Construction of Cardiac Anatomical Models Using Deformable Model Methods
نویسندگان
چکیده
Die elektrophysiologische und elektromechanische Darstellung des Herzens sind die wichtigsten Aspekte bei der mathematischen Modellierung dieses Organs. Vorraussetzung für eine solche Modellierung ist die korrekte Segmentation. Die Segmentation im kardiologischen Bereich gestaltet sich als besonders schwierig, da das Herz eine komplizierte Struktur besitzt, das Bildmaterial meist verrauscht ist und eine geringe Auflösung besitzt. Herkömmliche Verfahren wie Thresholding, Region-growth und Watershed liefern hier keine guten Ergebnisse. In diesem Artikel wurden die „Active Contour“-Segmentationsmethode und das „Statistical Shape Model“ genutzt, um kardiologisches Bildmaterial zu segmentieren. Im Prinzip wird ein statistical Shape model trainiert und angewendet, um das Herz grob zu semgentieren. Anschliessend wird eine Relaxationsphase angewendet, in der das active contour-Verfahren genutzt wird, um das „statistic shape model“ richtig einzupassen. Das Ergebnis der Arbeit ist, daß laut Autoren die kombinierte „active contour“/“statistical shape model“-Methode besser als herkömmliche automatische Segmentierungsverfahren arbeitet. Die Qualität der Resultate ist sogar vergleichbar mit einer manuellen Segmentation.
منابع مشابه
A Hybrid 3D Colon Segmentation Method Using Modified Geometric Deformable Models
Introduction: Nowadays virtual colonoscopy has become a reliable and efficient method of detecting primary stages of colon cancer such as polyp detection. One of the most important and crucial stages of virtual colonoscopy is colon segmentation because an incorrect segmentation may lead to a misdiagnosis. Materials and Methods: In this work, a hybrid method based on Geometric Deformable Models...
متن کاملI-48: Ultrasound Deformable Model for Virtual Surgery Simulation of Oocyte Retrieval in Infertility Programs
Background The use of a medical simulator should enhance the goals of minimally invasive surgery: patient safety, cosmesis, shortening the length of hospital admissions, and reducing cost. Using an innovative approach to the handling of ultrasound images in virtual reality simulation, this article describes a process that employs a hybrid model of deformable models that can be applied in the te...
متن کامل3D Anatomical Shape Atlas Construction Using Mesh Quality Preserved Deformable Models
The construction of 3D anatomical shape atlas has been extensively studied in medical image analysis research for a variety of applications. Among the multiple steps of shape atlas construction, establishing anatomical correspondences across subjects is probably the most critical and challenging one. The adaptive focus deformable model (AFDM) [16] was proposed to tackle this problem by exploiti...
متن کاملO-39: Ultrasound Deformable Model for Virtual Surgery Simulation of Oocyte Retrieval in Infertility Programs
Background The use of a medical simulator should enhance the goals of minimally invasive surgery: patient safety, cosmesis, shortening the length of hospital admissions, and reducing cost. Using an innovative approach to the handling of ultrasound images in virtual reality simulation, this article describes a process that employs a hybrid model of deformable models that can be applied in the te...
متن کاملSpatio-Temporal Free-Form Registration of Cardiac MR Image Sequences
In this paper we present two registration algorithms for the spatio-temporal alignment of cardiac MR image sequences. Both algorithms have the ability to correct spatial misalignment between the images sequences caused by global and local shape differences. In addition, they have the ability to correct temporal misalignment caused by differences in the length of the cardiac cycles and by differ...
متن کاملUnified Deterministic/Statistical Deformable Models for Cardiac Image Analysis
OF THE DISSERTATION Unified Deterministic/Statistical Deformable Models for Cardiac Image Analysis by Sharath Kumar Gopal Doctor of Philosophy in Computer Science University of California, Los Angeles, 2016 Professor Demetri Terzopoulos, Chair This thesis proposes to fully automate the shape and motion reconstruction of non-rigid objects from visual information using a unified deterministic/sta...
متن کامل