Lung Cancer Pathological Image Analysis Using a Hidden Potts Model

Nowadays, many biological data are acquired via images. In this article, we study the pathological images scanned from 205 patients with lung cancer with the goal to find out the relationship between the survival time and the spatial distribution of different types of cells, including lymphocyte, stroma, and tumor cells. Toward this goal, we model the spatial distribution of different types of cells using a modified Potts model for which the parameters represent interactions between different types of cells and estimate the parameters of the Potts model using the double Metropolis-Hastings algorithm. The double Metropolis-Hastings algorithm allows us to simulate samples approximately from a distribution with an intractable normalizing constant. Our numerical results indicate that the spatial interaction between the lymphocyte and tumor cells is significantly associated with the patient’s survival time, and it can be used together with the cell count information to predict the survival of the patients.

[1]  A. Borczuk,et al.  Invasive Size is an Independent Predictor of Survival in Pulmonary Adenocarcinoma , 2009, The American journal of surgical pathology.

[2]  F. Liang.  Continuous Contour Monte Carlo for Marginal Density Estimation With an Application to a Spatial Statistical Model , 2007 .

[3]  L. Chirieac,et al.  Prognostic significance of grading in lung adenocarcinoma , 2010, Cancer.

[4]  P. Grambsch,et al.  Penalized Survival Models and Frailty , 2003 .

[5]  F. Markowetz,et al.  Quantitative Image Analysis of Cellular Heterogeneity in Breast Tumors Complements Genomic Profiling , 2012, Science Translational Medicine.

[6]  Advances in NSCLc: histologic distinction between adenocarcinoma and squamous cell carcinoma. , 2012, MLO: medical laboratory observer.

[7]  Faming Liang,et al.  A BAYESIAN SPATIO-TEMPORAL GEOSTATISTICAL MODEL WITH AN AUXILIARY LATTICE FOR LARGE DATASETS , 2014 .

[8]  P. S. Sahni,et al.  Kinetics of the Q-state Potts model in two dimensions , 1983 .

[9]  J. Besag.  Spatial Interaction and the Statistical Analysis of Lattice Systems , 1974 .

[10]  Jungsil Ro,et al.  Micropapillary Component in Lung Adenocarcinoma: A Distinctive Histologic Feature With Possible Prognostic Significance , 2002, The American journal of surgical pathology.

[11]  Faming Liang,et al.  A double Metropolis–Hastings sampler for spatial models with intractable normalizing constants , 2010 .

[12]  Ali Mohammad-Djafari,et al.  Joint image restoration and segmentation using Gauss-Markov-Potts prior models and variational Bayesian computation , 2009, ICIP.

[13]  H. Maeda,et al.  Adenosquamous carcinoma of the lung: surgical results as compared with squamous cell and adenocarcinoma cases. , 2012, European journal of cardio-thoracic surgery : official journal of the European Association for Cardio-thoracic Surgery.

[14]  P. Green,et al.  Hidden Markov Models and Disease Mapping , 2002 .

[15]  F. Y. Wu.  The Potts model , 1982 .

[16]  Zoubin Ghahramani,et al.  MCMC for Doubly-intractable Distributions , 2006, UAI.

[17]  E. Ising.  Beitrag zur Theorie des Ferromagnetismus , 1925 .

[18]  A. Polyakov.  Interaction of Goldstone Particles in Two-Dimensions. Applications to Ferromagnets and Massive Yang-Mills Fields , 1975 .

[19]  James A. Glazier,et al.  Coarsening in the two-dimensional soap froth and the large-Q Potts model: A detailed comparison , 1990 .

[20]  Christian P. Robert,et al.  Bayesian computation for statistical models with intractable normalizing constants , 2008, 0804.3152.

[21]  Glazier,et al.  Simulation of biological cell sorting using a two-dimensional extended Potts model. , 1992, Physical review letters.

[22]  H. Stanley,et al.  Dependence of critical properties on dimensionality of spins , 1968 .

[23]  Jaewoo Park,et al.  Bayesian Inference in the Presence of Intractable Normalizing Functions , 2017, Journal of the American Statistical Association.

[24]  David Bruce Wilson,et al.  Exact sampling with coupled Markov chains and applications to statistical mechanics , 1996, Random Struct. Algorithms.

[25]  Ronald M. Summers,et al.  Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning , 2016, IEEE Transactions on Medical Imaging.

[26]  Ali Mohammad-Djafari,et al.  Joint NDT Image Restoration and Segmentation Using Gauss–Markov–Potts Prior Models and Variational Bayesian Computation , 2009, IEEE Transactions on Image Processing.

[27]  P. Grambsch,et al.  Proportional hazards tests and diagnostics based on weighted residuals , 1994 .

[28]  C. Gatsonis,et al.  Reduced Lung-Cancer Mortality with Low-Dose Computed Tomographic Screening , 2012 .

[29]  C. Geyer,et al.  Constrained Monte Carlo Maximum Likelihood for Dependent Data , 1992 .

[30]  Mikhail Teverovskiy,et al.  Multifeature Prostate Cancer Diagnosis and Gleason Grading of Histological Images , 2007, IEEE Transactions on Medical Imaging.

[31]  Giovanni Mettivier,et al.  Digital Imaging Processing , 2010 .

[32]  Andrew H. Beck,et al.  Systematic Analysis of Breast Cancer Morphology Uncovers Stromal Features Associated with Survival , 2011, Science Translational Medicine.

[33]  J. Møller,et al.  An efficient Markov chain Monte Carlo method for distributions with intractable normalising constants , 2006 .

[34]  Stan Z. Li,et al.  Markov Random Field Modeling in Image Analysis , 2001, Computer Science Workbench.

[35]  Faming Liang,et al.  Bayesian Analysis of Geostatistical Models With an Auxiliary Lattice , 2012 .

[36]  J. Kosterlitz,et al.  The critical properties of the two-dimensional xy model , 1974 .

[37]  Faming Liang,et al.  An Adaptive Exchange Algorithm for Sampling From Distributions With Intractable Normalizing Constants , 2016 .