Automated identification of circulating tumor cells by image cytometry

Presence of circulating tumor cells (CTC), as detected by the CellSearch® System, in patients with metastatic carcinomas is associated with poor survival prospects. CellTracks TDI, a dedicated image cytometer, was developed to improve the enumeration of these rare CTC. The CellSearch System was used to enumerate CTC in 7.5 mL blood of 68 patients with cancer and 9 healthy controls. Cartridges containing the fluorescently labeled CTC from this system were reanalyzed using the image cytometer, which acquires images with a TDI camera using a 40×/0.6 NA objective and lasers as light source. Automated classification of events was performed by the Random Forest method using Matlab. An automated classifier was developed to classify events into CTC, apoptotic CTC, CTC debris, leukocytes, and debris not related to CTC. A high agreement in classification was obtained between the automated classifier and five expert reviewers. Comparison of images from the same events in CellTracks TDI and CellTracks Analyzer II shows improved resolution in fluorescence images and improved classification by adding bright‐field images. Improved detection efficiency for CD45‐APC avoids the classification of leukocytes nonspecifically binding to cytokeratin as CTC. The correlation between number of CTC detected in CellTracks TDI and CellTracks Analyzer II is good with a slope of 1.88 and a correlation coefficient of 0.87. Automated classification of events by CellTracks TDI eliminates the operator error in classification of events as CTC and permits quantitative assessment of parameters. The clinical relevance of various CTC definitions can now be investigated. © 2011 International Society for Advancement of Cytometry

[1]  Tin Kam Ho,et al.  The Random Subspace Method for Constructing Decision Forests , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  S. Linder,et al.  Cytokeratin-18 Is a Useful Serum Biomarker for Early Determination of Response of Breast Carcinomas to Chemotherapy , 2007, Clinical Cancer Research.

[3]  Giandomenico Spezzano,et al.  An Adaptive Distributed Ensemble Approach to Mine Concept-Drifting Data Streams , 2007 .

[4]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[5]  E. Kubista,et al.  Circulating breast cancer cells are frequently apoptotic. , 2001, The American journal of pathology.

[6]  S. Digumarthy,et al.  Isolation of rare circulating tumour cells in cancer patients by microchip technology , 2007, Nature.

[7]  Pau-Choo Chung,et al.  A Fast Algorithm for Multilevel Thresholding , 2001, J. Inf. Sci. Eng..

[8]  A. Weiss,et al.  Detection and characterization of carcinoma cells in the blood. , 1998, Proceedings of the National Academy of Sciences of the United States of America.

[9]  Jan Greve,et al.  CellTracks TDI: An image cytometer for cell characterization , 2011, Cytometry. Part A : the journal of the International Society for Analytical Cytology.

[10]  Leon W M M Terstappen,et al.  Statistical considerations for enumeration of circulating tumor cells , 2007, Cytometry. Part A : the journal of the International Society for Analytical Cytology.

[11]  Jason P. Gleghorn,et al.  Capture of circulating tumor cells from whole blood of prostate cancer patients using geometrically enhanced differential immunocapture (GEDI) and a prostate-specific antibody. , 2010, Lab on a chip.

[12]  J. Fleiss.  Measuring nominal scale agreement among many raters. , 1971 .

[13]  K. Pienta,et al.  Circulating Tumor Cells Predict Survival Benefit from Treatment in Metastatic Castration-Resistant Prostate Cancer , 2008, Clinical Cancer Research.

[14]  I. Nagtegaal,et al.  Circulating tumour cells early predict progression-free and overall survival in advanced colorectal cancer patients treated with chemotherapy and targeted agents. , 2010, Annals of oncology : official journal of the European Society for Medical Oncology.

[15]  Alison Stopeck,et al.  Circulating tumor cells, disease progression, and survival in metastatic breast cancer. , 2004, The New England journal of medicine.

[16]  Anne-Michelle Noone,et al.  Circulating tumor cells: a useful predictor of treatment efficacy in metastatic breast cancer. , 2009, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[17]  M. Omary,et al.  Apoptosis Generates Stable Fragments of Human Type I Keratins* , 1997, The Journal of Biological Chemistry.

[18]  Jieyue Li,et al.  Automated analysis of Human Protein Atlas immunofluorescence images , 2009, 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[19]  A W Partin,et al.  Identification and characterization of circulating prostate carcinoma cells , 2000, Cancer.

[20]  Claire Holloway,et al.  Enumeration of Circulating Tumor Cells in the Blood of Breast Cancer Patients After Filtration Enrichment: Correlation with Disease Stage , 2004, Breast Cancer Research and Treatment.

[21]  D. Dearnaley,et al.  Characterization of ERG, AR and PTEN gene status in circulating tumor cells from patients with castration-resistant prostate cancer. , 2009, Cancer research.

[22]  David Ward,et al.  Comparison of statistical methods for classification of ovarian cancer using mass spectrometry data , 2003, Bioinform..

[23]  K. Pienta,et al.  Apoptosis of circulating tumor cells in prostate cancer patients , 2004, Cytometry. Part A : the journal of the International Society for Analytical Cytology.

[24]  E. Lane,et al.  Keratin 8/18 breakdown and reorganization during apoptosis. , 2004, Experimental cell research.

[25]  Michael D. Abràmoff,et al.  Image processing with ImageJ , 2004 .

[26]  Peter Kuhn,et al.  High speed detection of circulating tumor cells. , 2006, Biosensors & bioelectronics.

[27]  K. Schütze,et al.  Isolation by size of epithelial tumor cells : a new method for the immunomorphological and molecular characterization of circulatingtumor cells. , 2000, The American journal of pathology.

[28]  N. Lai,et al.  CYFRA 21-1 enzyme-linked immunosorbent assay. Evaluation as a tumor marker in non-small cell lung cancer. , 1996, Chest.

[29]  K. Wiman,et al.  A Novel High-Through-Put Assay for Screening of Pro-Apoptotic Drugs , 2002, Investigational New Drugs.

[30]  Jonathan W. Uhr,et al.  Tumor Cells Circulate in the Peripheral Blood of All Major Carcinomas but not in Healthy Subjects or Patients With Nonmalignant Diseases , 2004, Clinical Cancer Research.

[31]  A. Marchetti,et al.  Int6 Expression Can Predict Survival in Early-Stage Non–Small Cell Lung Cancer Patients , 2005, Clinical Cancer Research.

[32]  J. Bono,et al.  All circulating EpCAM+CK+CD45- objects predict overall survival in castration-resistant prostate cancer. , 2010, Annals of oncology : official journal of the European Society for Medical Oncology.

[33]  Jacob Cohen,et al.  Weighted kappa: Nominal scale agreement provision for scaled disagreement or partial credit. , 1968 .

[34]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[35]  Johannes R. Sveinsson,et al.  Random Forests for land cover classification , 2006, Pattern Recognit. Lett..

[36]  L. Terstappen,et al.  Characterization of circulating tumor cells by fluorescence in situ hybridization , 2009, Cytometry. Part A : the journal of the International Society for Analytical Cytology.

[37]  H. Jörnvall,et al.  An immunohistochemical study of the clearance of apoptotic cellular fragments , 2002, Cellular and Molecular Life Sciences CMLS.

[38]  J. Sim,et al.  The kappa statistic in reliability studies: use, interpretation, and sample size requirements. , 2005, Physical therapy.

[39]  M C Miller,et al.  Expression of epithelial cell adhesion molecule in carcinoma cells present in blood and primary and metastatic tumors. , 2004, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[40]  Chwee Teck Lim,et al.  Versatile label free biochip for the detection of circulating tumor cells from peripheral blood in cancer patients. , 2010, Biosensors & bioelectronics.

[41]  Michael Morse,et al.  Relationship of circulating tumor cells to tumor response, progression-free survival, and overall survival in patients with metastatic colorectal cancer. , 2008, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[42]  Giovanna Bises,et al.  Detection of EpCAM positive and negative circulating tumor cells in metastatic breast cancer patients , 2011, Acta oncologica.

[43]  G. Kramer,et al.  Differentiation between Cell Death Modes Using Measurements of Different Soluble Forms of Extracellular Cytokeratin 18 , 2004, Cancer Research.

[44]  Pamela C. Cosman,et al.  Automatic tracking, feature extraction and classification of C. elegans phenotypes , 2004, IEEE Transactions on Biomedical Engineering.

[45]  Thierry Maudelonde,et al.  Characterization and enumeration of cells secreting tumor markers in the peripheral blood of breast cancer patients. , 2005, Journal of immunological methods.

[46]  A. Stopeck,et al.  Tumor cells circulate in the peripheral blood of all major carcinomas but not in healthy subjects or patients with non-malignant diseases. , 2004, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[47]  David A Basiji,et al.  Sensitivity measurement and compensation in spectral imaging , 2006, Cytometry. Part A : the journal of the International Society for Analytical Cytology.

[48]  Ws. Rasband.  ImageJ, U.S. National Institutes of Health, Bethesda, Maryland, USA , 2011 .

[49]  Juan Manuel Górriz,et al.  SPECT image classification using random forests , 2009 .

[50]  Nathalie Harder,et al.  Feature Selection for Evaluating Fluorescence Microscopy Images in Genome-Wide Cell Screens , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[51]  J. R. Landis,et al.  The measurement of observer agreement for categorical data. , 1977, Biometrics.

[52]  D. Dearnaley,et al.  Circulating tumour cell (CTC) counts as intermediate end points in castration-resistant prostate cancer (CRPC): a single-centre experience. , 2009, Annals of oncology : official journal of the European Society for Medical Oncology.

[53]  F. O. Fackelmayer,et al.  DNA fragments in the blood plasma of cancer patients: quantitations and evidence for their origin from apoptotic and necrotic cells. , 2001, Cancer research.

[54]  F. Becker,et al.  Isolation of rare cells from cell mixtures by dielectrophoresis , 2009, Electrophoresis.

[55]  Jan Greve,et al.  Magnetic field design for selecting and aligning immunomagnetic labeled cells. , 2002, Cytometry.

[56]  Joydeep Ghosh,et al.  Investigation of the random forest framework for classification of hyperspectral data , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[57]  T. Kroll,et al.  Monitoring the response of circulating epithelial tumor cells to adjuvant chemotherapy in breast cancer allows detection of patients at risk of early relapse. , 2008, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[58]  Taghi M. Khoshgoftaar,et al.  An Empirical Study of Learning from Imbalanced Data Using Random Forest , 2007, 19th IEEE International Conference on Tools with Artificial Intelligence(ICTAI 2007).

[59]  Peter Kuhn,et al.  A rare-cell detector for cancer. , 2004, Proceedings of the National Academy of Sciences of the United States of America.

[60]  Frederik Schreuder,et al.  Laser image cytometer for analysis of circulating tumor cells , 2008 .