Intelligent Computation and Precise Measurement of DNA Content in Cell Nucleus: A Calibration Approach Based on Morphology and Support Vector Regression

In the study of quantitative cytology, the measurement of the DNA content in cell nuclear is the most important basis and necessary premise of cancer screening and diagnosis. Due to some unavoidable factors, certain errors may occur in the measurement of the DNA content through processing and analysis of the cell nuclei image. A new calibration approach based on morphology and SVR regression algorithm was proposed. Through spatial and optical calibration, the approach sufficiently utilized the information hidden in the images and features of the cell nucleus. The experiment showed that the approach could increase the measurement accuracy significantly, and show positive significance in improving the specificity and sensitivity of the pathological diagnosis.