A Stochastic Polygons Model for Glandular Structures in Colon Histology Images
- 15 May 2015
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 34 (11), 2366-2378
- https://doi.org/10.1109/tmi.2015.2433900
Abstract
In this paper, we present a stochastic model for glandular structures in histology images of tissue slides stained with Hematoxylin and Eosin, choosing colon tissue as an example. The proposed Random Polygons Model (RPM) treats each glandular structure in an image as a polygon made of a random number of vertices, where the vertices represent approximate locations of epithelial nuclei. We formulate the RPM as a Bayesian inference problem by defining a prior for spatial connectivity and arrangement of neighboring epithelial nuclei and a likelihood for the presence of a glandular structure. The inference is made via a Reversible-Jump Markov chain Monte Carlo simulation. To the best of our knowledge, all existing published algorithms for gland segmentation are designed to mainly work on healthy samples, adenomas, and low grade adenocarcinomas. One of them has been demonstrated to work on intermediate grade adenocarcinomas at its best. Our experimental results show that the RPM yields favorable results, both quantitatively and qualitatively, for extraction of glandular structures in histology images of normal human colon tissues as well as benign and cancerous tissues, excluding undifferentiated carcinomas.Keywords
Funding Information
- Qatar Foundation (NPRP5-1345-1-228)
This publication has 24 references indexed in Scilit:
- Computational pathology: Challenges and promises for tissue analysisComputerized Medical Imaging and Graphics, 2011
- Automatic segmentation of colon glands using object-graphsMedical Image Analysis, 2010
- Tumour differentiation grade is associated with TNM staging and the risk of node metastasis in colorectal cancerActa Oncologica, 2009
- An image analysis approach for automatic malignancy determination of prostate pathological imagesCytometry Part B: Clinical Cytometry, 2007
- Image segmentation using voronoi polygons and MCMC, with application to muscle fibre imagesJournal of Applied Statistics, 2006
- Gleason grading and prognostic factors in carcinoma of the prostateLaboratory Investigation, 2004
- Reversible jump Markov chain Monte Carlo computation and Bayesian model determinationBiometrika, 1995
- pathological prognostic factors in breast cancer. I. The value of histological grade in breast cancer: experience from a large study with long‐term follow‐upHistopathology, 1991
- Measures of the Amount of Ecologic Association Between SpeciesEcology, 1945