Fuzzy-Inspired Biosensing Strategy for Double-Feature Tumor Classification

This paper proposes a novel fuzzy-inspired biosensing strategy for contrast-enhanced tumor classification by using multiple features of the disease. Specifically, the proposed strategy considers two features of breast cancers, i.e., tissue malignancy and distance between cancerous cells, to determine the cancer status through the fuzzy relation transfer analysis. The analysis enables an intuitive yet systematic way to characterize the variation of classification fuzziness occurred in the biosensing process when nanoscale materials are utilized as contrast agents. Subsequently, root-mean-square-error of the membership function is introduced to evaluate the sensing integrity. Finally, numerical results are presented to demonstrate the principles of the proposed strategy.