method for exploiting genetic expression profiles
and distinguishing subtypes in an unsupervised manner. The proposed …

arxiv cancer information lg quantization vector