Tomasz Węgliński

Min-Cut/max-flow segmentation of hydrocephalus in children from CT datasets

This paper considers the problem of assessment of hydrocephalus in children using image processing and analysis algorithms. In particular, problem of lesion segmentation from CT brain scans is regarded. An approach for hydrocephalus segmentation based on min-cut/max-flow algorithm is pro-posed. Images after segmentation are next used to determine the volume of the lesion. Results of the proposed approach are presented, compared with the previous approaches proposed by the authors and discussed.

Accelerating the 3D Random Walker Image Segmentation Algorithm by Image Graph Reduction and GPU Computing

In this paper the problem of image segmentation using the random walker algorithm was considered. When applied to the segmentation of 3D images the method requires an extreme amount of memory and time resources in order to represent the corresponding enormous image graph and to solve the resulting sparse linear system. Having in mind these limitations the optimization of the random walker approach is proposed. In particular, certain techniques for the graph size reduction and method parallelization are proposed. The results of applying the introduced improvements to the segmentation of 3D CT datasets are presented and discussed. The analysis of results shows that the modified method can be successfully applied to the segmentation of volumetric images and on a single PC provides results in a reasonable time.

Automatic Assessment of Skull Circumference in Craniosynostosis

The premature fusion of one or more calvarias sutures of the infant’s skull causes a common pediatric disease called craniosynostosis. This condition causes a serious deformation of the head shape and may produce a noticeable disorder in the neuropsychological development of a child and can be treated only by a surgery. The fused sutures are typically confirmed by the computed tomography (CT) imaging. The surgical outcome and overall progress of the treatment is assessed based on a clinical judgment and an additional manual measurement of the head circumference (HC) index. The research presented in this paper considered the problem of an automatic calculation of the HC index based on CT scans. In particular, algorithms for the skull segmentation, determination of the head central sagittal plane and skull landmarks used for the calculation of the HC indices are introduced.

Survey of Modern Image Segmentation Algorithms on CT Scans of Hydrocephalic Brains

Abstract Paper presents the concept of applying image segmentation algorithms for precise extraction of cerebrospinal fluid (CSF) from CT brain scans. Accurate segmentation of the CSF from the intracranial brain area is crucial for further reliable analysis and quantitative assessment of hydrocephalus. Presented research was aimed at the comparison of effectiveness of three modern segmentation approaches used for this purpose. Specifically, random walk, level set and min-cut/max-flow algorithms were considered. The visual and numerical comparison of the segmentation results leads to conclusion that the most effective algorithm for the considered problem is level set, although the positive medical verification of the results revealed that either of considered algorithms can be successfully applied in the diagnostic applications.

The quantitative assessment of the pre- and postoperative craniosynostosis using the methods of image analysis.

This paper considers the problem of the CT based quantitative assessment of the craniosynostosis before and after the surgery. First, fast and efficient brain segmentation approach is proposed. The algorithm is robust to discontinuity of skull. As a result it can be applied both in pre- and post-operative cases. Additionally, image processing and analysis algorithms are proposed for describing the disease based on CT scans. The proposed algorithms automate determination of the standard linear indices used for assessment of the craniosynostosis (i.e. cephalic index CI and head circumference HC) and allow for planar and volumetric analysis which so far have not been reported. Results of applying the introduced methods to sample craniosynostotic cases before and after the surgery are presented and discussed. The results show that the proposed brain segmentation algorithm is characterized by high accuracy when applied both in the pre- and postoperative craniosynostosis, while the introduced planar and volumetric indices for the disease description may be helpful to distinguish between the types of the disease.

A Competitive Study of Graph Reduction Methods for Min S-T Cut Image Segmentation

Abstract When applied to the segmentation of 3D medical images, graph-cut segmentation algorithms require an extreme amount of memory and time resources in order to represent the image graph and to perform the necessary processing on the graph. These requirements actually exclude the graph-cut based approaches from their practical application. Hence, there is a need to develop the dedicated graph size reduction methods. In this paper, several techniques for the graph size reduction are proposed. These apply the idea of superpixels. In particular, two methods for superpixel creation are introduced. The results of applying the proposed methods to the segmentation of CT datasets using min-cut/max-flow algorithm are presented, compared and discussed.

Enhancement of Low-Dose CT Brain Scans Using Graph-Based Anisotropic Interpolation

This paper considers the problem of enhancement of low-dose CT images. These images are usually distorted by the artifact similar to ‘film grain’, which affects image quality and hinders image segmentation. The method introduced in this paper reduces influence of the distortion by retrieval of pixel intensities under the ‘grains’ using graph-based anisotropic interpolation. Results of applying the introduced method to low-dose CT scans of hydrocephalic brains are presented and discussed. The influence of the introduced method on the accuracy of image segmentation is analysed.