Lung Cancer Pathological Image Analysis Using a Hidden Potts Model

Cancer Informatics - Tập 16 - Trang 117693511771191 - 2017
Qianyun Li1, Faliu Yi2, Tao Wang3, Guanghua Xiao3, Faming Liang1
1Department of Biostatistics, University of Florida, Gainesville, FL, USA
2Image Analysis, UT Southwestern Medical Center, Dallas, TX, USA
3Department of Clinical Sciences, UT Southwestern Medical Center, Dallas, TX, USA

Tóm tắt

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.

Từ khóa


Tài liệu tham khảo

Cross MD, 2012, Med Lab Obs, 44, 40

10.1016/j.ejcts.2011.05.050

10.1097/00000478-200203000-00010

10.1002/cncr.24831

10.1097/PAS.0b013e318190157c

10.1109/TMI.2007.898536

10.1126/scitranslmed.3002564

10.1126/scitranslmed.3004330

Li S, 2009, Markov Random Field Modeling in Image Analysis

10.1109/TIP.2010.2047902

10.1198/016214502388618870

10.1080/00949650902882162

10.1103/RevModPhys.54.235

10.1007/BF02980577

10.1088/0022-3719/7/6/005

10.1016/0370-2693(75)90161-6

10.1103/PhysRevLett.20.589

10.1103/PhysRevLett.50.263

10.1080/13642819008215259

10.1103/PhysRevLett.69.2013

10.1093/biomet/93.2.451

10.1080/01621459.2015.1009072

10.1002/(SICI)1098-2418(199608/09)9:1/2<223::AID-RSA14>3.0.CO;2-O

Besag J, 1974, J Roy Stat Soc B, 36, 192, 10.1111/j.2517-6161.1974.tb00999.x

Geyer CJ, 1992, J Roy Stat Soc B, 54, 657, 10.1111/j.2517-6161.1992.tb01443.x

10.1198/106186007X238459

10.1214/11-BJPS174

Park J, 2016, Bayesian Inference in the Presence of Intractable Normalizing Functions: A Comparative Review

10.1056/NEJMoa1102873

Gonzalez RC, 2002, Digital Imaging Processing

10.1109/TMI.2016.2528162

10.1080/10618600.2012.679228

Xu G, 2015, Stat Sinica, 25, 61

10.1198/1061860031365

10.1093/biomet/81.3.515

Thông tin
Thông tin xuất bản

Cancer Informatics

Tập 16

117693511771191

Thông tin tác giả