Classification of Breast Cancer Cells Using the Integration of High-Frequency Single-Beam Acoustic Tweezers and Convolutional Neural Networks

Single-beam acoustic tweezers (SBAT) is a widely used trapping technique to manipulate microscopic particles or cells. Recently, the characterization of a single cancer cell using high-frequency (>30 MHz) SBAT has been reported to determine its invasiveness and metastatic potential. Investigation of cell elasticity and invasiveness is based on the deformability of cells under SBAT’s radiation forces, and in general, more physically deformed cells exhibit higher levels of invasiveness and therefore higher metastatic potential. However, previous imaging analysis to determine substantial differences in cell deformation, where the SBAT is turned ON or OFF, relies on the subjective observation that may vary and requires follow-up evaluations from experts. In this study, we propose an automatic and reliable cancer cell classification method based on SBAT and a convolutional neural network (CNN), which provides objective and accurate quantitative measurement results. We used a custom-designed 50 MHz SBAT transducer to obtain a series of images of deformed human breast cancer cells. CNN-based classification methods with data augmentation applied to collected images determined and validated the metastatic potential of cancer cells. As a result, with the selected optimizers, precision, and recall of the model were found to be greater than 0.95, which highly validates the classification performance of our integrated method. CNN-guided cancer cell deformation analysis using SBAT may be a promising alternative to current histological image analysis, and this pretrained model will significantly reduce the evaluation time for a larger population of cells.

[1]  Chi Woo Yoon,et al.  Acoustic tweezers for studying intracellular calcium signaling in SKBR-3 human breast cancer cells. , 2015, Ultrasonics.

[2]  M. S. Yousafzai,et al.  Investigation into local cell mechanics by atomic force microscopy mapping and optical tweezer vertical indentation , 2016, Nanotechnology.

[3]  Changyang Lee,et al.  Calibration of sound forces in acoustic traps , 2010, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[4]  R. Chow,et al.  Calibration of Trapping Force on Cell-Size Objects From Ultrahigh-Frequency Single-Beam Acoustic Tweezer , 2016, IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control.

[5]  Euan McLeod,et al.  Fundamental Limits of Optical Tweezer Nanoparticle Manipulation Speeds. , 2018, ACS nano.

[6]  Norman Zerbe,et al.  Distributed computing in image analysis using open source frameworks and application to image sharpness assessment of histological whole slide images , 2011, Diagnostic pathology.

[7]  C. Lim,et al.  AFM indentation study of breast cancer cells. , 2008, Biochemical and biophysical research communications.

[8]  Qifa Zhou,et al.  Multifunctional single beam acoustic tweezer for non-invasive cell/organism manipulation and tissue imaging , 2016, Scientific Reports.

[9]  Changyang Lee,et al.  A simple method for evaluating the trapping performance of acoustic tweezers. , 2013, Applied physics letters.

[10]  H. Kessler,et al.  Cellular unbinding forces of initial adhesion processes on nanopatterned surfaces probed with magnetic tweezers. , 2006, Nano letters.

[11]  K. Shung,et al.  Characterizing Deformability of Drug Resistant Patient-Derived Acute Lymphoblastic Leukemia (ALL) Cells Using Acoustic Tweezers , 2018, Scientific Reports.

[12]  Min Gon Kim,et al.  Label-free analysis of the characteristics of a single cell trapped by acoustic tweezers , 2017, Scientific Reports.

[13]  James K Gimzewski,et al.  AFM-based analysis of human metastatic cancer cells , 2008, Nanotechnology.

[14]  K. Kirk Shung,et al.  Cell Deformation by Single-beam Acoustic Trapping: A Promising Tool for Measurements of Cell Mechanics , 2016, Scientific Reports.

[15]  N. Gavara,et al.  Probing mechanical properties of living cells by atomic force microscopy with blunted pyramidal cantilever tips. , 2005, Physical review. E, Statistical, nonlinear, and soft matter physics.

[16]  Biran Wang,et al.  Mapping the CXCR4 receptor on breast cancer cells. , 2015, Biomaterials.

[17]  Ehsan Gazi,et al.  Measurement of elastic properties of prostate cancer cells using AFM. , 2008, The Analyst.

[18]  Non-contact high-frequency ultrasound microbeam stimulation for studying mechanotransduction in human umbilical vein endothelial cells. , 2014, Ultrasound in medicine & biology.

[19]  K. Shung,et al.  Quantification of Inter-Erythrocyte Forces with Ultra-High Frequency (410 MHz) Single Beam Acoustic Tweezer , 2017, Annals of Biomedical Engineering.

[20]  Gerard Pasterkamp,et al.  SlideToolkit: An Assistive Toolset for the Histological Quantification of Whole Slide Images , 2014, PloS one.

[21]  Jin Woo Choi,et al.  Acoustic Trapping Technique for Studying Calcium Response of a Suspended Breast Cancer Cell: Determination of Its Invasion Potentials , 2019, IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control.

[22]  J. Rao,et al.  Nanomechanical analysis of cells from cancer patients. , 2007, Nature nanotechnology.

[23]  Hyung Ham Kim,et al.  Evaluation method for acoustic trapping performance by tracking motion of trapped microparticle , 2018 .

[24]  Yoram Singer,et al.  Adaptive Subgradient Methods for Online Learning and Stochastic Optimization , 2011, J. Mach. Learn. Res..

[25]  Javier Tamayo,et al.  Effect of Actin Organization on the Stiffness of Living Breast Cancer Cells Revealed by Peak-Force Modulation Atomic Force Microscopy. , 2016, ACS nano.

[26]  Hyung Ham Kim,et al.  A One-Sided Acoustic Trap for Cell Immobilization Using 30-MHz Array Transducer , 2020, IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control.

[27]  Jun Kong,et al.  A data model and database for high-resolution pathology analytical image informatics , 2011, Journal of pathology informatics.

[28]  Sebastian Ruder,et al.  An overview of gradient descent optimization algorithms , 2016, Vestnik komp'iuternykh i informatsionnykh tekhnologii.

[29]  K. Kirk Shung,et al.  Cell membrane deformation induced by a fibronectin-coated polystyrene microbead in a 200-MHz acoustic trap , 2014, IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control.

[30]  Ruijiang Li,et al.  A Composite Model Integrating Imaging, Histological, and Genetic Features to Predict Tumor Mutation Burden in Non-Small Cell Lung Cancer Patients , 2019, International Journal of Radiation Oncology, Biology, Physics.

[31]  J. Myoung,et al.  Stretchable Piezoelectric Substrate Providing Pulsatile Mechanoelectric Cues for Cardiomyogenic Differentiation of Mesenchymal Stem Cells. , 2017, ACS applied materials & interfaces.

[32]  K. Hume,et al.  Volumetric and linear measurements of lung tumor burden from non-gated micro-CT imaging correlate with histological analysis in a genetically engineered mouse model of non-small cell lung cancer , 2018, Laboratory animals.

[33]  Matthew D. Zeiler ADADELTA: An Adaptive Learning Rate Method , 2012, ArXiv.

[34]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[35]  Jungwoo Lee,et al.  Microfluidic acoustic trapping force and stiffness measurement using viscous drag effect. , 2013, Ultrasonics.

[36]  Qifa Zhou,et al.  Investigating contactless high frequency ultrasound microbeam stimulation for determination of invasion potential of breast cancer cells , 2013, Biotechnology and bioengineering.

[37]  E. Schmelz,et al.  Evaluation of the influence of growth medium composition on cell elasticity. , 2011, Journal of biomechanics.

[38]  D. Grier A revolution in optical manipulation , 2003, Nature.

[39]  Farshid Guilak,et al.  Viscoelastic properties of human mesenchymally-derived stem cells and primary osteoblasts, chondrocytes, and adipocytes. , 2008, Journal of biomechanics.