No abstract

No abstract

Segmentation of computed tomography (CT) images has provided promising methods of constructing precise 3-dimensional heart models. However, the process is labor intensive, because heart regions such as cardiac chambers and blood vessels have similar intensities and exist within a small space. In this paper, we present a tool to ef ciently segment cardiac chambers and blood vessels. We extend traditional region growing to be spatially controllable. A user places multiple seeds, each having a bounding area and a threshold, and our tool grows regions around each seed independently within its bounding area. To ef ciently specify the bounding area, we propose two types of seeds (i.e., sphere and cylinder). We also provide a negative seed that generates xed background to avoid over-extraction errors. We compared our tool with a traditional scissor tool and con rmed that ours signi cantly reduced the time required for a segmentation task. We also present segmentation results of CT images of hearts having congenital diseases to illustrate the feasibility of our tool.

This paper proposes a high-quality computed tomography (CT) image reconstruction method from low-dose X-ray projection data. A state-of-the-art method, proposed by Xu et al., exploits dictionary learning for image patches. This method generates an overcomplete dictionary from patches of standard-dose CT images and reconstructs low-dose CT images by minimizing the sum of a data fidelity and a regularization term based on sparse representations with the dictionary. However, this method does not take characteristics of each patch, such as textures or edges, into account. In this paper, we propose to classify all patches into several classes and utilize an individual dictionary with an individual regularization parameter for each class. Furthermore, for fast computation, we introduce the orthogonality to column vectors of each dictionary. Since similar patches are collected in the same cluster, accuracy degradation by the orthogonality hardly occurs. Our simulations show that the proposed method outperforms the state-of-the-art in terms of both accuracy and speed.