A Bayesian hidden Potts mixture model for analyzing lung cancer pathology images

Qiwei Li, Xinlei Wang, Faming Liang, Faliu Yi, Yang Xie, Adi Gazdar, Guanghua Xiao

Research output: Contribution to journalArticle

Abstract

Digital pathology imaging of tumor tissues, which captures histological details in high resolution, is fast becoming a routine clinical procedure. Recent developments in deep-learning methods have enabled the identification, characterization, and classification of individual cells from pathology images analysis at a large scale. This creates new opportunities to study the spatial patterns of and interactions among different types of cells. Reliable statistical approaches to modeling such spatial patterns and interactions can provide insight into tumor progression and shed light on the biological mechanisms of cancer. In this article, we consider the problem of modeling a pathology image with irregular locations of three different types of cells: lymphocyte, stromal, and tumor cells. We propose a novel Bayesian hierarchical model, which incorporates a hidden Potts model to project the irregularly distributed cells to a square lattice and a Markov random field prior model to identify regions in a heterogeneous pathology image. The model allows us to quantify the interactions between different types of cells, some of which are clinically meaningful. We use Markov chain Monte Carlo sampling techniques, combined with a double Metropolis-Hastings algorithm, in order to simulate samples approximately from a distribution with an intractable normalizing constant. The proposed model was applied to the pathology images of $205$ lung cancer patients from the National Lung Screening trial, and the results show that the interaction strength between tumor and stromal cells predicts patient prognosis (P = $0.005$). This statistical methodology provides a new perspective for understanding the role of cell-cell interactions in cancer progression.

Original languageEnglish (US)
Pages (from-to)565-581
Number of pages17
JournalBiostatistics (Oxford, England)
Volume20
Issue number4
DOIs
StatePublished - Oct 1 2019

Fingerprint

Lung Cancer
Potts Model
Mixture Model
Cell
Tumor
Interaction
Spatial Pattern
Progression
Cancer
Normalizing Constant
Lung cancer
Mixture model
Pathology
Bayesian Hierarchical Model
Digital Imaging
Metropolis-Hastings Algorithm
Monte Carlo Sampling
Lymphocytes
Prognosis
Markov Chain Monte Carlo

Keywords

  • Double Metropolis–Hastings
  • Hidden Potts model
  • Lung cancer
  • Markov random field
  • Mixture model
  • Pathology image
  • Potts model
  • Spatial point pattern

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

A Bayesian hidden Potts mixture model for analyzing lung cancer pathology images. / Li, Qiwei; Wang, Xinlei; Liang, Faming; Yi, Faliu; Xie, Yang; Gazdar, Adi; Xiao, Guanghua.

In: Biostatistics (Oxford, England), Vol. 20, No. 4, 01.10.2019, p. 565-581.

Research output: Contribution to journalArticle

Li, Qiwei ; Wang, Xinlei ; Liang, Faming ; Yi, Faliu ; Xie, Yang ; Gazdar, Adi ; Xiao, Guanghua. / A Bayesian hidden Potts mixture model for analyzing lung cancer pathology images. In: Biostatistics (Oxford, England). 2019 ; Vol. 20, No. 4. pp. 565-581.
@article{2ba662c48a5b46cc8c08aa0b0dfa261c,
title = "A Bayesian hidden Potts mixture model for analyzing lung cancer pathology images",
abstract = "Digital pathology imaging of tumor tissues, which captures histological details in high resolution, is fast becoming a routine clinical procedure. Recent developments in deep-learning methods have enabled the identification, characterization, and classification of individual cells from pathology images analysis at a large scale. This creates new opportunities to study the spatial patterns of and interactions among different types of cells. Reliable statistical approaches to modeling such spatial patterns and interactions can provide insight into tumor progression and shed light on the biological mechanisms of cancer. In this article, we consider the problem of modeling a pathology image with irregular locations of three different types of cells: lymphocyte, stromal, and tumor cells. We propose a novel Bayesian hierarchical model, which incorporates a hidden Potts model to project the irregularly distributed cells to a square lattice and a Markov random field prior model to identify regions in a heterogeneous pathology image. The model allows us to quantify the interactions between different types of cells, some of which are clinically meaningful. We use Markov chain Monte Carlo sampling techniques, combined with a double Metropolis-Hastings algorithm, in order to simulate samples approximately from a distribution with an intractable normalizing constant. The proposed model was applied to the pathology images of $205$ lung cancer patients from the National Lung Screening trial, and the results show that the interaction strength between tumor and stromal cells predicts patient prognosis (P = $0.005$). This statistical methodology provides a new perspective for understanding the role of cell-cell interactions in cancer progression.",
keywords = "Double Metropolis–Hastings, Hidden Potts model, Lung cancer, Markov random field, Mixture model, Pathology image, Potts model, Spatial point pattern",
author = "Qiwei Li and Xinlei Wang and Faming Liang and Faliu Yi and Yang Xie and Adi Gazdar and Guanghua Xiao",
year = "2019",
month = "10",
day = "1",
doi = "10.1093/biostatistics/kxy019",
language = "English (US)",
volume = "20",
pages = "565--581",
journal = "Biostatistics",
issn = "1465-4644",
publisher = "Oxford University Press",
number = "4",

}

TY - JOUR

T1 - A Bayesian hidden Potts mixture model for analyzing lung cancer pathology images

AU - Li, Qiwei

AU - Wang, Xinlei

AU - Liang, Faming

AU - Yi, Faliu

AU - Xie, Yang

AU - Gazdar, Adi

AU - Xiao, Guanghua

PY - 2019/10/1

Y1 - 2019/10/1

N2 - Digital pathology imaging of tumor tissues, which captures histological details in high resolution, is fast becoming a routine clinical procedure. Recent developments in deep-learning methods have enabled the identification, characterization, and classification of individual cells from pathology images analysis at a large scale. This creates new opportunities to study the spatial patterns of and interactions among different types of cells. Reliable statistical approaches to modeling such spatial patterns and interactions can provide insight into tumor progression and shed light on the biological mechanisms of cancer. In this article, we consider the problem of modeling a pathology image with irregular locations of three different types of cells: lymphocyte, stromal, and tumor cells. We propose a novel Bayesian hierarchical model, which incorporates a hidden Potts model to project the irregularly distributed cells to a square lattice and a Markov random field prior model to identify regions in a heterogeneous pathology image. The model allows us to quantify the interactions between different types of cells, some of which are clinically meaningful. We use Markov chain Monte Carlo sampling techniques, combined with a double Metropolis-Hastings algorithm, in order to simulate samples approximately from a distribution with an intractable normalizing constant. The proposed model was applied to the pathology images of $205$ lung cancer patients from the National Lung Screening trial, and the results show that the interaction strength between tumor and stromal cells predicts patient prognosis (P = $0.005$). This statistical methodology provides a new perspective for understanding the role of cell-cell interactions in cancer progression.

AB - Digital pathology imaging of tumor tissues, which captures histological details in high resolution, is fast becoming a routine clinical procedure. Recent developments in deep-learning methods have enabled the identification, characterization, and classification of individual cells from pathology images analysis at a large scale. This creates new opportunities to study the spatial patterns of and interactions among different types of cells. Reliable statistical approaches to modeling such spatial patterns and interactions can provide insight into tumor progression and shed light on the biological mechanisms of cancer. In this article, we consider the problem of modeling a pathology image with irregular locations of three different types of cells: lymphocyte, stromal, and tumor cells. We propose a novel Bayesian hierarchical model, which incorporates a hidden Potts model to project the irregularly distributed cells to a square lattice and a Markov random field prior model to identify regions in a heterogeneous pathology image. The model allows us to quantify the interactions between different types of cells, some of which are clinically meaningful. We use Markov chain Monte Carlo sampling techniques, combined with a double Metropolis-Hastings algorithm, in order to simulate samples approximately from a distribution with an intractable normalizing constant. The proposed model was applied to the pathology images of $205$ lung cancer patients from the National Lung Screening trial, and the results show that the interaction strength between tumor and stromal cells predicts patient prognosis (P = $0.005$). This statistical methodology provides a new perspective for understanding the role of cell-cell interactions in cancer progression.

KW - Double Metropolis–Hastings

KW - Hidden Potts model

KW - Lung cancer

KW - Markov random field

KW - Mixture model

KW - Pathology image

KW - Potts model

KW - Spatial point pattern

UR - http://www.scopus.com/inward/record.url?scp=85073562318&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073562318&partnerID=8YFLogxK

U2 - 10.1093/biostatistics/kxy019

DO - 10.1093/biostatistics/kxy019

M3 - Article

C2 - 29788035

AN - SCOPUS:85073562318

VL - 20

SP - 565

EP - 581

JO - Biostatistics

JF - Biostatistics

SN - 1465-4644

IS - 4

ER -