Atomic Force Microscopy Detects the Difference in Cancer Cells of Different Neoplastic Aggressiveness via Machine Learning

Abstract

A novel method based on atomic force microscopy (AFM) working in Ringing mode (RM) to distinguish between two similar human colon epithelial cancer cell lines that exhibit different degrees of neoplastic aggressiveness is reported on. The classification accuracy in identifying the cell line based on the images of a single cell can be as high as 94% (the area under the receiver operating characteristic [ROC] curve is 0.99). Comparing the accuracy using the RM and the regular imaging channels, it is seen that the RM channels are responsible for the high accuracy. The cells are also studied with a traditional AFM indentation method, which gives information about cell mechanics and the pericellular coat. Although a statistically significant difference between the two cell lines is also seen in the indentation method, it provides the accuracy of identifying the cell line at the single‐cell level less than 68% (the area under the ROC curve is 0.73). Thus, AFM cell imaging is substantially more accurate in identifying the cell phenotype than the traditional AFM indentation method. All the obtained cell data are collected on fixed cells and analyzed using machine learning methods. The biophysical reasons for the observed classification are discussed.

Cell mechanics can be robustly derived from AFM indentation data using the brush model: error analysis

“…30 Furthermore, the use of a novel AFM imaging mode, named Ringing mode, allowed to separate two similar cell lines of human colorectal epithelial cancer of different aggressiveness based on the use of images of the cell surface. 31 The brush model was suggested to find the effective Young's modulus of the cell body, which is covered with the PB layer, through the analysis of the force curves collected in AFM indentation experiments. The model takes into account the presence of the non-Hertzian behavior of the PB layer.…”

Advances in tissues and cells characterization by Raman micro‐spectroscopy, atomic force microscopy, and tip‐enhanced Raman spectroscopy

“…[ 65 ] It has been applied in studies of ocular surfaces and tissue engineering in the visual science field [ 66 ] and even in cancer research. It has already been used for characterization of breast tissue tissues, [ 67 ] bladder cancer detection, [ 68 ] differentiation of human colon cancer epithelial cells with varying neoplastic aggressiveness, [ 69 ] evaluation of cell adhesiveness and elasticity, [ 70 ] studying mechanical properties of cancerous cells, [ 71,72 ] and measurement of viscoelasticity of cancer cells in comparison with healthy cells. [ 73,74 ] Imaging in fluids, including physiological buffers, and compiling dynamic data are possible tasks using AFM.…”

Correlation of cell mechanics with the resistance to malignant transformation in naked mole rat fibroblasts

“…38 Furthermore, it has been demonstrated that the cell surface can be substantially changed as a result of genetic alterations. 39…”

“…38 Furthermore, it has been demonstrated that the cell surface can be substantially changed as a result of genetic alterations. 39 In this work, we use the AFM technique to measure the physical properties of NMR and mouse fibroblasts in response to malignant transformations induced by LT oncoproteins and the Ras oncogene. Indentation force curves were collected with AFM.…”