Stent implantation is the most common treatment of coronary heart disease, one of the major causes of death worldwide. During a stenting procedure, the clinician inserts interventional devices inside the patient's vasculature. The navigation of the devices inside the patient's anatomy is monitored in real-time, under X-ray fluoroscopy. Three specific interventional devices play a key role in this procedure: the guide-wire, the angioplasty balloon and the stent. The guide-wire appears in the images as a thin curvilinear structure. The angioplasty balloon, that has two characteristic markerballs at its extremities, is mounted on the guide-wire. The stent is a 3D metallic mesh, whose appearance is complex in the fluoroscopic images. Stents are barely visible, but the proper assessment of their deployment is key to the procedure. The objective of the work presented in this thesis is twofold. On the first hand, we aim at designing, studying and validating image processing techniques that improve the visualization of stents. On the second hand, we study the processing of curvilinear structures (like guide-wires) for which we propose a new image processing technique. We present algorithms dedicated to the 2D and 3D visualization of stents. Since the stent is hardly visible, we do not intend to directly locate it by image processing means in the images. The position and motion of the stent are inferred from the location of two landmarks: the angioplasty balloon and of the guide-wire, which have characteristic shapes. To this aim, we perform automated detection, tracking and registration of these landmarks. The cornerstone of our 2D stent visualization enhancement technique is the use of the landmarks to perform motion compensated noise reduction. We evaluated the performance of this technique for 2D stent visualization over a large database of clinical data (nearly 200 cases). The results demonstrate that our method outperforms previous state of the art techniques in terms of image quality. A comprehensive validation confirmed that we reached the level of performance required for the commercial introduction of our algorithm. It is currently deployed in a large number of clinical sites worldwide. The 3D stent visualization that we propose, uses the landmarks to achieve motion compensated tomographic reconstruction. We show preliminary results over 22 clinical cases. Our method seems to outperform previous state of the art techniques both in terms of automation and image quality. The previous stent visualization methods involve the segmentation of the part of the guide-wire extending through the stent. We propose a generic tool to process such curvilinear structures that we call the Polygonal Path Image (PPI). The PPI relies on the concept of locally optimal paths. One of its main advantages is that it unifies the concepts of several previous state of the art techniques in a single formalism. Moreover the PPI enables to control the smoothness and the length of the structures to segment. Its parametrization is simple and intuitive. In order to fully benefit from the PPI, we propose an efficient scheme to compute it. We demonstrate its applicability for the task of automated guide-wire segmentation, for which it outperforms previous state of the art techniques
Identifer | oai:union.ndltd.org:CCSD/oai:tel.archives-ouvertes.fr:tel-00786326 |
Date | 09 January 2012 |
Creators | Bismuth, Vincent, Bismuth, Vincent |
Publisher | Université Paris-Est |
Source Sets | CCSD theses-EN-ligne, France |
Language | English |
Detected Language | English |
Type | PhD thesis |
Page generated in 0.2457 seconds