Search

In this paper, we present a textural features analysis applied to a medical image segmentation problem where other methods fail, i.e. the localization of thrombotic tissue in the aorta. This problem is extremely relevant because many clinical applications are being developed for the computer assisted, image driven planning of vascular intervention, but standard segmentation techniques based on edges or gray level thresholding are not able to differentiate thrombus from surrounding tissues like vena, pancreas having similar HU average and noisy patterns. Our work consisted in a deep analysis of the texture segmentation approaches used for CT scans, and on experimental tests performed to find out textural features that better discriminate between thrombus and other tissues. Finding that Run Length codes are those performing better both in literature and experiments, we tried to understand the reason of their success suggesting a revision of this approach with feature selection and the use of specifically thresholded Run Lengths that improve the discriminative power of measures reducing the computational cost.

The recent diffusion of web technologies in medical environments is deeply changing the work of radiologists and surgeons, allowing them to store and retrieve patient information, images but also reports and elaborated data. Among elaborated data, 3D reconstructions are becoming more popular because they allow, for example, a precise evaluation of the geometry of organs thus making the measurements necessary for surgical planning easier and more accurate. In this paper, we describe the architecture of a service for 3D model quantitative evaluation, specialized to the analysis of Abdominal Aortic Aneurysms. It is based on a centralized server that stores model images and measurement information and exchanges data with clients using web standards like XML, DICOM3 and VRML97. This allows the secure exchange of heterogeneous data (images, 3D models and reports) that is necessary for complex applications. Furthermore, this arrangement ensures that each step of the complex medical and IT-related procedure is performed by the most trained and expert personnel available, even if he/she is not at the end user location. Easy 3D model measurement and analysis is ensured by using VRML97 and External Authoring Interface [EAI Working Group, “Web site and mailing list” http://www.vrml.org/WorkingGroups/vrml-eai ]; standardization in patient data and report management is ensured using DICOM3 and XML.

We tested a novel approach for the quantitative remote analysis of abdominal aortic aneurysm by reconstructing their 3D geometry and topological structure (i.e. centerline path) and put them on the web as VRML97 models including specialized code enabling the user to perform guided inspection and measurements useful for surgical planning.