A model of the spatial tumour heterogeneity in colorectal adenocarcinoma tissue

Abstract

BackgroundThere have been great advancements in the field of digital pathology. The surge in development of analytical methods for such data makes it crucial to develop benchmark synthetic datasets for objectively validating and comparing these methods. In addition, developing a spatial model of the tumour microenvironment can aid our understanding of the underpinning laws of tumour heterogeneity.ResultsWe propose a model of the healthy and cancerous colonic crypt microenvironment. Our model is designed to generate synthetic histology image data with parameters that allow control over cancer grade, cellularity, cell overlap ratio, image resolution, and objective level.ConclusionsTo the best of our knowledge, ours is the first model to simulate histology image data at sub-cellular level for healthy and cancerous colon tissue, where the cells have different compartments and are organised to mimic the microenvironment of tissue in situ rather than dispersed cells in a cultured environment. Qualitative and quantitative validation has been performed on the model results demonstrating good similarity to the real data. The simulated data could be used to validate techniques such as image restoration, cell and crypt segmentation, and cancer grading.Electronic supplementary materialThe online version of this article (doi:10.1186/s12859-016-1126-2) contains supplementary material, which is available to authorized users.

Subcellular protein expression models for microsatellite instability in colorectal adenocarcinoma tissue images

“…For modelling the different cell compartments, we use the deformed circle model used in Kovacheva et al [ 18 ]. When we are generating cell organelles of a particular type, we draw model parameter values from the relevant PDFs as described above.…”

“…12 b ). To generate a realistic texture for this protein we use the chromatin texture used for the nuclear channel of the THeCoT model [ 18 ]. If the user specifies a mutation in the MSH2 gene, the protein is not expressed in the epithelial cells.…”

“…However, tissue microenvironment was not taken into account in that work. More recently, a model has been proposed for simulating the microenvironment of healthy and cancerous colon tissue [ 17 , 18 ]. This model has a number of user-defined parameters that allow control over the tissue appearance and is capable of simulating microscopy images for cancers of various differentiation grade.…”

“…These proteins were selected as a case study to illustrate how a variety of proteins can be included within the framework to enable the generation of synthetic multiplex fluorescence image data of both healthy and cancerous tissue samples. The models have been integrated within a model of the tumour microenvironment of colorectal cancer [ 17 , 18 ], and take into account the cell phenotypes present in the tissue as well as the presence of relevant gene mutations. We have also developed models for a number of subcellular organelles, which were learned from real high-resolution confocal microscopy images.…”

Segmentation of digitized histological sections for quantification of the muscularized vasculature in the mouse hind limb

“…Features have been extracted from prostate histology in order to determine the Gleason grade of prostate cancer (Niazi et al, 2016). Modelling of colorectal adenocarcinoma histology on H&E has been performed to assess tissue morphology parameters (Kovacheva et al, 2016). Regarding IHC, vascular endothelial cell detection has been performed in order to assess tumour microvessel density in previous work (Kather et al, 2015;Tsou et al, 2015).…”