Identification of geometrical features of cell surface responsible for cancer aggressiveness: Machine learning analysis of atomic force microscopy images.

It has been recently demonstrated that atomic force microscopy (AFM) allows for rather precise identification of malignancy of cells. An example of human colorectal epithelial cells imaged in AFM Ringing mode has demonstrated the ability to distinguish cells with different cancer aggressiveness with the help of machine learning (ML). The ML methods traditionally analyze the entire image. The problem with such an approach is the lack of information about which features of the cell surface are associated with the high aggressiveness of the cells. Here we suggest a machine learning approach to overcome this problem and reveal the geometry of features on the cell surface associated with cancer aggressiveness.