Abstract:In this study, we present several image segmentation techniques for various image scales and modalities. We consider cellular-, organ-, and whole organism-levels of biological structures in cardiovascular applications. Several automatic segmentation techniques are presented and discussed in this work. The overall pipeline for reconstruction of biological structures consists of the following steps: image pre-processing, feature detection, initial mask generation, mask processing, and segmentation post-processing. Several examples of image segmentation are presented, including patient-specific abdominal tissues segmentation, vascular network identification and myocyte lipid droplet micro-structure reconstruction.
Aortic valve disease accounts for 45% of deaths from heart valve diseases.% \cite{Coffey2015}. An appealing approach to treat aortic valve disease is surgical replacement of the valve leaflets based on chemically treated autologous pericardium. This procedure is attractive due to its low cost and high effectiveness. We aim to develop a computational technology for patient-specific assessment of reconstructed aortic valve function that can be used by surgeons at the preoperative stage. The framework includes automatic computer tomography image segmentation, mesh generation, simulation of valve leaflet deformation. The final decision will be based on uncertainty analysis and leaflet shape optimization. This paper gives a proof of concept of our methodology: simulation methods are presented and studied numerically.
Generation of three-dimensional personalized geometric models of anatomical structures is an important process for many practical tasks: computer-aided diagnosis, treatment planning and numerical modeling in biomedical applications. Despite many efforts done by different research groups, automatic segmentation of organs still does not have any general solution. The main difficulties are caused by peculiarities of different medical imaging modalities, image variability (for the same modality) resulting from the wide range of imaging devices, noise and artifacts, large patient anatomical variability and overlapping of intensity ranges of neighboring anatomical structures. In this article, we propose segmentation method based on analysis of texture features and developed specially for segmentation of abdominal organs. Its main advantage is robustness to interpatient gray level and anatomical variability.The proposed method was validated on the patient data. The method implementation was accelerated using graphics processing unit (GPU).
K E Y W O R D Sabdomen segmentation, personalized anatomical models, texture analysis
The work addresses segmentation techniques for generation of individualized computational domains on the basis of medical imaging dataset. The computational domains will be used in 3D electrophysiology models and 3D-1D coupled hemodynamics models. Several techniques for user-guided and automated segmentation of soft tissues, segmentation of vascular and tubular structures, generation of centerlines, 1D network reconstruction, correction and local adaptation are examined. We propose two algorithms for automatic vascular network segmentation and user-guided cardiac segmentation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.