A New Method for CTC Images Recognition Based on Machine Learning

Circulating tumor cells (CTCs) derived from primary tumors and/or metastatic tumors are markers for tumor prognosis, and can also be used to monitor therapeutic efficacy and tumor recurrence. Circulating tumor cells enrichment and screening can be automated, but the final counting of CTCs currently requires manual intervention. This not only requires the participation of experienced pathologists, but also easily causes artificial misjudgment. Medical image recognition based on machine learning can effectively reduce the workload and improve the level of automation. So, we use machine learning to identify CTCs. First, we collected the CTC test results of 600 patients. After immunofluorescence staining, each picture presented a positive CTC cell nucleus and several negative controls. The images of CTCs were then segmented by image denoising, image filtering, edge detection, image expansion and contraction techniques using python’s openCV scheme. Subsequently, traditional image recognition methods and machine learning were used to identify CTCs. Machine learning algorithms are implemented using convolutional neural network deep learning networks for training. We took 2300 cells from 600 patients for training and testing. About 1300 cells were used for training and the others were used for testing. The sensitivity and specificity of recognition reached 90.3 and 91.3%, respectively. We will further revise our models, hoping to achieve a higher sensitivity and specificity.

[1]  Hui Zheng,et al.  Precisely Enumerating Circulating Tumor Cells Utilizing a Multi-Functional Microfluidic Chip and Unique Image Interpretation Algorithm , 2017, Theranostics.

[2]  Shan Zheng,et al.  Circulating tumor cells detection in neuroblastoma patients by EpCAM-independent enrichment and immunostaining-fluorescence in situ hybridization , 2018, EBioMedicine.

[3]  K. Pantel,et al.  Biology and clinical relevance of EpCAM , 2019, Cell stress.

[4]  D. Heymann,et al.  Circulating Tumor Cells: A Review of Non-EpCAM-Based Approaches for Cell Enrichment and Isolation. , 2016, Clinical chemistry.

[5]  Arvid Lundervold,et al.  An overview of deep learning in medical imaging focusing on MRI , 2018, Zeitschrift fur medizinische Physik.

[6]  T. Schlange,et al.  Circulating Tumor Cell PD-L1 Expression as Biomarker for Therapeutic Efficacy of Immune Checkpoint Inhibition in NSCLC , 2019, Cells.

[7]  T. Fehm,et al.  The clinical use of circulating tumor cells (CTCs) enumeration for staging of metastatic breast cancer (MBC): International expert consensus paper. , 2019, Critical reviews in oncology/hematology.

[8]  Marios Anthimopoulos,et al.  Lung Pattern Classification for Interstitial Lung Diseases Using a Deep Convolutional Neural Network , 2016, IEEE Transactions on Medical Imaging.

[9]  Pedro M. Domingos,et al.  Naive Bayes models for probability estimation , 2005, ICML.

[10]  Brooke L. Billman,et al.  Circulating Tumor DNA Analysis in Patients With Cancer: American Society of Clinical Oncology and College of American Pathologists Joint Review. , 2018, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[11]  César Domínguez,et al.  IJ-OpenCV: Combining ImageJ and OpenCV for processing images in biomedicine , 2017, Comput. Biol. Medicine.

[12]  John W. Park,et al.  Circulating Tumor Cells , 2017, Methods in Molecular Biology.

[13]  M. Tiemann,et al.  Determination of PD-L1 Expression in Circulating Tumor Cells of NSCLC Patients and Correlation with Response to PD-1/PD-L1 Inhibitors , 2019, Cancers.

[14]  Michael V. McConnell,et al.  Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning , 2017, Nature Biomedical Engineering.

[15]  S Paget,et al.  THE DISTRIBUTION OF SECONDARY GROWTHS IN CANCER OF THE BREAST. , 1889 .

[16]  T. Fehm,et al.  Prognostic Relevance of Circulating Tumor Cells in Molecular Subtypes of Breast Cancer. , 2015, Geburtshilfe und Frauenheilkunde.

[17]  Jialin Yang,et al.  Distribution of circulating tumor cell phenotype in early cervical cancer , 2019, Cancer management and research.

[18]  M. Ziman,et al.  Liquid biopsy in Ovarian cancer using Circulating Tumor DNA and Cells: Ready for Prime Time? , 2019, Cancer letters.

[19]  Stefanie S Jeffrey,et al.  Circulating tumor cell technologies , 2016, Molecular oncology.

[20]  K. Pantel,et al.  Prognostic Relevance of Circulating Tumor Cells in Blood and Disseminated Tumor Cells in Bone Marrow of Patients with Squamous Cell Carcinoma of the Oral Cavity , 2013, Clinical Cancer Research.

[21]  Qinghua Zhou,et al.  Detection of Circulating Tumor Cell Molecular Subtype in Pulmonary Vein Predicting Prognosis of Stage I–III Non-small Cell Lung Cancer Patients , 2019, Front. Oncol..

[22]  Nangang Zhang,et al.  Wedge-shaped microfluidic chip for circulating tumor cells isolation and its clinical significance in gastric cancer , 2018, Journal of Translational Medicine.

[23]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[24]  Lin Yang,et al.  An Automatic Learning-Based Framework for Robust Nucleus Segmentation , 2016, IEEE Transactions on Medical Imaging.

[25]  D. Planchard,et al.  A prospective examination of circulating tumor cell profiles in non-small-cell lung cancer molecular subgroups , 2017, Annals of oncology : official journal of the European Society for Medical Oncology.

[26]  Michael Wainberg,et al.  Deep learning in biomedicine , 2018, Nature Biotechnology.

[27]  J. Mazières,et al.  PD-L1 expression in circulating tumor cells of advanced non-small cell lung cancer patients treated with nivolumab. , 2018, Lung cancer.

[28]  J. Ross Quinlan,et al.  Induction of Decision Trees , 1986, Machine Learning.

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

[30]  V. Bobek,et al.  Circulating Tumor Cells in Diagnosis and Treatment of Lung Cancer , 2019, In Vivo.

[31]  A. Lucci,et al.  Pilot Study of Circulating Tumor Cells in Early-Stage and Metastatic Uveal Melanoma , 2019, Cancers.

[32]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[33]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[34]  M. Westphal,et al.  Clonality of circulating tumor cells in breast cancer brain metastasis patients , 2019, Breast Cancer Research.

[35]  Leon W. M. M. Terstappen,et al.  Unbiased and Automated Identification of a Circulating Tumour Cell Definition That Associates with Overall Survival , 2011, PloS one.

[36]  Dinggang Shen,et al.  Machine Learning in Medical Imaging , 2012, Lecture Notes in Computer Science.

[37]  Sejoon Lee,et al.  Centromere 17 copy number gain reflects chromosomal instability in breast cancer , 2019, Scientific Reports.

[38]  R. Matkowski,et al.  Circulating Tumor , 2014 .

[39]  M. Tiemann,et al.  Determination of PD-L1 Expression in Circulating Tumor Cells of NSCLC Patients and Correlation with Response to PD-1/PD-L1 Inhibitors , 2019, Cancers.

[40]  G. Deep,et al.  Circulating tumor cell-derived organoids: Current challenges and promises in medical research and precision medicine , 2018, Biochimica et biophysica acta. Reviews on cancer.

[41]  D. Atanackovic,et al.  Characterization of different CTC subpopulations in non-small cell lung cancer , 2016, Scientific Reports.

[42]  Yan Qiu Chen,et al.  Improving nearest neighbor classification with cam weighted distance , 2006, Pattern Recognit..

[43]  Srini Tridandapani,et al.  Deep Learning in Radiology. , 2018, Academic radiology.

[44]  James D. Brenton,et al.  Liquid biopsies come of age: towards implementation of circulating tumour DNA , 2017, Nature Reviews Cancer.

[45]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[46]  T. Price,et al.  Circulating tumour cells: the evolving concept and the inadequacy of their enrichment by EpCAM-based methodology for basic and clinical cancer research. , 2014, Annals of oncology : official journal of the European Society for Medical Oncology.

[47]  M. Huss,et al.  A primer on deep learning in genomics , 2018, Nature Genetics.

[48]  Chaoyang Zhang,et al.  Deep Learning Based Analysis of Histopathological Images of Breast Cancer , 2019, Front. Genet..

[49]  Maximilian Diehn,et al.  Circulating Tumor DNA Analysis in Patients With Cancer: American Society of Clinical Oncology and College of American Pathologists Joint Review. , 2018, Archives of pathology & laboratory medicine.

[50]  N. Stoecklein,et al.  Circulating biomarkers for early detection and clinical management of colorectal cancer. , 2019, Molecular aspects of medicine.

[51]  Shuo Wang,et al.  Overview of deep learning , 2016, 2016 31st Youth Academic Annual Conference of Chinese Association of Automation (YAC).

[52]  Yu-Yen Ou,et al.  Classifying the molecular functions of Rab GTPases in membrane trafficking using deep convolutional neural networks. , 2018, Analytical biochemistry.

[53]  L. Harris,et al.  Reliable and Sensitive Identification of Occult Tumor Cells Using the Improved Rare Event Imaging System , 2004, Clinical Cancer Research.

[54]  Tuan-Tu Huynh,et al.  Identification of clathrin proteins by incorporating hyperparameter optimization in deep learning and PSSM profiles , 2019, Comput. Methods Programs Biomed..

[55]  J. Kaifi,et al.  PD-L1 Expression with Epithelial Mesenchymal Transition of Circulating Tumor Cells Is Associated with Poor Survival in Curatively Resected Non-Small Cell Lung Cancer , 2019, Cancers.

[56]  Christian Riess,et al.  A Gentle Introduction to Deep Learning in Medical Image Processing , 2018, Zeitschrift fur medizinische Physik.

[57]  A. Schneeweiss,et al.  Molecular Subtype Conversion between Primary and Metastatic Breast Cancer Corresponding to the Dynamics of Apoptotic and Intact Circulating Tumor Cells , 2019, Cancers.

[58]  L. Varanasi,et al.  Frequency of chromosome 17 polysomy in relation to CEP17 copy number in a large breast cancer cohort , 2016, Genes, chromosomes & cancer.

[59]  Y. Maehara,et al.  Therapeutic strategy for postoperative recurrence in patients with non-small cell lung cancer. , 2014, World journal of clinical oncology.

[60]  Yu-Yen Ou,et al.  Incorporating deep learning with convolutional neural networks and position specific scoring matrices for identifying electron transport proteins , 2017, J. Comput. Chem..

[61]  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.

[62]  CLINICAL POTENTIAL OF CIRCULATING TUMOR CELLS IN COLORECTAL CANCER: A PROSPECTIVE STUDY , 2019, ESGE Days 2019.