Cezary Boldak

Influence of applied corneal endothelium image segmentation techniques on the clinical parameters

The corneal endothelium state is verified on the basis of an in vivo specular microscope image from which the shape and density of cells are exploited for data description. Due to the relatively low image quality resulting from a high magnification of the living, non-stained tissue, both manual and automatic analysis of the data is a challenging task. Although, many automatic or semi-automatic solutions have already been introduced, all of them are prone to inaccuracy. This work presents a comparison of four methods (fully-automated or semi-automated) for endothelial cell segmentation, all of which represent a different approach to cell segmentation; fast robust stochastic watershed (FRSW), KH method, active contours solution (SNAKE), and TOPCON ImageNET. Moreover, an improvement framework is introduced which aims to unify precise cell border location in images pre-processed with differing techniques. Finally, the influence of the selected methods on clinical parameters is examined, both with and without the improvement framework application. The experiments revealed that although the image segmentation approaches differ, the measures calculated for clinical parameters are in high accordance when CV (coefficient of variation), and CVSL (coefficient of variation of cell sides length) are considered. Higher variation was noticed for the H (hexagonality) metric. Utilisation of the improvement framework assured better repeatability of precise endothelial cell border location between the methods while diminishing the dispersion of clinical parameter values calculated for such images. Finally, it was proven statistically that the image processing method applied for endothelial cell analysis does not influence the ability to differentiate between the images using medical parameters.

A Texture-Based Energy for Active Contour Image Segmentation

This paper presents a two-dimensional deformable modelbased image segmentation method that integrates texture feature analysis into the model evolution process. Traditionally, the deformable models use edge and intensity-based information as the influencing image forces. Incorporation of the image texture information can increase the methods robustness and application possibilities. The algorithm generates a set of texture feature maps and selects the features that are best suited for the currently segmented region. Then, it incorporates them into the image energies that control the deformation process. Currently, the method uses the Grey Level Co-occurrence Matrix (GLCM) texture features, calculated using hardware acceleration. The preliminary experimental results, compared with outcomes obtained using standard energies, show a clearly visible improvement of the segmentation on images with various texture patterns.

Fast 3D Segmentation of Hepatic Images Combining Region and Boundary Criteria

Abstract A new approach to the liver segmentation from 3D images is presented and compared to the existing methods in terms of quality and speed of segmentation. The proposed technique is based on 3D deformable model (active surface) combining boundary and region information. The segmentation quality is comparable to the existing methods but the proposed technique is significantly faster. The experimental evaluation was performed on clinical datasets (both MRI and CT), representing typical as well as more challenging to segment liver shapes.

A Distributed Approach for Development of Deformable Model-Based Segmentation Methods

This paper presents a distributed solution for the development of deformable model-based medical image segmentation methods. The design and implementation stages of the segmentation methods usually require a lot of time and resources, since the variations of the tested algorithms have to be constantly evaluated on many different data sets. To address this problem, we extended our web platform for development of deformable model-based methods with an ability to distribute the computational workload. The solution was implemented on a computing cluster of multi-core nodes with the use of the Java Parallel Processing Framework. The experimental results show significant speedup of the computations, especially in the case of resource-demanding three-dimensional methods.

Toward Texture-Based 3D Level Set Image Segmentation

This paper presents a three-dimensional level set-based image segmentation method. Instead of the typical image features, like intensity or edge information, the method uses texture feature analysis in order to be more applicable to image sets withs distinctive patterns. The current implementation makes use of a set of Grey Level Co-occurrence Matrix texture features that are generated and selected according to the characteristics of the initial region. The region is then deformed using the level set-based algorithm to cover the desired image area. The generation of the texture features and the level set surface deformation scheme are performed with graphics card hardware acceleration. The preliminary experiments, performed on synthetic data sets, show promising segmentation results.