Automatic identification of angiogenesis in double stained images of liver tissue

Abstract

BackgroundTo grow beyond certain size and reach oxygen and other essential nutrients, solid tumors trigger angiogenesis (neovascularization) by secreting various growth factors. Based on this fact, several researches proposed that density of newly formed vessels correlate with tumor malignancy. Vessel density is known as a true prognostic indicator for several types of cancer. However, automated quantification of angiogenesis is still in its primitive stage, and deserves more intelligent methods by taking advantages accruing from novel computer algorithms.ResultsThe newly introduced characteristics of subimages performed well in identification of region-of-angiogenesis. The proposed technique was tested on 522 samples collected from two high-resolution tissues. Having 0.90 overall f-measure, the results obtained with Support Vector Machines show significant agreement between automated framework and manual assessment of microvessels.ConclusionThis study introduces a new framework to identify angiogenesis to measure microvessel density (MVD) in digitalized images of liver cancer tissues. The objective is to recognize all subimages having new vessel formations. In addition to region based characteristics, a set of morphological features are proposed to differentiate positive and negative incidences.

Sparse Non-negative Matrix Factorization (SNMF) based color unmixing for breast histopathological image analysis

“…For instance, CD31, CD34, and CD105 proteins are found on some specific types of cancerous cells in human breast histological tissue, respectively. As they are indicators of angiogenesis, the immunostaining of these proteins can be used to evaluate the degree of tumor angiogenesis in histological tissue sections [3,5,8,22]. In clinical practice, the malignancy grading of the tumor and angiogenic activity are largely based on the intensity, architectural, and vascular density features of brown diaminobenzidine (DAB) in IHC stained breast tissue [2].…”

AutoTag and AutoSnap: Standardized, semi-automatic capture of regions of interest from whole slide images

“…It is also not possible to create images at the coordinates and no grids are overlaid. Microvessel counting can be performed manually on the images created by this process, or can be used for automatic image analysis when the digital grid is discarded [1] , [8] .…”

Proceedings of the 2009 MidSouth Computational Biology and Bioinformatics Society (MCBIOS) Conference

“…Mete et al [ 47 ] present a novel digital image analysis approach to the automated evaluation of angiogenesis in Liver Cancer. The method identifies regional, morphological and fractal features and helps measure micro-vessel density on digitized images of liver tumor sections.…”